Title: Towards an Information Theory Based Methodology for the Quality Assessment of Online Comments

Year of Publication: March - 2014
Page Numbers: 14-19
Authors: Otto K.M. Cheng , Raymond Y.K. Lau
Conference Name: The Second International Conference on E-Technologies and Business on the Web (EBW2014)
- Malaysia


With the rapid proliferation of the Social Web, there has been an exponential growth of the number of usercontributed online comments posted to the Internet these days. These online comments contain users' opinions about various entities such as consumer products, financial products, social events, political figures, and so on. Accordingly, firms or individuals can leverage these ever increasing online comments to extract valuable business intelligence to facilitate business strategy development or consumer comparison shopping. Meanwhile, firms have strong financial motivation to strategically manipulate online comments to boost sales, and political parties have the political motivation to strategically influence online comments to strengthen their political campaigns. As a result, there has been growing concerns about the quality and the truthfulness of user-contributed online comments. Although a lot of research about opinion mining has been carried out, relatively little work about the systematic assessment of the quality of online comments is done. To improve the hygiene and the usefulness of online comments, there is a pressing need to develop a robust methodology for an objective and systematic assessment of the quality of online comments. The main contribution of this paper is the design, development, and evaluation of a novel information theory based methodology for the assessment of the quality of online comments. Our preliminary experiments show that the proposed quality assessment methodology is more effective than other baseline methods such as a peer-review based quality assessment approach.