Beverly P. Woolf - US grants

The focus of this project is building a mechanism for managing intelligent tutoring discourse and on automating the process of transferring such knowledge from teachers to the tutoring system. The first research area focuses on problems of dialogue management for science education and implements a discourse framework-a virtual machine-that enables tutoring feedback in the form of examples, analogies, and simulations within interactive simulations. The virtual machine is being implemented within simulations that allow a student to test his/her hypothesis about domains such as physics and astronomy, specifically statics dynamics, and celestial mechanics. The second component of this work is automation-the process of transferring knowledge from experts, such as teachers, psychologists, and curriculum developers, to the intelligent tutors. The project seeks to build programming-free tools for representing tutoring strategies, domain knowledge, and intervention tactics. These tools are designed to assist teachers in visualizing their science knowledge in a form amenable to Artificial Intelligence systems and in encoding this knowledge in the form of examples, analogies, or remediation techniques.

Shiladitya DasSarma DUE 9551531 U of Massachusetts Amherst FY1995 $273,459 Amherst, MA 1003 ILI - Leadership in Laboratory Development: Life Sciences Title: Intelligent Tutor for Concepts in Molecular Genetics This project is developing a computer laboratory fop tutoring undergraduate students in fundamental concepts of molecular genetics. The topics covered include (a) DNA structure and replication, (b) RNA transcription, translation, and splicing, (c) genetic recombination, repair, and transposition, (d) genetic engineering and recombinant DNA technology, and (e) modern genomic analysis and societal implications. The major challenges in teaching these fundamental genetic concepts to undergraduates are (1) transmitting the visual imagery of dynamic molecular processes, (2) providing a solid intellectual framework to explore interrelationships between genetic processes, and (3) at more advanced levels, conveying the experimental basis for evolution of genetic principles. The project exploits recent advances in computer hardware (increased memory size and data storage) and software (intelligent tutoring systems) to develop a multimedia tutorial package which conveys the visual imagery, conceptual relationships, and experimental basis of molecular genetics in a deeper and more effective manner than currently possible through lectures or textbooks. The electronic tutor, named "MOLGENT", is being tested during its developmental phase, in a variety of undergraduate classes, including introductory biology, microbiology, and molecular and cellular biology courses, and an innovative senior-level course entitled "Concepts in Molecular Genetics" at the University of Massachusetts at Amherst. The effectiveness of tutorials is being monitored and improved through student discuss ion groups. Once developed, the prototype software will be promoted via demonstrations at the educational section of meetings of biological societies (e.g. American Society for Microbiology, Genetics Society of America, and American Society for Biochemistry and Molecular Biology) and distributed broadly via publishers.

9555737 Beal Mathematics is required for work in most sciences, yet many girls lose confidence in their ability to do math and take the course requirements, thus ensuring that women will be underrepresented in science. Prior research indicates that a critical factor contributing to girls' declining self confidence in their math competence is the type of instruction and performance feedback typically provided by classroom teachers. The goal of this project is to utilize the power of intelligent computer based tutoring systems to enhance the confidence, motivation, and skill mastery of female students in elementary grades 3 - 5. We will apply intervention before late elementary school, the point at which gender differences in attitudes towards math become apparent. The intelligent computer tutor is designed on the basis of research indicating that female students benefit from and appreciate pedagogy that reflects a) exploration rather than competition; b) an interface and environment that includes females (versus software based on male students' interests); c) the provision of confidence enhancing feedback that sets high expectations, provides specific information about how to overcome errors, and emphasizes appropriate effort rather than native ability as key to math success.

Mathematics is a critical filter for girls' participation in science and engineering careers, yet many girls dislike and avoid math, and are therefore underprepared for college science majors and graduate programs. The goal of this project is to increase girls' interest in math and their confidence in their ability to learn math, through the power of intelligent computer instructional technology. In collaboration with teacher partners (classroom teachers, and math and computer specialists) the awardee has developed a computer tutor, WhaleWatch, for teaching fractions to elementary school girls and boys. Preliminary experiments indicate that girls who work with WhaleWatch show enhanced math self concept and also place a higher value on the AnimalWatch, to include a) 20 hours of mathematics activities and biology; b) extensive graphics and visualization tools for instruction; and c) enhanced instruction and help features that are individually tailored to each student's progress. The impact of AnimalWatch on girls' math self concept, their beliefs in the value of learning math, and their emotions and attributions about math performance will be evaluated in fifth grade classrooms in collaborating school districts, to identify the learning conditions that are most beneficial for girls. The effects of AnimalWatch on teachers' expectations about female students will also be evaluated. To effect systemic change in math instruction, teachers will be provided with and trained in the use of AnimalWatch, which will be distributed via CD-ROM.

The Web provides thousands of resources for thousands of communities. However, these resources are difficult to locate and do not coordinate, resulting in unproductive experiences for users. The PIs propose an agent-based framework to reason about and retrieve appropriate materials, providing meaningful user guidance. These agents will be in the area of instructional technology and will employ user modeling and planning to provide robust performance despite changing availability of resources, modifications in the network configuration and variable user needs. Agents will communicate and select specialized learning resources to solve aspects of larger learning problems. They will negotiate distribution of learning tasks among available resources ensuring that all aspects of the total problem are addressed in a coordinated manner. A simulated large-scale on-line learning community will be constsructed to demonstrate the intended behavior. The simulation will simplify learning and tutoring yet will include conflict resolution and propose methods to avoid failure. It will illustrate qualitative, quantitative and visual benefits of the integrated community and explore the properties of on-line communities, anticipating and avoiding problems that arise as massive on-line learning communities develop. The PIs will demonstrate which techniques are productive, which impractical and which are scaleable in a massive network.

Visualization and spatial reasoning are integral components of intelligent systems. They form the basis for understanding a wide variety of topics across science, mathematics and engineering, including molecular structures, topologies, motion and forces, and manufacturing processes. Historically, many students, especially female students, have had difficulty acquiring visualization and spatial reasoning skills, creating potential barriers to advancement in science, mathematics and engineering. Within engineering, faculty have found it both challenging and time consuming to teach topics that require strong visualization and spatial reasoning skills, topics such as product design, manufacturing, and engineering modeling and analysis. Similarly, engineering students have found these topics unmotivating and difficult to comprehend. With the advent of sophisticated computer graphics and animation, one might expect that the need for human visualization skills has been eliminated. But this is not the case. Computers cannot replace the need for these skills in science and engineering just as calculators have not replaced the need for quantitative skills. Thus this project has three goals: l) to advance our understanding of human visualization and spatial reasoning; 2) to use this knowledge to develop computer-based visualization instruction; and 3) to incorporate this instruction into intelligent multimedia tutors in ways that maximize their effectiveness for a broad mix of students while minimizing the development time and cost for the faculty involved. The achievement of such goals has required that we put together a team of researchers with backgrounds in psychology, education, engineering and computer science.

