Exploring Self-Identified Counseling Expertise in Online Support Forums

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4467–4480 August 1–6, 2021. ©2021 Association for Computational Linguistics 4467 Exploring Self-Identified Counseling Expertise in Online Support Forums Allison Lahnala1, Yuntian Zhao1, Charles Welch1, Jonathan K. Kummerfeld1, Lawrence An2,4, Kenneth Resnicow3,4, Rada Mihalcea1, Ver´onica P´erez-Rosas1 1Computer Science & Engineering, University of Michigan 2Medical School, University of Michigan 3School of Public Health, University of Michigan 4Center for Health Communications Research, University of Michigan {alcllahn,clzhao,cfwelch,jkummerf,lcan, kresnic,mihalcea,vrncapr}@umich.edu Abstract A growing number of people engage in online health forums, making it important to under- stand the quality of the advice they receive. In this paper, we explore the role of expertise in responses provided to help-seeking posts regarding mental health. We study the dif- ferences between (1) interactions with peers; and (2) interactions with self-identified men- tal health professionals. First, we show that a classifier can distinguish between these two groups, indicating that their language use does in fact differ. To understand this difference, we perform several analyses addressing engage- ment aspects, including whether their com- ments engage the support-seeker further as well as linguistic aspects, such as dominant language and linguistic style matching. Our work contributes toward the developing efforts of understanding how health experts engage with health information- and support-seekers in social networks. More broadly, it is a step toward a deeper understanding of the styles of interactions that cultivate supportive engage- ment in online communities. 1 Introduction Online social media forums play a critical role in health-related information sharing (Record et al., 2018). Health experts have noted that they can help reduce healthcare inequalities and improve access to health care, for instance by empowering coalitions of people living with chronic illness or specific disabilities (Griffiths et al., 2012), or by providing an anonymous forum for people seeking emotional support (De Choudhury and De, 2014). On the other hand, these forums elevate concerns about spreading medically inaccurate, misleading, or unsound information (Dom´ınguez and Sapi˜na, 2015; Gage-Bouchard et al., 2018), which has had harmful public health impacts (Poland et al., 2011; Nobles et al., 2019). One study concluded that health information seekers in forums such as Red- dit are likely to enact suggested behaviors regard- less of perceived credibility (Record et al., 2018). However, the researchers also noted that this open- ness to information could be an opportunity for experts to encourage healthy behaviors through in- formation sharing. In this landscape, it is critical to understand the dynamics that cultivate safe communities that ben- efit the health and well-being of their participants and the broader implications for health commu- nication (Chou et al., 2009). Health experts are thus considering social media’s role in their in- teractions with patients and broader public health issues, and their role in engaging with the plat- forms (Dom´ınguez and Sapi˜na, 2015; Nobles et al., 2019, 2020). This motivates an important research direction: understanding how experts engage with users in online platforms. This can inform platform design, moderation decisions, and health promo- tion efforts by experts. This work focuses …

Content truncated to 500 words