Table of Contents
Fetching ...

Peer Recommendation Interventions for Health-related Social Support: a Feasibility Assessment

Zachary Levonian, Matthew Zent, Ngan Nguyen, Matthew McNamara, Loren Terveen, Svetlana Yarosh

TL;DR

This paper tackles whether peer recommendation interventions can meaningfully affect health-related online peer connections. It designs an email-based Site Suggestion interface with a content-based, implicit-feedback recommender and tests it in CaringBridge over 12 weeks, focusing on reading and interacting with peers. The findings provide evidence of demand, practical feasibility, and modest efficacy signals (readership and some interactions) while showing no clear second-order harms, thereby supporting a larger, controlled trial to establish causal health benefits. The work offers practical guidance on implementing and evaluating peer recommendations in OHCs and discusses design choices to balance personalization, privacy, and user well-being.

Abstract

Online health communities (OHCs) offer the promise of connecting with supportive peers. Forming these connections first requires finding relevant peers - a process that can be time-consuming. Peer recommendation systems are a computational approach to make finding peers easier during a health journey. By encouraging OHC users to alter their online social networks, peer recommendations could increase available support. But these benefits are hypothetical and based on mixed, observational evidence. To experimentally evaluate the effect of peer recommendations, we conceptualize these systems as health interventions designed to increase specific beneficial connection behaviors. In this paper, we designed a peer recommendation intervention to increase two behaviors: reading about peer experiences and interacting with peers. We conducted an initial feasibility assessment of this intervention by conducting a 12-week field study in which 79 users of CaringBridge received weekly peer recommendations via email. Our results support the usefulness and demand for peer recommendation and suggest benefits to evaluating larger peer recommendation interventions. Our contributions include practical guidance on the development and evaluation of peer recommendation interventions for OHCs.

Peer Recommendation Interventions for Health-related Social Support: a Feasibility Assessment

TL;DR

This paper tackles whether peer recommendation interventions can meaningfully affect health-related online peer connections. It designs an email-based Site Suggestion interface with a content-based, implicit-feedback recommender and tests it in CaringBridge over 12 weeks, focusing on reading and interacting with peers. The findings provide evidence of demand, practical feasibility, and modest efficacy signals (readership and some interactions) while showing no clear second-order harms, thereby supporting a larger, controlled trial to establish causal health benefits. The work offers practical guidance on implementing and evaluating peer recommendations in OHCs and discusses design choices to balance personalization, privacy, and user well-being.

Abstract

Online health communities (OHCs) offer the promise of connecting with supportive peers. Forming these connections first requires finding relevant peers - a process that can be time-consuming. Peer recommendation systems are a computational approach to make finding peers easier during a health journey. By encouraging OHC users to alter their online social networks, peer recommendations could increase available support. But these benefits are hypothetical and based on mixed, observational evidence. To experimentally evaluate the effect of peer recommendations, we conceptualize these systems as health interventions designed to increase specific beneficial connection behaviors. In this paper, we designed a peer recommendation intervention to increase two behaviors: reading about peer experiences and interacting with peers. We conducted an initial feasibility assessment of this intervention by conducting a 12-week field study in which 79 users of CaringBridge received weekly peer recommendations via email. Our results support the usefulness and demand for peer recommendation and suggest benefits to evaluating larger peer recommendation interventions. Our contributions include practical guidance on the development and evaluation of peer recommendation interventions for OHCs.
Paper Structure (99 sections, 17 figures, 20 tables)

This paper contains 99 sections, 17 figures, 20 tables.

Figures (17)

  • Figure 1: Study outline: assessing the feasibility of a peer recommendation intervention in an OHC.
  • Figure 2: The CaringBridge interface. We record six logged-in user actions: visits (to any of these site pages), follows (clicks on "Follow Site" and others, see sec. \ref{['sec:prior_use']}), Journal updates, reactions (on Journal updates, comments, or guestbooks), comments (on Journal updates or guestbooks), and guestbooks.
  • Figure 3: Existing design of email notifications on CaringBridge and the Site Suggestion email interface designed for this study. Data shown is a representative fabrication.
  • Figure 4: CaringBridge peer recommendation system overview. Full details in Appendix \ref{['app:sec:hyperparameter_search']}.
  • Figure 5: Field study timeline.
  • ...and 12 more figures