Although visualization and spatial reasoning are fundamental cognitive skills, the cognitive processes that govern them are poorly understood. Thus, as our first goal, we will undertake during year l a series of experiments in our Eye Movement Laboratories designed to test alternative theories of how individuals represent mentally and reason spatially about 3-D objects and their transformations. We will use the detailed eye movement data as a window on the underlying cognitive processes. We have made similar use of such data in reading, visual search and scene perception (Rayner, l992, l998; Rayner & Pollatsek, l992). We expect these data to reveal large, stable differences among individuals, not only between low and high spatial ability participants, but also within groups of participants of similar spatial abilities.

Visualization and spatial reasoning skills are critical to the understanding of many concepts within science and engineering. Yet, we have little understanding of how we can best teach these skills. Thus, as our second goal, we will develop during year 2 computer-based visualization skills instruction modules based on what we have learned during the first year about the problems that individuals have and the strategies that work successfully, modules that will take advantage of current advances in instructional theories and technologies. Having developed the modules, we will then conduct a series of experiments in the second year designed to test theoretically motivated methods for delivering visualization instruction that improve the content of the instruction delivered to high and low spatial ability learners, optimize the mix of part- and whole-task training, and maximize the number of individuals that develop expertise.

Biological Sciences (61) The Protein Explorer features discovery-based, interactive learning with built-in quizzing. There are three levels of presentation: basic, an introduction to the principles of protein structure; guided, an intermediary level offering a dozen built-in molecules; and advanced. Guided Protein Explorer leads the student through a series of fundamental questions, automatically rendering the molecule in the best manner for observing the answer to each question, while quizzing the student. It also enables students to use the same series of questions to explore any of the 10,000 macromolecules available from the Protein Data Bank To assist in interpreting the images of an unknown molecule, built-in molecules which illustrate major categories (e.g. soluble vs. lipid-seeking) are offered for comparison. As an advance over the existing software (RasMol and Chime) serving as a base for this product, no specialized technical knowledge of the software is required to use the basic or guided forms. Protein Explorer is freely downloadable from an educational macromolecular visualization website, www.rcsb.org, currently visited by 5,000-6,000 people per week.

Some national assessments show that the gender gap in math achievement has narrowed dramatically in the last decade, and that there has been a significant increase in the number of mathematics courses taken by high school women. However, other data indicate that female students do not confront the critical transition from high school to college with deep, conceptually based mathematical competence that supports entry into STEM (science, technology, engineering, mathematics) careers. Specifically, female students perform much less well than males on complex problem solving, when they must apply novel problem solving approaches, and when they must work under time pressure or transfer skills to problems not previously seen. Other research points to differences in female and male students learning styles; female students require more structured, concrete and repetitive instruction whereas males do equally well with more abstract hints and help, suggesting that they have a deeper understanding of mathematical concepts. A related concern is that female students increased math course taking has not translated into a higher number of women in the pipeline towards careers; that is, women are taking additional math but are not planning to utilize it in their careers. The consequences are seen in the continued under-representation of females in STEM majors and careers, and the critical lack of mathematically sophisticated workers in numbers sufficient to meet our nations needs.

This project is designed to investigate the factors that contribute to female students shallower mathematical competence, as well as the learning styles that characterize male and female students at the critical transition from high school to college. Our investigations take place in the context of a multimedia, multi-component simulation environment: AnimalWorld. AnimalWorld provides high school women (and men) with 1) an intelligent tutor for high school mathematics (fractions; algebra; geometry; ratios/proportions/decimals; probability) that provides gender adaptive instruction and allows for analysis of male and female learning styles; 2) a virtual mentor component, in which students who are solving math problems in the simulated world can meet real female researchers and experts (through video clips embedded in the simulation) who discuss their training and the importance of math for their careers; 3) a math at your fingertips module in which students periodically rehearse math facts to free cognitive resources for higher-order problem solving, predicting increased math test scores; 4) a module to enhance students spatial cognition through dynamic manipulation of objects in simulated three-dimensional environments, which will allow us to provide a strong test of the hypothesis that females poorer math achievement reflects less well developed spatial cognition; and 5) an SAT-Math preparation module designed to narrow the striking gender gap on this critical achievement test.

Our prediction is that female students who work with AnimalWorld will show significant increases in their complex math problem-solving skill, including their SAT-Math exam performance; that gender adaptive instruction will foster greater conceptual understanding in female students; and that virtual mentors will encourage female students to report greater interest in STEM careers. The results will increase our understanding of male and female learning styles, as well as provide new approaches to effective mathematics instruction for all students.

Mathematical Sciences (21)

This project adapts a proven online Web-based learning system for the mathematics curriculum and develops curricular materials for the first calculus course. The system provides electronic homework, allowing instructors to easily create assignments that help students understand and master the material covered in class. It has already been extended in chemistry to support more interactive learning activities such as guided discovery and intelligent tutoring. The products of this project include a suite of basic online homework activities that cover the curricula of the first semester of the calculus course sequence, interactive guided discovery modules focused on topics and concepts where animation and simulation can be employed to support learning, and intelligent tutors that focus on difficult but key concepts in the curriculum and adaptively assist students in developing their understanding of them. All interactive activities are integrated into the basic online system, which records student progress for instructor review. A computer laboratory is created to support students doing online learning activities. Math faculty will create content for the homework system and interactive activities. Project staff modify the system to better support mathematics, train instructors in system use, help design interactive activities, and implement many of these activities. This project addresses a critical national need to improve the mathematical preparation of undergraduates from a wide variety of disciplines.

Chemistry (12)
The proposed project has three goals: (1) to increase the retention rate for students in basic organic chemistry courses, (2) to enhance the ability of students in these courses to use scientific reasoning, and (3) to drive innovation in the teaching of organic chemistry. These are accomplished by creating interactive learning software delivered to students over the web by a versatile platform called OWL developed at the institution and now used in general chemistry. The software consists of guided discovery modules and intelligent tutors. Using guided discovery modules, students run virtual experiments, interpret data, and then form, test, and revise hypotheses. The students' scientific reasoning ability is enhanced while gaining an appreciation for the experimental basis for the organic chemistry they are learning. Using intelligent tutors, students explore topics like SN1, SN2, E1, & E2 reactivity and synthesis. Students receive immediate feedback, tuned to each individual's level of mastery. Combined with regular electronic homework, also delivered by OWL, students are prompted to keep current in their courses by participating actively in their own learning. Student participation in all components of this system, called "Organic OWL," is encouraged by allotment of credit for passed homework and completed modules and tutors. The learning power of the software will be enhanced significantly by a provision for students to draw and to submit their own structures using the ChemDraw and ChemFinder programs, in cooperation with CambridgeSoft Inc., Cambridge, MA. The materials are text-independent, and the OWL delivery platform are to be available commercially within one year of the start of the project.

