Jason E. Owen, Ph.D. - US grants

DESCRIPTION (provided by applicant): Individuals with cancer face an array of psychosocial needs, and it has been estimated that up to 35% of cancer survivors experience clinically-significant levels of distress. Psychosocial interventions may be effective for improving quality of life and reducing levels of mood disturbance in these patients. Unfortunately, barriers to accessing psychosocial intervention are common, and many are unable to access those services. Internet- based psychosocial interventions improve accessibility of care and offer additional methodological advantages, including the ability to easily collect self-report data, track exposure to the intervention, and evaluate effects of specific intervention components. A study conducted by the PI is one of only three randomized trials of the effects of internet-based psychosocial intervention on adjustment to cancer, and all three of these trials were limited to now-outdated Internet interventions provided exclusively to women with breast cancer. There is a clear and pressing need to evaluate an internet-based intervention that: a) has modern features that will increase the amount of time spent interacting with intervention components (i.e., social-networking features), b) is inclusive of other cancers (i.e., not just breast cancer), and c) employs a system for carefully tracking levels of behavioral engagement with the intervention. The specific aims of the proposed study are 1) to evaluate the feasibility of a randomized, controlled trial of an online social-networking intervention and to identify key strengths and weaknesses of the intervention materials and 2) to estimate effect sizes necessary for adequately powering a larger controlled trial comparing face-to-face and online interventions. To accomplish these aims, a registry-based recruitment procedure will be used to identify recently diagnosed individuals with cancer who are currently experiencing significant cancer-related distress. Individuals interested in participating in the study will be randomized to receive access to a 12-week internet-based treatment group or to a 12-week waiting list control group. Subjects assigned to the treatment group will have access to a group discussion board, a structured 12-week coping-skills training course, professional facilitation of the group, a real-time chat board, and personal profiles established by other group members. Subjects will be asked to complete online self-report measures of distress, mood disturbance, and quality of life at baseline and again after participation in the 12-week group. Wait-list control subjects will be able to join a group after they complete the 12-week assessment and will be asked to complete a 24-week assessment in order to measure change over time. It is hypothesized that the treatment group will show greater improvements in quality of life and mood disturbance compared to the control group and that greater levels of engagement with the intervention materials will be associated with greater improvements in mood and quality of life. Long-term goals of the research team are to continually improve effect sizes and accessibility of psychosocial interventions for cancer survivors and to evaluate the effects of internet-based and face-to-face interventions in a head-to-head trial. PUBLIC HEALTH RELEVANCE: Only a handful of studies have evaluated the effects of internet-based psychological treatments for distress in those living with cancer. The proposed study will evaluate whether a website developed specifically for providing psychological treatment and enhancing communication between cancer survivors can improve distress among cancer survivors who indicate that they have high levels of distress. If successful, the study will also provide valuable information needed to improve the treatment and to adequately conduct a larger trial comparing internet-based and face-to-face treatments.

