Resilience in Web-Based Mental Health Communities: Building a Resilience Dictionary With Semiautomatic Text Analysis
Bibliographic record
Abstract
BACKGROUND: Resilience is an accepted strengths-based concept that responds to change, adversity, and crises. This concept underpins both personal and community-based preventive approaches to mental health issues and shapes digital interventions. Online mental health peer-support forums have played a prominent role in enhancing resilience by providing accessible places for sharing lived experiences of mental issues and finding support. However, little research has been conducted on whether and how resilience is realized, hindering service providers' ability to optimize resilience outcomes. OBJECTIVE: This study aimed to create a resilience dictionary that reflects the characteristics and realization of resilience within online mental health peer-support forums. The findings can be used to guide further analysis and improve resilience outcomes in mental health forums through targeted moderation and management. METHODS: A semiautomatic approach to creating a resilience dictionary was proposed using topic modeling and qualitative content analysis. We present a systematic 4-phase analysis pipeline that preprocesses raw forum posts, discovers core themes, conceptualizes resilience indicators, and generates a resilience dictionary. Our approach was applied to a mental health forum run by SANE (Schizophrenia: A National Emergency) Australia, with 70,179 forum posts between 2018 and 2020 by 2357 users being analyzed. RESULTS: The resilience dictionary and taxonomy developed in this study, reveal how resilience indicators (ie, "social capital," "belonging," "learning," "adaptive capacity," and "self-efficacy") are characterized by themes commonly discussed in the forums; each theme's top 10 most relevant descriptive terms and their synonyms; and the relatedness of resilience, reflecting a taxonomy of indicators that are more comprehensive (or compound) and more likely to facilitate the realization of others. The study showed that the resilience indicators "learning," "belonging," and "social capital" were more commonly realized, and "belonging" and "learning" served as foundations for "social capital" and "adaptive capacity" across the 2-year study period. CONCLUSIONS: This study presents a resilience dictionary that improves our understanding of how aspects of resilience are realized in web-based mental health forums. The dictionary provides novel guidance on how to improve training to support and enhance automated systems for moderating mental health forum discussions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.005 |
| Science and technology studies | 0.007 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".