Computer Science (31)

This country urgently needs more people trained in computer science. At present the number of students entering the CS pipeline in American colleges and universities is not increasing and, in the case of female and minority students, is actually declining. Thus if we are to meet our national need for CS researchers, software developers, and information technology workers, it is vital to attract, engage, support, and retain computer science students more effectively.

Our project addresses these issues by developing a prototype for innovative multimedia instructional software for introductory computer programming classes. These software tools will be built on top of the existing OWL on-line instruction system, a system that has been used with great success in chemistry, physics and mathematics. The array of proposed software tools is designed to make the techniques of introductory programming and problem-solving more accessible for students with a wide range of backgrounds in computing.

This proof of concept project will include a fairly extensive suite of "single-step" OWL-based learning activities, a small collection of more complex, multistage problem solving exercises, an evaluation plan for a full study, including baseline data for that study, and a preliminary statistical assessment of the performance of CS-OWL machinery in our classes.

- Construction of a suite of questions about code behavior by creating multiple choice and fill-in-the-blank questions for beginning CS1 activities, and using existing OWL machinery to automate grading, gather statistics, and keep class records for participating students
- Construction of a collection of OWL-embedded interactive activities, which illustrate and develop elementary OO programming skills.
- Develop the indexing scheme for a database of elementary Java code examples, for the purpose of developing student reading skills, and for the purpose of supplying raw material for other CS-OWL activities.
- Development of guided problem solving exercises, which are designed to teach multi-step problem solving skills. develop three or four multi-stage problem-solving examples
- Develop an evaluation plan in which lays the groundwork for a future full evaluation by establishing a baseline assessment of student performance in our CS1 classes over the next several semesters. We also expect to provide some preliminary statistics that show some early signs that our CS-OWL system is an effective learning tool.

The primary objective of this project is to develop new methods for optimizing an automated pedagogical agent to improve its teaching efficiency through customization to individual students based on information about their responses to individual problems, student individual differences such as level of cognitive development, spatial ability, memory retrieval speed, long-term retention, effectiveness of alternative teaching strategies (such as visual vs. computational solution strategies), and degree of engagement with the tutor. An emphasis will be placed on using machine learning and computational optimization methods to automate the process of developing efficient Intelligent Tutoring Systems (ITS) for new subject domains. The approach is threefold.
First, a methodology based on hierarchical graphical models and machine learning will be developed and evaluated for automating the creation of student models with rich representations of student state based on data collected from populations of students over multiple tutoring episodes. Second, methods will be developed and evaluated for deriving pedagogical decision strategies that are effective and efficient not just over the short-term (from one math problem to the next one), but over the long-term where retention over a period of at least one month is the objective. Third, a systematic study will be conducted of the role that known and powerful latent and instructional variables can have on performance through their inclusion in student models. Research in cognitive and educational psychology clearly shows the critical role that latent variables such as short-term memory and engagement play in learning, and that instructional variables such as over-learning and review, and massed and distributed practice have on the rate at which material is learned. The investigators jointly have strengths in the areas of intelligent tutoring, machine learning and optimization, and cognitive, mathematical and educational psychology, strengths that are needed in order to make the synergistic advances that are being proposed. Our preliminary simulations and classroom experiments suggest that we can significantly reduce the time it takes students to learn new material based on improved pedagogical decisions.
For intellectual merit, he proposed research should advance fundamental knowledge of the learning and teaching of basic mathematics and more advanced algebra and geometry. It should add to the set of growing statistical and computational techniques that are available to estimate the complex hidden hierarchical structures that govern human behavior. The research should also significantly broaden the capabilities of machine learning systems by addressing learning scenarios that are grounded on the real and challenging problem of mathematics education than the abstract scenarios typically studied at present. For broader impact, this foundational educational research will lead to the broadening of participation of underrepresented groups, especially women, in a variety of science, technology, engineering and mathematics (STEM) disciplines. It will advance discovery and understanding of learning and engagement as predictors of individual differences in learning and will result in intelligent tutors that are more sensitive to individual differences. It will unveil the extent to which students of different genders and cognitive abilities learn more efficiently with different forms of teaching. This research will benefit society as machine learning methods, which provide a core technology for building complex systems, will be applicable to a variety of teaching systems.

Biological Science (61). This CCLI Educational Materials Development proof-of-concept project addresses the need to engage forest ecology students, including non-majors and future teachers, in activities that require critical thinking and scientific reasoning. It does this by building inquiry-oriented materials that approach forestry as an environmental mystery, asking students "Why are there no middle sized trees in this well developed forest?" "How often and which species of trees were logged?" and "How long ago was this beaver pond abandoned?" The software automatically records and analyzes students' observations, data and hypotheses and helps students draw inferences and revise hypotheses. The software works on a desktop computer and on a Personal Digital Assistant so students can record data and perform data analysis during field trips. The three forestry cases developed are tested for their effectiveness in a variety of post-secondary institutions and secondary schools, examining how and if inquiry learning is supported by the materials. Evaluation includes assessment of the software's usability and the consequent changes in student attitudes towards scientific reasoning. This work incorporates artificial intelligence, interactive multimedia and web-based technology in a rich, reliable and authoritative collection of teaching materials, thereby addressing the need for instruction appropriate to students of different learning styles and genders.

One promise of the Internet is educational "mass customization." Thanks to the National Science Digital Library (NSDL; http://nsdl.org), the opportunity exists to filter millions of resources and customize them for individual learners. This NSDL targeted research project is organizing digital libraries by dimensions that are important to teachers and learners--specifically, cognitive characteristics (cognitive development, spatial and math retrieval skills, reading level), affective characteristics (self-efficacy, motivation, beliefs/attitudes toward the subject), and social characteristics (gender, main language, ethnicity). The investigators hypothesize that customization of resources will result in visitors spending more time in NSDL and students achieving more in-depth learning.

