Answers are grounded in this paper and cite their sources.
Analysis of user interactions in online health communities reveals distinct progression patterns, suggesting key features for improving health recommender systems.
This study explores how ovarian cancer (OvCa) patients and caregivers engage with online health communities (OHCs), offering insights to address the cold‐start problem in health recommender systems. Analyzing 909 initial posts and 14,816 comments from the National Ovarian Cancer Coalition (NOCC) forum, we examined how users’ contributions evolve over time. Initial interactions typically center on emotional support and personal experience sharing, while more advanced engagement, such as advice and referrals, emerge later as users gain more domain knowledge. We introduce a novel “start position” metric to identify when users begin providing each support type. Our results reveal distinct progression patterns and emphasize the importance of dynamic user modeling to reflect users’ evolving knowledge and roles. These findings inform the design of OvCa‐specific recommender system, which our team develops with support of the National Library of Medicine.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: