Using Custom Fuzzy Thesaurus to Incorporate Semantic and Reduce Data Sparsity for Twitter Sentiment Analysis

Heba M. Ismail, Nazar Zaki, Boumediene Belkhouche

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Considerable research efforts have been devoted to Twitter sentiment analysis in recent years. Given the informal writing style of Twitter, there exists an endless variety of sound vocabulary, slogans, emoticons and special characters that can be used to express one's opinion in a maximum of 140-characters. This results in a sparsity problem making the training of machine learning classifiers from Twitter data a highly challenging task. In this work we propose using sentiment replacement of Twitter slogans and incorporating a fuzzy thesaurus for twitter sentiment classification in order to incorporate semantic as well as solve the sparsity problem. The experimental results show that the proposed method consistently outperforms the baselines in addition to some methods in the literature.

Original languageEnglish
Title of host publicationProceedings - 2016 3rd International Conference on Soft Computing and Machine Intelligence, ISCMI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages47-52
Number of pages6
ISBN (Electronic)9781509036967
DOIs
Publication statusPublished - Oct 2 2017
Event3rd International Conference on Soft Computing and Machine Intelligence, ISCMI 2016 - Dubai, United Arab Emirates
Duration: Nov 23 2016Nov 25 2016

Publication series

NameProceedings - 2016 3rd International Conference on Soft Computing and Machine Intelligence, ISCMI 2016

Other

Other3rd International Conference on Soft Computing and Machine Intelligence, ISCMI 2016
Country/TerritoryUnited Arab Emirates
CityDubai
Period11/23/1611/25/16

Keywords

  • data sparsity
  • fuzzy set information retrieval
  • semantic sentiment
  • sentiment analysis
  • text mining
  • twitter

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Using Custom Fuzzy Thesaurus to Incorporate Semantic and Reduce Data Sparsity for Twitter Sentiment Analysis'. Together they form a unique fingerprint.

Cite this