DESCRIPTION (provided by applicant): Understanding mechanisms of action is key to improving psychosocial interventions for cancer and other chronic disease conditions. In cancer, emotional expression has been identified as one possible mediator of the effect of psychosocial intervention on patient-reported outcomes. However, scientific evaluations of psychological mechanisms of adjustment to cancer and other chronic diseases are constrained by limitations associated with self-report measures. Because self-care resources, peer-to-peer networks, and more recent forms of psychosocial intervention are increasingly being delivered online, linguistic and behavioral data can be used to characterize internal coping processes, social interactions, and other manifest behaviors. Few tools are currently available for harnessing text as a potential data source, and signal detection indices of existing tools leave room for considerable improvement in these methodologies (Bantum &Owen, 2009). In the present study, natural language processing and other tools of computational linguistics will be used to develop a machine-learning classifier to identify emotional expression in electronic text data. The aims of the study are: 1) to annotate a large text corpus from cancer survivors using an objective and reliable emotion-coding procedure, 2) to incorporate linguistic and psychological features into a machine-learning classification method and identify which of these features are most strongly associated with codes assigned by trained human raters, and 3) to develop combined psychological and natural language processing (NLP) methods for identifying linguistic markers of emotional coping behaviors. To accomplish these aims, a comprehensive corpus of emotionally-laden cancer communications will be developed from 5 existing linguistic datasets. Five raters will be selected and undergo a rigorous training procedure for coding emotional expression using an emotion-coding system previously developed by the research. Coding will take place using an Internet-based coding interface that will allow the investigators to continuously monitor inter-rater reliability. Simultaneous with the coding process, the investigators will link the electronic text data with key linguistic and psychological features, including Linguistic Inquiry and Word Count (LIWC), Affective Norms for English Words (ANEW), WordNet, part of speech tags, patterns of capitalization and punctuation, emoticons, and textual context. A machine-learning classifier, using tools of natural language processing, will then be applied to the text/feature data and validated against human-rated emotion codes. The long-term objective of this research is to advance a methodology for objectively identifying coping behavior, particularly emotional expression, in order to supplement self-report measures and improve scientific understanding of adjustment to chronic disease, trauma, or other psychological conditions. This work is essential for identifying mechanisms of action in psychosocial interventions for cancer survivors and others and has significance for the fields of medicine, psychology, computational linguistics, and artificial intelligence. PUBLIC HEALTH RELEVANCE: Identifying specific emotional, cognitive, and behavioral factors that contribute to adjustment to cancer and other chronic diseases is essential for being able to develop and improve effective interventions to promote health and well-being. To date, the study of these factors as mechanisms of action has been limited to self-report measures that may not correlate well with other more objective indicators. The proposed study will improve our ability to identify mechanisms of action by supplementing self-report measures with objectively identified markers of coping behaviors such as emotional expression in natural language used by individuals living with cancer.

DESCRIPTION (provided by applicant): Developing practical methods for extracting and analyzing objective behavioral, linguistic, and social- networking data from e-health interventions is crucial for identifying and evaluating potential mechanisms of action for these interventions. Understanding how users engage with intervention content, the social networks in which individual engagement is embedded, and the quality of the interactions that occur between users will be instrumental in improving existing e-health interventions and making them more effective. Only a handful of Internet-based interventions has been tested for cancer survivors, and most randomized trials have shown evidence of positive outcomes. Among the studies showing positive effects, a common treatment element is the use of social-networking features, such as professional facilitation, discussion boards, private messages, and other ways for survivors to make personal connections with similar others. This study will plug several large gaps among methodological tools available for analysis of Internet-based interventions. First, the study will use objective behavioral data to identify several longitudinal markers of individual engagement with an intervention, including time spent using the intervention, time spent in skills-training exercises, and word count. Second, the study will identify specific social-networking attributes and markers of the quality of support received that can be used to predict intervention engagement and outcomes over time. The aims of the study are: 1) to identify, characterize, and compare social-networking attributes of the STC and HSN interventions, 2) to evaluate the longitudinal effects of social-networking attributes and social interaction quality on exposure to the intervention (i.e., dose of treatment), and 3) to evaluate the effects of social-networking attributes and social interaction quality on outcomes of the interventions. Behavioral, linguistic, and self-report data will be derived from two of the largest, Internet-based survivorshp trials: Surviving and Thriving Cancer (STC, n = 352) and Health-Space.net (HSN, n = 200). Linguistic (i.e., text) data will be subjected to automated text analysis to generate markers of quality of social support. Patterns of interactions between participants will be used to generate actor-other matrices, which will be subjected to social network analysis. Website use data will be used to generate markers of individual engagement with each intervention. Statistical analyses will be used to evaluate the effects of social-networking attributes and interaction quality on engagement and outcomes across time. These results could be used to quickly identify subgroups at risk for low-engagement with an intervention, to tailor intervention content based on social network attributes or quality of support, or to benchmark the network properties of other group-based e-health interventions. Given the substantial reach available to Internet-based interventions, even relatively modest improvements to outcomes (e.g., by improving levels of engagement) would have the potential to greatly improve the public health impact of these kinds of interventions.