As a testbed, the investigators are creating a customized learning environment, "Customized MathForum," within the Math Forum Digital Library (MFDL; http://mathforum.org), which is one of the most popular instructional digital libraries and has one of the largest communities of users (over a million individuals). The investigators are indexing the digital library according to cognitive, affective, and social dimensions and are evaluating whether such indexing helps stakeholders (teachers, students, and contributors/authors) find effective and efficient material and whether such indexing results in more effective learning than when resources are chosen randomly. Project activities include:

* designing a customized learning environment for middle school and high school teachers and students within MFDL;
* generating a portal to a special library of 750 arithmetic and geometry problems individualized for specific cognitive and behavioral skills;
* developing smart search tools and intelligent agents that will search the digital library for appropriate resources;
* integrating an enhanced metadata system in MFDL along dimensions that are important to teachers and learners--e.g., relation to state educational standards, and cognitive, affective, and social characteristics;
* evaluating the impact of providing customized problems for students and teachers; and
* disseminating tools for customized services to other digital library service providers.

Though described in terms of MFDL, this research is general and the methodology is applicable to many NSDL collections.

This project builds on tools and technologies that have evolved from several NSF-supported projects in three domains: intelligent tutoring systems, digital libraries, and instructional networks. The research directly addresses computational issues (advances in machine agents in distributed environments and the integration of intelligent tutors and digital libraries) and cognitive and affective issues (human learning characteristics and student models that improve online instruction). The research should result in sensitive instruction that is responsive to individual differences, especially among underrepresented minorities and women, and should unveil the extent to which students of different cognitive abilities learn with different forms of teaching.

This project, funded through the Ethics Education in Science and Engineering (EESE) cross-directorate program, involves interdisciplinary collaboration to design, pilot, and evaluate a web-based curriculum for graduate students, faculty and professionals. The investigators expand science & engineering ethics education by incorporating international dimensions. Specifically, the interdisciplinary project team produces teaching materials, pedagogies, teaching notes and web-based tools in: workplace ethics, international accountability, transnational spread and conduct, variation in international regulatory processes, responsible participation, ethical conflict between nations, and stakeholder and social inclusion. These materials are developed for inquiry-based web modules that are customized tutorials for diverse learners.

The researchers will pilot test these tutorials in multiple sites and disciplines. The curriculum will be evaluated objectively by tests of students? acquisition of target knowledge and reasoning skills, and subjectively by student and instructor perceptions of the content, usability and importance of the materials. The refined curriculum will be disseminated through the National Online Resource Center and the National Center for Digital Government, among other modes.

This important expansion of ethics education will be innovative in several ways: 1) by using interactive, customizable software that allows students to engage in active inquiry in the nine education modules; 2) by focusing on the ethical issues inherent in globalization of science and engineering and the international regulation of science and technology; and 3) by making visible the diversity of ethical structures and processes in governmental bodies around the world. The widely disseminated curriculum will benefit scientists and engineers across the disciplines, who face the challenges of globalization in the economy and in their research settings. This educational project is designed to effect a broad impact by affording scientists and engineers a greater capacity to work reflectively and ethically across countries and cultures and to engage ethical challenges involved in working in multiple political and social settings.

Emotion and motivation are fundamental to learning; students with high intrinsic motivation often outperform students with low motivation. Yet affect and emotion are often ignored or marginalized with respect to classroom practice. This project will help redress the emotion versus cognition imbalance. The researchers will develop Affective Learning Companions, real-time computational agents that infer emotions and leverage this knowledge to increase student performance. The goal is to determine the affective state of a student, at any point in time, and to provide appropriate support to improve student learning in the long term. Emotion recognition methods include using hardware sensors and machine learning software to identify a student's state. Five independent affective variables are targeted (frustration, motivation, self-confidence, boredom and fatigue) within a research platform consisting of four sensors (skin conductance glove, pressure mouse, face recognition camera and posture sensing devices). Emotion feedback methods include using a variety of interventions (encouraging comments, graphics of past performance) varied according to type (explanation, hints, worked examples) and timing (immediately following an answer, after some elapsed time). The interventions will be evaluated as to which best increase performance and in which contexts. Machine learning optimization algorithms search for policies that further engage individual students who are involved in different affective and cognitive states. Animated agents are enhanced with appropriate gestures and empathetic feedback in relation to student achievement level and task complexity. Approximately 500 ethnically and economically diverse students in Massachusetts and Arizona will participate.

The broader impact of this research is its potential for developing computer-based tutors that better address student diversity, including underrepresented minorities and disabled students. The solution proposed here provides alternative representations of scientific content, alternative paths through material and alternative means of interaction; thus, potentially leading to highly individualized science learning. Further, the project has the potential to advance our understanding of emotion as a predictor of individual differences in learning, unveiling the extent to which emotion, cognitive ability and gender impact different forms of learning.

Intellectual Merit. This project analyzes whether specific software interventions produce motivational and mathematics achievement gains for girls within real K12-level educational settings, at two crucial moments of girls? development of attitudes towards STEM, grades 5-6 and 10-11. Randomized controlled evaluations are used to analyze the impact of strategies that improve girls' and minorities' performance in mathematics and motivation to pursue mathematics coursework. The study uncovers empirically-supported guidelines for the design of math software that benefit girls' and minorities' motivation and achievement in mathematics. This research furthers research into computation techniques (intelligent agents/learning companions, user modeling and tools), educational psychology (rigorous analysis of the impact of interventions on motivation and self-efficacy, student characteristics and on-line instruction) and developmental psychology (gender differences across several ages).

Broader Impact. The project provides Internet environments for students in poorly performing school districts and those who might be home-schooled as a result of a disability. It advances the understanding of students who find potential failure in math to be threatening (most often, females and students from traditionally under represented minority groups), promoting interest in mathematics among generally underrepresented students. It improves the quality of on-line courseware and reduces the barrier for entry to STEM. The project will produce instruction that is responsive to individuals, lays the groundwork for more innovative curricula and creates new understandings of the complexities of taught materials.

On-line role-playing environments provide exciting avenues for teaching science and are particularly effective with students who might otherwise be excluded from science study. However, such environments are expensive to build, difficult to modify and rarely support collaboration.

This project develops a broad vision of inquiry role-playing environments and collaboration. An intelligent tutoring system will be modified to classify and analyze student dialogue elements providing automatic analysis of inquiry and collaboration. The tutor monitors each student's actions using sentence openers that track collaboration indicators and explore the effect of both individual and group activities. The investigators will examine whether and how several theories of learning apply to multi-player activities. A comparison of efficiency in individual and group settings will be made and student strategies analyzed in both effective and less effective group settings. A variety of tools will be developed, building on prior NSF supported projects that develop critical thinking and deep learning in science.

The team includes multi-disciplinary and multi-institutional collaborators who are experts in computer supported collaborative learning, domain knowledge, inquiry learning and classroom collaboration. Computer scientists, educational researchers, and biologists from three institutions will develop active, engaging virtual communities around inquiry cases. Approximately 350 students and 10 teachers/professors serving ethnically and economically diverse students will participate in the project. Software will be freely available and potentially have a broad impact on thousands of students in dozens of science disciplines.

