A method for analyzing health behavior in online forums

Thumbnail Image

Files

CHS-2.pdf (581.51 KB)

Links to Files

https://dl.acm.org/doi/abs/10.1145/2808719.2812592

Permanent Link

https://doi.org/10.1145/2808719.2812592
 http://hdl.handle.net/11603/22434

Collections

UMBC Information Systems Department
UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2015-09-09

Type of Work

conference papers and proceedings
preprints
Text

Department

Program

Citation of Original Publication

Yesha, Rose; Gangopadhyay, Aryya; A method for analyzing health behavior in online forums; BCB '15: Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics, 9 September, 2015, Pages 615–621; https://doi.org/10.1145/2808719.2812592

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Abstract

The prevalence of online social networks has enabled users to communicate, connect, and share content. Many of these networks serve as the de-facto Internet portal for millions of users. Due to the enormous popularity of these sites, the data about the users and their communications offer an enormous opportunity to analyze human behaviors on a large scale. It is important to analyze patterns within these records in order to more effectively treat individuals. In this paper, a method is presented for identifying these themes and patterns within forum data. This methodology includes automatic extraction of the main themes or patterns in the data, quantify the similarities and differences in the contents of different online forums, and finding similar documents based on user queries. We used data sets from four different forums. In this paper we describe a method that automatically differentiates between online discussion groups related to different behavioral health challenges and identifies the most appropriate discussion forum for a given input. Finally, we evaluated the efficacy of our method by using cross-validation.