RepComment: A Fair Comment-Sentiment Representation System

Author

Ting Wu ; Chun Yin Tan ; Ming Yip Cheung ; Pan Hui

Author_Institution

Dept. of Comput. Sci. & Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China

fYear

2014

fDate

14-14 Dec. 2014

Firstpage

1246

Lastpage

1249

Abstract

Most Online Social Networks (OSNs) allow registered members to leave comments on particular entities. An entity can either be a person, a location, or a product. These comments have already become an important reference for many people in the daily life. However, a popular entity usually receives an extensive number of comments and it has become infeasible for users to read through all of them. In this demonstration, we propose Rep Comment, a fair comment-sentiment representation system based on a novel probability sampling model that can choose a small set of comments (samples) that are most resemble and representative for the original comment set. The proposed approximation algorithm significantly reduces the computation cost of the sampling problem while keeping relatively high accuracy.

Keywords

approximation theory; data mining; information filtering; probability; sampling methods; social networking (online); OSN; RepComment; approximation algorithm; fair comment-sentiment representation system; online social network; probability sampling model; Accuracy; Approximation algorithms; Approximation methods; Crawlers; Distance measurement; Optimization; Social network services; Comment Sampling; Online Social Network; Probability Model;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Mining Workshop (ICDMW), 2014 IEEE International Conference on

Conference_Location

Shenzhen

Print_ISBN

978-1-4799-4275-6

Type

conf

DOI

10.1109/ICDMW.2014.22

Filename

7022745