This is funding to support travel by 25 students currently enrolled in PhD programs in the United States to participate in the ITS (Intelligent Tutoring Systems) Doctoral Student Consortium, at the upcoming International ITS Conference, to be held June 23rd-27th 2008, in Montreal, Quebec. The ITS International Conference is the premier biennial event for promoting promotes rigorous research and development of interactive and adaptive learning environments for learners of all ages; ITS will be the 9th event in the series. The interdisciplinary areas that ITS represents, comprising cognitive science, computer science, and educational technology, are critical research domains that enhance the effectiveness and usability of software learning systems. Active participation of young researchers in this conference is very important, both for the health of the field and for the researchers themselves. The ITS 2008 Young Researcher's Track (YRT) provides a unique opportunity for PhD students partway through their dissertation research to receive valuable feedback and individual mentoring from top researchers in the field. The YRT officially takes place on June 25-27, 2008 during the three days of the conference that follow the pre-conference workshops and tutorials. The program format dedicated to the students will include three 1.5 hour structured poster sessions open to all conference participants. Students will be paired-up with a senior member of the ITS community who serve as a mentor during the conference. The PI holds an active leadership roles within ITS 2008, and personally holds over $1.5 million of NSF grants in the areas of advanced learning technologies and intelligent tutoring systems.

Bringing young and creative researchers to ITS 2008 will help advance an important and socially valuable interdisciplinary research field. For many graduate students, the cost of attending the conference exceeds their travel budget. Thus, NSF funding will significantly impact the careers of the next generation of ITS researchers, by enabling a number of them to take part in an important event they would otherwise have to miss; in particular, those who lack funding from other sources (e.g., advisor's grants). The students will have an opportunity to gain wider exposure in the community for their innovative work, and to obtain feedback and guidance from senior members of the research community. Participation will also help foster a sense of community among these young researchers, by allowing them to create a social network both among themselves and with senior researchers at a critical stage in their professional development. The PI and co-PI have indicated that they will act to assure participation by members of traditionally under-represented institutions, and will pay close attention to inclusion of minorities and women.

The Preparing for College: Using Technology to Support Achievement for Students with Learning Disabilities in Mathematics project will advance knowledge about improved learning, motivation and achievement of undergraduate students with mathematics learning disabilities when using digital interventions. This demonstration research project will result in pilot-tested interventions, which will serve as the basis for more advanced studies of how students with learning disabilities learn math in a cyber-enabled environment.

The primary intervention tool for this project is a cyber-enabled mathematics tutor, "Wayang Outpost," that helps students solve challenging test problems, teaches explicitly, and uses visual representations to help students learn. Modifications to the tutoring system will be piloted that address cognitive, metacognitive, and affective dimensions of the system, corresponding to the representation/expression and engagement strands underlying universal design for learning.

This demonstration research pilot project will include testing a series of interventions with undergraduates in developmental mathematics classes at the University of Massachusetts and at Arizona State University. The project will target approximately 200 undergraduates, with and without learning disabilities, across four classrooms in experimental and control conditions.

Engineering - Electrical (55)
This collaborative project between the University of Massachusetts Amherst and the Massachusetts Maritime Academy is evaluating and dissemination a new interactive instructional circuit analysis computer environment (CIRCE) for college physics and engineering laboratories. CIRCE includes interactive, on-line software that provides immediate feedback, which is known to increase student learning and mastery of concepts. It also provides students with hands-on experience with electrical measurements and their interpretation. CIRCE includes an authoring tool that allows faculty to modify the environment to fit their own laboratory apparatus and curriculum goals. The project seeks to improve student learning by (1) providing immediate feed-back of the laboratory report and an opportunity for students to correct their errors, (2) freeing instructors from the task of checking student work so they can provide higher-level supervision of the laboratory exercise and (3) supporting the educational community by enabling flexible creation of new laboratory software. A consortium of faculty from 4-year colleges and the University of Massachusetts Amherst are introducing the software into their circuit analysis classes and evaluate its efficacy.

This project will develop and evaluate software to support people engaged in online social deliberation, especially as it relates to dispute resolution and collaborative inquiry. The software will model and monitor deliberative processes skills while people are either in collaboration or involved in settling disputes. Applications will be in three domains that already support online conversations: 1) online dispute resolution (e.g., eBay and the U.S. National Mediation Board); 2) collaborative learning in open-ended inquiry learning environments; and 3) dialog and deliberation on civic and ethical issues. The project will scaffold situations, adding structure or focusing attention on social processes, support improvement of individual skills, and facilitate a. Wisdom of crowds that enables participants to produce improved results. This project involves faculty across five departments: legal studies, psychology, political science, computer science and education.

Intellectual Merit. This research advances social issues (collaboration, dispute resolution, and critical thinking) and computation techniques (online dispute resolution, argumentation and collaboration). It furthers research into building social communities, explores issues of coaching and collaboration and develops evaluation tools for measuring the effect of online support.

Broader Societal Impact. This project advances the understanding of online human-human communication. It will enable more people to access social deliberative tools, promote interest in discussion among more people and improve the quality of on-line disputes as well as collaborations. The project lays the groundwork for more intelligent communication in online communities, creates new understandings of the complexities of collaboration and produces new modes of synergistic online discussions.

The purpose of this proposal is to explore the extent to which timely emotional, cognitive, and metacognitive interventions in tutoring software will have positive effects on students' emotions, attitudes, and achievements in mathematics. The intelligent tutor, Wayang Outpost, a high school mathematics tutoring system, is being enhanced to leverage automatic detection of emotions to guide cognitive, metacognitive, and affective forms of learning support.

The PIs are conducting a set of experiments to understand the interplay of observed emotional states, emotion assessments, student behavior within tutors, and student achievement. In particular, the experiments are testing the effects of the tutoring system when it assesses the emotions of a student and then responds with instructional support appropriate to that student's affect and content knowledge.

In this project, an interdisciplinary team of researchers in learning technologies and mathematics education are working together to investigate issues related to motivation in learning mathematics. They are taking the results of lab-based studies into classrooms. The novel technology and approaches developed in the lab were tested with a small population of learners; in their classroom-based investigations, they are testing feasibility of the approach with a more diverse population and refining the technology for use in a broad range of classroom learning environments. This translational research project will not only make significant contributions to the field of learning technologies, but will also contribute to our understanding of issues related to motivation in mathematics learning.

