When do Online Audiences Amplify Benefits of Self-Disclosure? The Role of Shared Experience and Anticipated Interactivity

Using Machine Learning of Online Expression to Explain Recovery Trajectories: Content Analytic Approach to Studying a Substance Use Disorder Forum

BACKGROUND

Smartphone-based apps are increasingly used to prevent relapse among those with substance use disorders (SUDs). These systems collect a wealth of data from participants, including the content of messages exchanged in peer-to-peer support forums. How individuals self-disclose and exchange social support in these forums may provide insight into their recovery course, but a manual review of a large corpus of text by human coders is inefficient.

OBJECTIVE

The study sought to evaluate the feasibility of applying supervised machine learning (ML) to perform large-scale content analysis of an online peer-to-peer discussion forum. Machine-coded data were also used to understand how communication styles relate to writers' substance use and well-being outcomes.

METHODS

Data were collected from a smartphone app that connects patients with SUDs to online peer support via a discussion forum. Overall, 268 adult patients with SUD diagnoses were recruited from 3 federally qualified health centers in the United States beginning in 2014. Two waves of survey data were collected to measure demographic characteristics and study outcomes: at baseline (before accessing the app) and after 6 months of using the app. Messages were downloaded from the peer-to-peer forum and subjected to manual content analysis. These data were used to train supervised ML algorithms using features extracted from the Linguistic Inquiry and Word Count (LIWC) system to automatically identify the types of expression relevant to peer-to-peer support. Regression analyses examined how each expression type was associated with recovery outcomes.

RESULTS

Our manual content analysis identified 7 expression types relevant to the recovery process (emotional support, informational support, negative affect, change talk, insightful disclosure, gratitude, and universality disclosure). Over 6 months of app use, 86.2% (231/268) of participants posted on the app's support forum. Of these participants, 93.5% (216/231) posted at least 1 message in the content categories of interest, generating 10,503 messages. Supervised ML algorithms were trained on the hand-coded data, achieving F1-scores ranging from 0.57 to 0.85. Regression analyses revealed that a greater proportion of the messages giving emotional support to peers was related to reduced substance use. For self-disclosure, a greater proportion of the messages expressing universality was related to improved quality of life, whereas a greater proportion of the negative affect expressions was negatively related to quality of life and mood.

CONCLUSIONS

This study highlights a method of natural language processing with potential to provide real-time insights into peer-to-peer communication dynamics. First, we found that our ML approach allowed for large-scale content coding while retaining moderate-to-high levels of accuracy. Second, individuals' expression styles were associated with recovery outcomes. The expression types of emotional support, universality disclosure, and negative affect were significantly related to recovery outcomes, and attending to these dynamics may be important for appropriate intervention.

Meeting Young Adults' Social Support Needs across the Health Behavior Change Journey: Implications for Digital Mental Health Tools

In pursuit of mental wellness, many find that behavioral change is necessary. This process can often be difficult but is facilitated by strong social support. This paper explores the role of social support across behavioral change journeys among young adults, a group at high risk for mental health challenges, but with the lowest rates of mental health treatment utilization. Given that digital mental health tools are effective for treating mental health conditions, they hold particular promise for bridging the treatment gap among young adults, many of whom, are not interested in - or cannot access - traditional mental healthcare. We recruited a sample of young adults with depression who were seeking information about their symptoms online to participate in an Asynchronous Remote Community (ARC) elicitation workshop. Participants detailed the changing nature of social interactions across their behavior change journeys. They noted that both directed and undirected support are necessary early in behavioral change and certain needs such as informational support are particularly pronounced, while healthy coping partnerships and accountability are more important later in the change process. We discuss the conceptual and design implications of our findings for the next generation of digital mental health tools.

Intraindividual, Dyadic, and Network Communication in a Digital Health Intervention: Distinguishing Message Exposure from Message Production

Communicating within digital health interventions involves a range of behaviors that may contribute to the management of chronic illnesses in different ways. This study examines whether communication within a smartphone-based application for addiction recovery produces distinct effects depending on 1) the "level" of communication, defined as intraindividual communication (e.g., journal entries to oneself); dyadic communication (e.g., private messaging to other individuals); or network communication (e.g., discussion forum posts to all group members), and 2) whether individuals produce or are exposed to messages. We operationalize these communication levels and behaviors based on system use logs as the number of clicks dedicated to each activity and assess how each category of system use relates to changes in group bonding and substance use after 6 months with the mobile intervention. Our findings show that (1) intraindividual exposure to one's own past posts marginally predicts decreased drug use; (2) dyadic production predicts greater perceived bonding; while dyadic exposure marginally predicts reduced drug use; (3) network production predicts decreased risky drinking. Implications for digital health interventions are discussed.