Can the adoption of health information on social media be predicted by information characteristics?. Issue 1 (8th December 2020)

• Record Type: Journal Article
• Authors: Wang, Zhibing; Sun, Zhumei
• Is Part Of: Aslib journal of information management. Volume 73:Issue 1(2021)
• Page Start: 80
• Page End: 100
• Publication Date: 2020-12-08
• Subjects: Information adoption -- Health information -- Social media -- Information characteristics -- Prediction -- Support vector machine; Information science -- Periodicals; Library science -- Periodicals; 020.5
• DOI: 10.1108/AJIM-12-2019-0369
• Languages: English
• ISSNs: 2050-3806

Abstract

Abstract : Purpose: This paper aims to explore the relationship between the characteristics of social media health information and its adoption. The purpose is to identify information characteristics that can be used to estimate the level of health information adoption in advance. Design/methodology/approach: According to the Information Adoption Model (IAM), the study extracted ten information characteristics from the aspects of information quality and information source credibility. The sample data was collected from the top ten influential health accounts based on the Impact List of Sina Weibo to test the effectiveness of these characteristics in distinguishing information at different levels of adoption. The forecasting of information adoption level is regarded as a binary classification question in the study and support vector machine (SVM) is used to do the research. Findings: The results indicate that ten information characteristics chosen in this study are related to information adoption. Based on these information characteristics, it is feasible to estimate the level of health information adoption, and the estimation accuracy is relatively high. Originality/value: A lot of work has been done in previous researches to reveal the factors that influence information adoption. The theoretical contribution of this work is to further discuss how to use the influencing factors to do some predictive work for information adoption. In practice, it will help health information publishers to disseminate high-quality health information more effectively as well as promote the adoption of health information.