The International Conference on Intelligent Tutoring Systems (ITS) provides a forum for interchange of ideas around the applications of computer science to education and human learning. Presentations at the conference focus on developments and rigorous research around the design and use of interactive and adaptive learning technologies for learners of all ages, for subject matters that span the school curriculum, and for professional applications in industry, the military, and medicine. The conferences promotes cross-fertilization of information and ideas from several cyberlearning related fields: artificial intelligence, cognitive science, education, learning sciences, human-computer interaction, educational technology, psychology, and STEM disciplines.

This project will support travel for advanced graduate students from US universities to attend the 11th International Conference on Intelligent Tutoring Systems (ITS), to be held in Chania, Crete, in Greece, from June 15 to 18, 2012 (http://its2012.teicrete.gr). Those advanced graduate students will participate in the Young Research Track at the conference. That track is designed to provide young researchers with mentoring beyond what they get at their home institutions that will help them transition from graduate school to a fruitful research career. Young Researcher activities include structured poster sessions in which students present their work and one-on-one mentoring throughout the conference from a senior member of the ITS community who shares research interests with a young researcher and who comes from a different university and has a different approach than the young researcher experiences in his/her home institution. It is expected that conversations between peers and between mentors and mentees will continue throughout each young researcher's career.

This activity supports the mission of NSF to train more advanced professionals in Science, Technology, Engineering, and Mathematics. This conference is unique in its synthesis and cross-fertilization across three STEM capacities: building cutting-edge learning technologies, investigating pedagogical methods that are theoretically grounded in the cognitive, social, and learning sciences, and rigorously testing the learning environments for their effectiveness at promoting learning (in STEM disciplines and other disciplines) among K-12, college, and workplace populations.

A major factor influencing learning is students' emotions and their general affective state. Given the pivotal role that affect plays in learning activities it is not surprising that there has been a good deal of interest in developing affect-aware technologies. The overwhelming majority of this work, however, has focused on modeling affect, i.e., designing computational models capable of inferring how students are feeling while interacting with an Intelligent Tutoring System (ITS). While modeling of affect is a critical first step in providing adaptive support tailored to students' affective needs, very little work exists on systematically exploring the impact of affective interventions on students' performance, learning, affect and attitudes, i.e., how to respond to students' emotions such as frustration, anxiety, boredom, and hopelessness as they arise. The research fills this gap by analyzing the value of tailoring different types of interventions to negative affective states for individual students and groups of students.

The project has two main goals. First, it addresses how to respond to negative student emotion (e.g., frustration, anxiety, boredom) in computer-based learning environments through a variety of interventions. Some correspond to specially-designed digital characters, integrated into the learning environment, which are intended to act like students' learning companions. These agents support students through (a) non-verbal behaviors (e.g., having the characters express empathy in response to student frustration), (b) messages targeting students' cognitive and meta-cognitive skills, as well as motivation and affect. Other interventions involve supporting collaboration between students to mitigate negative emotional states when detected. The impact of these interventions are investigated through a series of eight experiments with a total of 800 students. These experiments help to unveil general prescriptive principles to address student affect.

The second goal accomplished by this research is that the experiments provide valuable data to continue to extend and validate existing models of emotion. Specifically, the project triangulates and integrates a complex space of partially overlapping models and constructs of affect in learning (i.e. emotions, attitudes, incoming moods, motivation, engaged use or misuse of software). The project refines several well-established models, in particular the control-value theory of emotions to provide a more stable theoretical framework for the field of emotions in educational software.

This research is unique and ground breaking, as few researchers have targeted students' emotion in classrooms, gathered fine grained data on emotions during learning, or assessed the impact of specific affective treatments on a moment-to-moment basis. Students using the tutoring systems have already shown statistically significant gains and learning outcomes, as well as increased positive affect and attitudes. The new affective interventions will greatly increase the broad impact of these systems.
This research is developing: (1) prescriptive principles about how to respond to student affect; (2) new understanding about the impact of cognitive, affective, and meta-cognitive interventions on emotions and learning; (3) new understanding about individual differences in learning, unveiling the extent to which emotion, cognitive abilities, and gender impact learning; (4) instruction that is sensitive to individual differences; and (5) refined theories of student emotion.

This research is also: (1) increasing participation in mathematics of underrepresented populations (women and minorities) who often avoid STEM careers; (2) creating broad access to web-based technologies that help to engage more students by addressing their affective and social needs; and (3) addressing the one-size-fits-all approach to education, by responding to individual student needs with alternative representations of content and pathways through which material is presented.

The United States has historically been the global leader in the field of Intelligent Tutoring Systems, or ways to use computerized artificial intelligence to enhance teaching and learning in contexts ranging from children learning math in school, to soldiers learning highly technical jobs in the US military. The preeminent conference in this field is the ITS conference; at this conference the latest research is presented and practitioners learn the state of the art techniques that allow creation of these important educational technologies.

This proposal would support seven Ph.D. students, selected through a competitive process, to attend the conference, present their work, and receive additional mentoring outside of their dissertation committees. The intellectual merit of the work rests on the studies the graduate students submit to be considered for participation in the early career track of the conference; this work is then enhanced by guidance from world-class mentors who meet with the students in a structured format to improve their research. The broader impact includes the career impact on the seven selected students, especially since promising graduate students whose advisors may not have funding to send them to the conference can still be included, and their work can be showcased and improved. Possible long-term broader impacts include building the field of ITS researchers and improving the quality of tutoring systems, and thus eventually, improving the quality of education.

This exploratory research seeks to advance understanding of how research-based, highly innovative technology tools that support student learning can be implemented in schools in a sustainable way. This is an important and basically unchartered area of research. Both public and private agencies and business have invested significant sums in designing and testing technology systems and applications for education. While exciting and potentially transformative, many of these innovative tools have not been successfully implemented, in part because of a lack of knowledge or theory about what is needed in the schools. Different designs (e.g. whole unit, replacement units, tutoring systems, etc.) may require different levels of support. There is very little research on what it takes to implement and sustain technology enhanced educational systems and products that lead to increased student learning.

Through a series of case studies, this project will study what is needed to implement three very different types of digital resources that can be implemented and sustained in schools. The case studies will focus on technology difficulties, systems integration and pedagogical support. The findings could have broad impact on the how educational technology is developed and implemented.

The Cyberlearning and Future Learning Technologies Program funds efforts that support envisioning the future of learning technologies and advancing what we know about how people learn in technology-rich environments. Capacity-building (CAP) projects help build the capacity of the field to do high-quality, high-impact research on learning. This project supports the mission of NSF to train more advanced professionals in Science, Technology, Engineering, and Mathematics (STEM) by supporting doctoral students attendance at the International Conference on Artificial Intelligence in Education (AIED) and the 6th International Conference on Educational Data Mining (EDM) to be held in Madrid, Spain in June of 2015.

