ENHANCED TWOFOLD-LDA MODEL FOR ASPECT DISCOVERY AND SENTIMENT CLASSIFICATION

Nicola Burns, Y Bi, H. Wang, Terry Anderson

Research output: Contribution to journalArticle

78 Downloads (Pure)

Abstract

There is a need to automatically classify information from online reviews. Customers want to know useful information about different aspects of a product or service and also the sentiment expressed towards each aspect. This paper proposes an Enhanced Twofold-LDA model (Latent Dirichlet Allocation), in which one LDA is used for aspect assignment and another is used for sentiment classification, aiming to automatically determine aspect and sentiment. The enhanced model incorporates domain knowledge (i.e. seed words) to produce more focused topics and has the ability to handle two aspects in at the sentence level simultaneously. The experiment results show that the Enhanced Twofold-LDA model is able to produce topics more related to aspects in comparison to the state of arts method ASUM (Aspect and Sentiment Unification Model), whereas comparable with ASUM on sentiment classification performance. Additionally, an investigation is carried out to show the importance of research for customer satisfaction on various visual charts.
Original languageEnglish
JournalInternational Journal of Knowledge-Based Organizations
Publication statusAccepted/In press - 1 Aug 2018

Fingerprint Dive into the research topics of 'ENHANCED TWOFOLD-LDA MODEL FOR ASPECT DISCOVERY AND SENTIMENT CLASSIFICATION'. Together they form a unique fingerprint.

  • Cite this