Files in this item



application/pdf065_ready.pdf (611kB)
(no description provided)PDF


application/octet-stream065.epub (2MB)


application/ (483kB)


Title:A Machine Learning Approach for Rating the Quality of Depression Treatment Web Pages
Author(s):Zhang, Yanjun; Cui, Hong; Burkell, Jacquelyn; Mercer, Robert E.
Subject(s):machine learning
Naive Bayes classification
quality assessment
web health care information
evidence-based health care guidelines
Abstract:As health care information proliferates on the web, the content quality is varied and difficult to assess, partially due to the large volume and the dynamicity. This paper reports an automated approach in which the quality of depression treatment web pages is assessed according to evidence-based depression treatment guidelines. A supervised machine learning technique, specifically Naive Bayes classification, is used to identify the sentences that are consistent with the guidelines. The quality score of a depression treatment web page is the number of unique evidence-based guidelines covered in this page. Significant Pearson correlation (p<.001) was found between the quality rating results by the machine learning approach and the results by human raters on 31 depression treatment web pages in this case study. The semantic-based, machine learning quality rating method is promising and it may lead to an efficient and effective quality assessment mechanism for health care information on the Web.
Issue Date:2014-03-01
Citation Info:Zhang, Y., Cui, H., Burkell, J., & Mercer, R. E. (2014). A Machine Learning Approach for Rating the Quality of Depression Treatment Web Pages. In iConference 2014 Proceedings (p. 192 - 212). doi:10.9776/14065
Series/Report:iConference 2014 Proceedings
Genre:Conference Paper / Presentation
Other Identifier(s):65
Publication Status:published
Peer Reviewed:yes
Rights Information:Copyright 2014 is held by the authors of individual items in the proceedings. Copyright permissions, when appropriate, must be obtained directly from the authors.
Date Available in IDEALS:2014-02-28

This item appears in the following Collection(s)

Item Statistics