The intellectual merit of the grant rests on the quality of the research being presented at the conferences. Together, the conferences provide cross-fertilization of information and ideas from artificial intelligence, cognitive science, machine learning, education, learning sciences, educational technology, psychology, philosophy, sociology, anthropology, linguistics, and the many domain-specific areas for which cyberlearning systems are designed and built. The broader impact of the work rests in the inculcation of students into this field. Doctoral students will be selected from U.S. institutions. The criteria for selection include either having a paper accepted for one of the conferences and/or or submitting an strong rationale for what the student would learn at the conference. All students receiving support will be assigned a mentor. The selecting committee will strive to ensure that there is diversity of institutions, topics, disciplines, ethnicities, and gender in the cohort of awardees. Selected students will receive up to $1,000 to partially cover expenses.

This PFI: AIR Technology Translation (TT) project addresses the high failure rate of K12 students to learn mathematics. This project focuses on technology translation of an intelligent online tutor, named MathSpring, which is important because it provides adaptive and personalized responses to students and teaches by matching the learning needs of individual students with effective teaching approaches. It applies theoretical understanding of cognitive, metacognitive and affective student characteristics to each tutor response. The MathSpring Tutor is also important because no online tutor today responds by analyzing both student knowledge and behavior. This PFI:AIR-TT project will result in a scale-up of the MathSpring Tutor and provide advantages in the marketplace by capitalizing on the general appeal of animation and humanoid characters that talk to students about the importance of perseverance and effort. The project will also provide low-cost, quality solutions for a wide range of students, adaptive tutoring based on student models, just-in-time verbal and animated interactions designed to move students away from boredom or disengagement, and the capability to select from among potentially 700 problems in the system.

These features of the MathSpring tutor provide improved performance, efficiency and efficacy when compared to classroom teaching or to the leading competing technology, primarily drill and practice problems, videos of lectures or games in this market space. The potential economic impact of translating this technology to the market place will positively contribute to the growth rate of eLearning within the next 5 years and to the U.S. competitiveness in the eLearning domain. Since the annual U.S. education expenditure for K-12 is approximately $625 billion, a large potential exists for making both a commercial and social impact in this space. Potential outcomes include: personalized tutors that guide students into their own zone or state of ?flow?; identification of target educational markets; and reaching any student with access to a computer and an Internet connection.

This PFI project addresses the following technology gaps as the software is translated from research discovery toward commercial application: identification of tutor responses that are effective for students in distress (e.g., bored, unmotivated); building sufficient content so the tutor can be used through an entire semester in Grades 5-9; and providing tools that enable teachers to select math problem based on the Common Core curriculum. The project work also includes hardening the tutor, porting it to two platforms (e.g., Android, IOS) and identifying consortia of schools (e.g., linked by geography, or pedagogy) for long-term partnerships.

Personnel involved in this project, e.g., graduate students and programmers, will receive innovation and technology translation experiences through efforts to identify paths through the idiosyncratic school procurement process and the communication of the efficacy studies arising from credible evaluation of MathSpring. The project engages CarneyLabs to guide commercial aspects of the translation and Virginia Advanced Studies Strategies (VASS), a non-profit company that works with the Virginia Department of Education (DoED), to provide a test environment in this technology translation effort from research discovery toward commercial reality.

This project supports teachers, administrators and researchers to collaborate around online education resources and big data. It will increase the capacity of participants in Educational Big Data in the Northeast to analyze data from schools, students and administrators and to improve teaching and learning. However, as more refined data comes from online instructional systems and the use of data mining techniques, participants will learn to search for patterns and associations and to draw conclusions about student knowledge, performance and behavior. This research addresses several grand challenges in education: 1) Predict future student events, e.g., college attendance, college major, from existing large-scale longitudinal educational data sets involving the same thousands of students. 2) Help teachers to make sense of dense online data to influence their teaching, e.g., what should they say or do in response to student activity. 3) Provide personal instruction to each student based on using big data that represents student skills and behavior and infers students' cognitive, motivational, and metacognitive factors in learning. The project will improve the capacity in data-driven education by sharing educational databases, managing yearly data competitions, and conducting educational data science workshops and hackathons. Measurable results include studying gigabytes of data to: create actionable recommendations for classroom teachers; make effective and successful predictions about students; develop new AI methods for education; and create new data science tool sets. Key outcomes include introducing many researchers to educational big data, learning analytics and models of teaching interventions. The team intends to improve classroom learning and leverage the unique types of data available from digital education to better understand students, groups and the settings in which they learn.

Computers have been in classrooms for decades and yet educators have not identified the most effective ways of using them. Despite advances in evaluation methods to measure human learning, most researchers still use measures available 50 years ago. This project will leverage and extend state-of-the-art big data bases and technologies to measure online learning, especially features of student engagement and learning associated with improved student outcome. This project has the potential to reach millions of students (while learning), hundreds of researchers while measuring human learning (from education, cognitive science, learning sciences, psychology, and computer science) and a dozen other organizations (publishers, testing organizations, non-profit organizations, teachers, parents, and stakeholders). The team brings together a unique blend of researchers from data science (Baker, Heffernan); adaptive education technology and computer science (Woolf, Arroyo); and learning sciences (Arroyo, Heffernan). It includes women and minorities (Woolf, Arroyo), people who helped develop the largest educational database in the world (Baker), developers of data science teaching materials (Arroyo, Baker), and others who have developed online tutoring systems that achieve significant student success in learning (e.g., Heffernan, Arroyo, Woolf).

The Cyberlearning and Future Learning Technologies Program funds efforts that support envisioning the future of learning technologies and advance what we know about how people learn in technology-rich environments. Integration (INT) projects refine and study emerging genres of learning technologies that have already undergone several years of iterative refinement in the context of rigorous research on how people learn with such technologies; INT projects contribute to our understanding of how the prototype tools might generalize to a larger category of learning technologies. This INT project integrates prior work from two well-developed NSF-sponsored projects on (i) advanced computer vision and (ii) affect detection in intelligent tutoring systems. The latter work in particular developed instruments to detect student emotion (interest, confusion, frustration and boredom) and showed that when a computer tutor responded to negative student affect, learning performance improved. The current project will expand this focus beyond emotion to attempt to also detect persistence, self-efficacy, and the trait called 'grit.' The project will measure the impact of these constructs on student learning and explore whether the grit trait (a persistent tendency towards sustained initiative and interest) can be improved and whether and how it depends on other recently experienced emotions. The technological innovation enabling this research into the genre of broadly affectively aware instruction is Smartutors, a tool that uses advanced computer vision techniques to view a student's gaze, hand gestures, head, and face to increase the "bandwidth" for automatically detecting their affect. One goal is to reorient students to more productive attitudes once waning attention is recognized.

