Work

Content-specific network analysis of peer-to-peer communication in an online community for smoking cessation.

Year: 2016

Type: article

Abstract: Analysis of user interactions in online communities could improve our understanding of health-related behaviors and inform the design of technological solutions that support behavior change. However, to achieve this we would need methods that provide granular perspective, yet are scalable. In this paper, we present a methodology for high-throughput semantic and network analysis of large social media datasets, combining semi-automated text categorization with social network analytics. We apply this method to derive content-specific network visualizations of 16,492 user interactions in an online community for smoking cessation. Performance of the categorization system was reasonable (average F-measure of 0.74, with system-rater reliability approaching rater-rater reliability). The resulting semantically specific network analysis of user interactions reveals content- and behavior-specific network topologies. Implications for socio-behavioral health and wellness platforms are also discussed.

Source: PubMed Central

Authors: Sahiti Myneni, Nathan K Cobb, Trevor Cohen

Institution: Georgetown University

Language: English

Topic: Smoking Behavior and Cessation

Subfield: Public Health, Environmental and Occupational Health

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

Funder: U.S. National Library of Medicine

Award: Content-based social network analysis methods for data-driven health promotion