Dataset Information

Finding influential users of online health communities: a new metric based on sentiment influence.

ABSTRACT:

Objective

Online health communities (OHCs) have become a major source of support for people with health problems. This research tries to improve our understanding of social influence and to identify influential users in OHCs. The outcome can facilitate OHC management, improve community sustainability, and eventually benefit OHC users.

Methods

Through text mining and sentiment analysis of users' online interactions, the research revealed sentiment dynamics in threaded discussions. A novel metric--the number of influential responding replies--was proposed to directly measure a user's ability to affect the sentiment of others.

Results

Using the dataset from a popular OHC, the research demonstrated that the proposed metric is highly effective in identifying influential users. In addition, combining the metric with other traditional measures further improves the identification of influential users.

SUBMITTER: Zhao K

PROVIDER: S-EPMC4173171 | biostudies-literature | 2014 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Finding influential users of online health communities: a new metric based on sentiment influence.

Zhao Kang K Yen John J Greer Greta G Qiu Baojun B Mitra Prasenjit P Portier Kenneth K

Journal of the American Medical Informatics Association : JAMIA 20140121 e2

<h4>Objective</h4>Online health communities (OHCs) have become a major source of support for people with health problems. This research tries to improve our understanding of social influence and to identify influential users in OHCs. The outcome can facilitate OHC management, improve community sustainability, and eventually benefit OHC users.<h4>Methods</h4>Through text mining and sentiment analysis of users' online interactions, the research revealed sentiment dynamics in threaded discussions. ...[more]

PMID: 24449805

Similar Datasets

Project description:BackgroundElectronic health (eHealth) literacy is an important skill that allows patients to navigate intelligibly through the vast, often misleading Web-based world. Although eHealth literacy has been investigated in general and specific demographic populations, it has not yet been analyzed on users of online health communities (OHCs). Evidence shows that OHCs are important Web 2.0 applications for patients for managing their health, but at the same time, warnings have been expressed regarding the quality and relevance of shared information. No studies exist that investigate levels of eHealth literacy among users of OHCs and differences in eHealth literacy between different types of users.ObjectiveThe study aimed to investigate eHealth literacy across different types of users of OHCs based on a revised and extended eHealth literacy scale (eHEALS).MethodsThe study was based on a cross-sectional Web survey on a simple random sample of 15,000 registered users of the most popular general OHC in Slovenia. The final sample comprised 644 users of the studied OHC. An extended eHEALS (eHEALS-E) was tested with factor analytical procedures, whereas user types were identified with a hierarchical clustering algorithm. The research question was analyzed with analysis of variance (ANOVA) procedure and pairwise comparison tests.ResultsFactor analysis of the revised and extended eHEALS revealed six dimensions: awareness of sources, recognizing quality and meaning, understanding information, perceived efficiency, validating information, and being smart on the Net. The factor solution demonstrates a good fit to the data (root mean square error of approximation [RMSEA]=.059). The most developed dimension of eHEALS-E is awareness of different Internet sources (mean=3.98, standard deviation [SD]=0.61), whereas the least developed is understanding information (mean=3.11, SD=0.75). Clustering resulted in four user types: active help-seekers (48.3%, 311/644), lurkers (31.8%, 205/644), core relational users (16.9%, 109/644), and low-engaged users (3%, 19/644). Analysis of the research question showed statistically significant differences among user types across all six dimensions of eHEALS-E. Most notably, core relational users performed worse than lurkers on the validating information dimension (P=.01) and worse than active help-seekers on the being smart on the Net dimension (P=.05). Active help-seekers have the highest scores in all dimensions of the eHEALS-E, whereas low-engaged users have statistically significantly lower scores on all dimensions of the eHEALS-E in comparison with the other groups.ConclusionsThose who are looking for advice and support in OHCs by making queries are well equipped with eHealth literacy skills to filter potential misinformation and detect bad advice. However, core relational users (who produce the most content in OHCs) have less-developed skills for cross-validating the information obtained and navigating successfully through the perils of the online world. Site managers should monitor their activity to avoid the spread of misinformation that might lead to unhealthy practices.

Dataset Information

Finding influential users of online health communities: a new metric based on sentiment influence.

Objective

Methods

Results

Publications

Finding influential users of online health communities: a new metric based on sentiment influence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets