Sentiment classification of Chinese cosmetic reviews based on integration of collocations and concepts

• Published in: Electronic library Vol. 38; no. 1; pp. 155 - 169
• Main Authors: Hung, Chihli, Cao, You-Xin
• Format: Journal Article
• Language: English
• Published: Oxford Emerald Publishing Limited 19.03.2020; Emerald Group Publishing Limited
• Subjects: Academic Achievement; Activity Units; Benchmarks; Chinese; Classification; Collocation methods; Consumer satisfaction; Cosmetics; Data mining; Decision making; Decision trees; Documents; Domains; Evaluation; Internet; Modelling; Multilayer perceptrons; Negative Attitudes; Opinions; Preferences; Research Methodology; Researchers; Romanization; Semantics; Semiotics; Sentiment analysis; Support vector machines; Teaching Methods; User generated content; Word of mouth advertising; Word Processing; China; Sentiment analysis; Context-aware lexicon; Word of mouth; Preference vector modelling; Chinese collocation
• ISSN: 0264-0473; 1758-616X; 1758-616X
• DOI: 10.1108/EL-04-2019-0093

Purpose This paper aims to propose a novel approach which integrates collocations and domain concepts for Chinese cosmetic word of mouth (WOM) sentiment classification. Most sentiment analysis works by collecting sentiment scores from each unigram or bigram. However, not every unigram or bigram in a WOM document contains sentiments. Chinese collocations consist of the main sentiments of WOM. This paper reduces the complexity of the document dimensionality and makes an improvement for sentiment classification. Design/methodology/approach This paper builds two contextual lexicons for feature words and sentiment words, respectively. Based on these contextual lexicons, this paper uses the techniques of associated rules and mutual information to build possible Chinese collocation sets. This paper applies preference vector modelling as the vector representation approach to catch the relationship between Chinese collocations and their associated concepts. Findings This paper compares the proposed preference vector models with benchmarks, using three classification techniques (i.e. support vector machine, J48 decision tree and multilayer perceptron). According to the experimental results, the proposed models outperform all benchmarks evaluated by the criterion of accuracy. Originality/value This paper focuses on Chinese collocations and proposes a novel research approach for sentiment classification. The Chinese collocations used in this paper are adaptable to the content and domains. Finally, this paper integrates collocations with the preference vector modelling approach, which not only achieves a better sentiment classification performance for Chinese WOM documents but also avoids the curse of dimensionality.