Opinion Influence Analysis in Online Forum Threads

Author

Cercel, Dumitru-Clementin ; Trausan-Matu, Stefan

Author_Institution

Fac. of Autom. Control & Comput., Univ. Politeh. of Bucharest, Bucharest, Romania

fYear

2014

fDate

22-25 Sept. 2014

Firstpage

228

Lastpage

235

Abstract

This paper treats the phenomenon of opinion influence in online forum threads. Influence among users´ opinions is analyzed by taking into consideration the changes in their opinions. Therefore, a change in a user´s opinion is modeled as a change of his/her posts´ polarity. The hypothesis that underlies our research is that users´ opinions may change over time as a consequence of the interactions between them in online discussions such as online forum threads. Moreover, a user´s new post in an online forum thread is considered to have an influence on all the posts sent by other users in reaction to this. Our approach to the opinion influence phenomenon that arises in online forum threads is based on Natural Language Processing techniques, Latent Semantic Analysis and Post-Level Sentiment Analysis. The results obtained by us show that all the previous posts that contain opinions have an influence, more or less significant, on a new post in the same online forum thread.

Keywords

Internet; Web sites; natural language processing; latent semantic analysis; natural language processing techniques; online discussions; online forum threads; opinion influence analysis; opinion influence phenomenon; post-level sentiment analysis; user opinion; Instruction sets; Media; Message systems; Natural language processing; Semantics; Social network services; Speech; Latent Semantic Analysis; Online Forum Thread; Opinion Influence; Reply Chain;

fLanguage

English

Publisher

ieee

Conference_Titel

Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), 2014 16th International Symposium on

Conference_Location

Timisoara

Print_ISBN

978-1-4799-8447-3

Type

conf

DOI

10.1109/SYNASC.2014.38

Filename

7034688