This research team brings together a unique blend of leading interdisciplinary researchers in computer vision; adaptive education technology and computer science; mathematics education; learning companions; and meta-cognition, emotion, self-efficacy and motivation. Nine experiments will provide valuable data to extend and validate existing models of grit and emotion. In particular, the team will gather fine-grained data on grit, assess the impact of tutor interventions in real-time, and contribute thereby to a theory of grit. Visual data of student behavior will be integrated with advanced analytics of log data of students' actions based on the behavior of over 10,000 prior students (e.g., hint requests, topic mastery) to provide individualized guidance and tutor responses in a timely fashion. This will allow the researchers to measure the impact of interventions on student performance and attitude, and it will uncover how grit levels relate to emotion and what impact emotions and grit combined have on overall student initiative. By identifying interventions that are sensitive to individual differences, this research will refine theories of motivation and emotion and will reveal principles about how to respond to student grit and affect, especially when attention and persistence begin to wane. To ensure classroom success, the PIs will evaluate Smartutors with 1,600 students and explore its transferability by testing it in a more difficult mathematics domain with older students.

The Cyberlearning and Future Learning Technologies Program funds efforts that will help envision the next generation of learning technologies and advance what we know about how people learn in technology-rich environments. Cyberlearning CAP projects build capacity for research and development in the field of Cyberlearning by improving technical infrastructure, human capital, and in other ways. The Intelligent Tutoring Systems (ITS) 2016 conference offers a rare professional opportunity for interdisciplinary students to converge and present cutting-edge research from the fields of artificial intelligence (AI), learning science, computer science, cognitive and learning sciences, psychology, and educational technology.

This project supports travel for selected advanced graduate students to attend the doctoral consortium at the ITS 2016 conference in Croatia. The conference has a special Young Research Track within the main conference for advanced graduate students. In this track a special session supports students to share their research with papers, posters, tutorials, workshops, and informal interactions with accomplished researchers. Students present their research ideas and receive feedback from researchers in the ITS community. An important goal of the doctoral consortium is to build the new generation of researchers in the forward-looking technical area of intelligent tutoring systems.

The Cyberlearning and Future Learning Technologies Program funds efforts that will help envision the next generation of learning technologies and advance what we know about how people learn in technology-rich environments. Cyberlearning CAP projects build capacity for research and development in the field of Cyberlearning by improving technical infrastructure, human capital, and in other ways. The Intelligent Tutoring Systems (ITS) 2016 conference offers a rare professional opportunity for interdisciplinary students to converge and present cutting-edge research from the fields of artificial intelligence (AI), learning science, computer science, cognitive and learning sciences, psychology, and educational technology.

This project supports travel for selected advanced graduate students to attend the doctoral consortium at the ITS 2016 conference in Croatia. The conference has a special Young Research Track within the main conference for advanced graduate students. In this track a special session supports students to share their research with papers, posters, tutorials, workshops, and informal interactions with accomplished researchers. Students present their research ideas and receive feedback from researchers in the ITS community. An important goal of the doctoral consortium is to build the new generation of researchers in the forward-looking technical area of intelligent tutoring systems.

The NSF Convergence Accelerator supports team-based, multidisciplinary efforts that address challenges of national importance and show potential for deliverables in the near future.

The broader impact/potential benefit of this Convergence Accelerator Phase I project is to provide a software tool to guide individual workers in the US manufacturing workforce through the process of job selection and upskilling in their entire career. Due to the rapid development of workplace technology, such as robots and computer interfaces to machinery, future jobs require skills that are not taught in schools or standard training programs. Therefore, worker reskilling and retraining as part of the lifelong learning process is critical to the US economy and is a topic of national importance. The investigators will study this problem by collecting and analyzing data from a large partner corporation in the manufacturing industry and interviewing real workers and stakeholders; the proposed approaches will be tested by workers both employed by the partner corporation and recruited by a local partner city government. The investigators will integrate their expertise on computer science, educational technology, and social and economic analyses of the labor market to propose an effective, fair, and scalable software solution that can help a broad segment of workers in the US workforce, in both the manufacturing industry and beyond.

This Convergence Accelerator Phase I project aims at ultimately developing a framework that performs worker profile Diagnosis, training program RECommendation, and intelligent Training platform development (DIRECT) for the purpose of continuous workforce development. DIRECT is an integrated software tool that helps workers identify desirable future jobs, recommends training programs, and guides workers through the process of planning future career paths. It consists of four consecutive and intertwined components: (i) a skill level diagnosis and assessment component that uses cognitive models to assess worker skill levels from on-job data, (ii) a training experience development component that uses intelligent tutoring concepts to help workers acquire new skills, (iii) a skill gap identification component that uses labor market analysis to identify high-demand jobs and the skill gaps between a worker and their desirable job, and (iv) a future job and training program recommendation component that uses predictive artificial intelligence algorithms to connect workers to future jobs and select training programs to acquire the necessary skills. In Phase I of the project, the investigators will work with industry and government partners to formulate concrete research problems, identify data sources, develop prototypes, and conduct pilot studies to ensure that DIRECT is effective and practical.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

This NSF Convergence Accelerator Workshop will create smart and integrated platforms, devices and processes for education technology. Current educational technologies often do not sufficiently leverage basic research on learning, nor have a culture of continuous improvement, nor meet the needs of diverse learners, nor leverage the growing power of computers. One issue is the disconnected, fragmented, and often closed nature of different sectors: educators, parents, commercial ventures, not-for-profit organizations, stakeholders, researchers, and communities. A concerted effort among diverse stakeholders is needed now to create real and immediate solutions. Significant technology exists for digital instruction. Experts in academia (learning science, AI, human-computer interaction, education, psychology), industry and government will identify barriers and solutions to the delivery of high-quality online education; they will inform best practices in design, generate future development and testing, and leverage technology and new modes of platform design. This workshop will support communities to reason about fruitful near-term approaches for scaling up innovative pedagogies. We will increase the number of trials of new products; test more often and fail faster; identify promising interventions, and evaluate the conditions and circumstances that increase the probability of successful products. <br/>The scientific agenda will investigate and augment human learning at large scale in authentic education settings (online, hybrid, and on-the-job). The workshop will establish a framework for new AI, learning science, and education theory and technologies to understand, model, infer, and respond to learning. It will explore new theory, algorithms, big data, and systems that optimize every point in the education process to understand students, organize what they can learn, and optimize how they learn. The workshop will couple use-inspired AI research with foundational AI and learning science research in a virtuous cycle and forge new partnerships among diverse stakeholders as they bridge the divide with novel tools from engineers, makers, technologists, and designers. It will make a laser focus on projects that present well-defined deliverables within 3-years.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.