Table of Contents
Fetching ...

ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communities

Shiwei Wu, Mingxiang Wang, Chuhan Shi, Zhenhui Peng

TL;DR

This work addresses the difficulty viewers face in seeking social support within online mental health communities by introducing ComViewer, an interactive visual tool with a Zoomable Posts panel, an interactive Note-taking panel, and a Questioning panel that leverages large language models for summaries and guidance. Through a formative study (N=10) and a within-subject user study (N=20), the approach demonstrates significant improvements in informational support, engagement, and perceived usefulness compared to a baseline OMHC interface. The study provides design principles for visual information-seeking and AI-assisted sensemaking in OMHCs, and discusses generalizability, limitations, and future enhancements of integrating visualization with LLMs for mental-health support contexts.

Abstract

Online mental health communities (OMHCs) offer rich posts and comments for viewers, who do not directly participate in the communications, to seek social support from others' experience. However, viewers could face challenges in finding helpful posts and comments and digesting the content to get needed support, as revealed in our formative study (N=10). In this work, we present an interactive visual tool named ComViewer to help viewers seek social support in OMHCs. With ComViewer, viewers can filter posts of different topics and find supportive comments via a zoomable circle packing visual component that adapts to searched keywords. Powered by LLM, ComViewer supports an interactive sensemaking process by enabling viewers to interactively highlight, summarize, and question any community content. A within-subjects study (N=20) demonstrates ComViewer's strengths in providing viewers with a more simplified, more fruitful, and more engaging support-seeking experience compared to a baseline OMHC interface without ComViewer. We further discuss design implications for facilitating information-seeking and sense making in online mental health communities.

ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communities

TL;DR

This work addresses the difficulty viewers face in seeking social support within online mental health communities by introducing ComViewer, an interactive visual tool with a Zoomable Posts panel, an interactive Note-taking panel, and a Questioning panel that leverages large language models for summaries and guidance. Through a formative study (N=10) and a within-subject user study (N=20), the approach demonstrates significant improvements in informational support, engagement, and perceived usefulness compared to a baseline OMHC interface. The study provides design principles for visual information-seeking and AI-assisted sensemaking in OMHCs, and discusses generalizability, limitations, and future enhancements of integrating visualization with LLMs for mental-health support contexts.

Abstract

Online mental health communities (OMHCs) offer rich posts and comments for viewers, who do not directly participate in the communications, to seek social support from others' experience. However, viewers could face challenges in finding helpful posts and comments and digesting the content to get needed support, as revealed in our formative study (N=10). In this work, we present an interactive visual tool named ComViewer to help viewers seek social support in OMHCs. With ComViewer, viewers can filter posts of different topics and find supportive comments via a zoomable circle packing visual component that adapts to searched keywords. Powered by LLM, ComViewer supports an interactive sensemaking process by enabling viewers to interactively highlight, summarize, and question any community content. A within-subjects study (N=20) demonstrates ComViewer's strengths in providing viewers with a more simplified, more fruitful, and more engaging support-seeking experience compared to a baseline OMHC interface without ComViewer. We further discuss design implications for facilitating information-seeking and sense making in online mental health communities.

Paper Structure

This paper contains 58 sections, 6 figures, 3 tables.

Figures (6)

  • Figure 1: A common information-seeking flow in online mental health communities. ComViewer supports this flow with a Zoomable Posts Panel, a Note-taking Panel, and a Questioning Panel.
  • Figure 2: ComViewer: (A) The Zoomable Posts panel consists of (A1) the Post-list View, which shows the searching posts lists results in the OMHC; (A2) the Circle Packing View which allows viewers to interact with posts and comments with (1-3): three levels of posts visualization, and (A3) the Support Filtering View, which help viewers filter posts/comments based on their desired level of social support; (B) The Note-taking panel consists of (B1) the Post-detail view with the interactive component which allow viewers to highlight or select reading content to inform organization and questioning, (B2) the Folder view which allows viewers to organize useful information while reading consists of (4-6) three folders according to colors; (C) the Questioning panel which allows viewers to ask questions while reading and displays the question flow.
  • Figure 3: The Zoomable Posts Panel has three levels: (A) the topic level, (B) the post level, and (C) the comment level. (A1) Topical keywords for the posts cluster that are highly relevant to the search query. (A2) Bar charts in which the length of and the number next to each bar indicate how many posts in the current circle pack seek a certain level of informational or emotional support in the topic or post level, or how many comments provide a specific level of informational or emotional support in the comment level. (B1) A hovered post circle with a white border and its title displayed alongside. (B2) Posts with content similar to that of the currently hovered post are highlighted in black. (B3) Selecting the bar corresponding to posts that provide high informational support to help filter posts in the circle packing view. (C1) Selecting the bar corresponding to comments that provide high emotional and informational support to help filter comments in the circle packing view.
  • Figure 4: Folder view: (A) Collection page (B) Summary page (C) Mind map page. (A1) Folder labels with the same color as the highlighted color for color-coded content organization. (A2) Three on-page conversion buttons. (A3) Modifications to the collection. (A4) Button to jump back to the highlighted address in the text. (B1) Modifications to the summary. (C1) Operations component for mind map.
  • Figure 5: Questioning Panel: (A) Folder boards to show the list of questions. (B) Whiteboard with a question and generated answer. (C) Modification to the answer. (D) Recommended questions. (E) Input box for adding new questions. (F) Linear layout of whiteboards to show continuity of questions. (G) Horizontal layout of questions to demonstrate multi-dimensionality of questions.
  • ...and 1 more figures