Enhancing Health Information-Gathering Experiences in Online Health Communities

Abstract

Online health communities can offer a range of diverse personal health expertise and experiences, yet gathering relevant health information is a significant challenge for members and researchers as each party faces different obstacles. For instance, members face challenges that pertain to text based computer-mediated communication (CMC) and information availability as determined by the active participation of other members. Similarly, the challenge of making sense of vast amounts of text prevents researchers from reaping the full benefits of the collective knowledge. In my dissertation, I examine the challenges of gathering health information from online health communities in two parts according to the respective stakeholders. I first address the challenge that patient members face during their time of interaction with the online community to gather information. Within the context of CMC in online health communities, I focus on issues associated with topic changes–topic drift—and sustainment of active participation–posting messages to participate in the communities. Next, I address the challenge of processing and making sense of a large amount of collective knowledge shared in online health communities. Within the context of patient-generated text in online cancer communities, I focus on the challenges of automatically understanding patient-generated text using existing natural language processing (NLP) tools. More specifically, my specific aims for this dissertation are: 1. Understand topic drift and its effect on gathering health information from online health communities 2. Understand the beneficial effects of vocabulary similarity–homophily of vocabulary usage—associated with active participation in online health communities 3. Understand the challenges of automatically processing online community text and automated methods to detect failures I examine these specific aims using two distinct online health communities: cancerconnect.com (a small, private online health community for patients with a wide range of cancers) and webmd.com (a large, public online health community with many non-cancer, disease-specific sub-communities). One of the most important findings I discovered is that many members of online communities are willing to go the extra mile to help others in similar situations. Yet, many challenges are hindering the experience of gathering health information from online health communities. Although these efforts leave a digital trace that is embedded with diverse personal health expertise and experiences, we still lack the capability to automatically utilize this invaluable information. I contribute to resolving the issues faced by members and researchers; thereby, maximizing the benefits of online health communities and improving the experience of gathering health information from them. I extend the existing knowledge related to topic drift, sustaining active participation, and processing patient-generated text with respect to the experience of gathering health information from online health communities.