Discovering negative comments by sentiment analysis on web forum

Wei Yun Hsu, Hui Huang Hsu*, Vincent Shin-Mu Tseng

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Social media enables people to communicate with each other on the Internet in real-time and rich styles. In other words, there is a lot of information on the social media. If we can extract negative opinions of some brands, enterprises or politics, we can use these opinions to know the market demands and solve problems. In this paper, we propose a novel approach to extract negative-sentiment-oriented features and identify negative opinions in social media with text mining and machine learning techniques, support vector machine and neural network, as well as data collection with Web crawler. The experimental results show that our proposed methods can work effectively.

Original languageEnglish
Pages (from-to)1297-1311
Number of pages15
JournalWorld Wide Web
Issue number3
StatePublished - 15 May 2019


  • neural network
  • sentiment analysis
  • support vector machine
  • text mining


Dive into the research topics of 'Discovering negative comments by sentiment analysis on web forum'. Together they form a unique fingerprint.

Cite this