TwitterSentiDetector: a domain-independent Twitter sentiment analyser. Issue 2 (3rd April 2018)

• Record Type: Journal Article
• Authors: Kabakus, Abdullah Talha; Kara, Resul
• Is Part Of: Infor. Volume 56:Issue 2(2018)
• Page Start: 137
• Page End: 162
• Publication Date: 2018-04-03
• Subjects: Twitter sentiment analysis -- sentiment analysis -- natural language processing -- social media mining -- sentiment detection; Operations research -- Periodicals; Electronic data processing -- Periodicals; Systems engineering -- Periodicals; Systems engineering; Electronic data processing; Periodicals; 003.05
• DOI: 10.1080/03155986.2017.1340797
• Languages: English
• ISSNs: 0315-5986

Abstract

ABSTRACT: Sentiment analysis has become more crucial after the rise of social media, especially the Twitter since it provides structured and publicly available data. TwitterSentiDetector is a domain-dependent and unsupervised Twitter sentiment analyser that focuses on the differences occurred by the informal language used in Twitter. TwitterSentiDetector uses natural language processing techniques alongside the proposed linguistic methods to classify sentiments of tweets into positive, negative, and neutral through the polarity scores obtained from sentiment lexicons. According to tests on widely used Twitter data-sets that contain manually detected sentiments labels alongside tweets, TwitterSentiDetector' s sentiment detection ratio is calculated as up to 69%. When the target sentiment classes are decreased to positive and negative, the detection ratio is increased up to 87%. The results are calculated very similarly when the same data-set is evaluated by the proposed tweet-level context aware sentiment analysis module which confirms the validity of each approach.