Aspect-based opinion polling from customer reviews

Jingbo ZHU, Huizhen WANG, Muhua ZHU, Ka Yin Benjamin TSOU, Matthew MA

Research output: Contribution to journalArticlespeer-review

129 Citations (Scopus)


Opinion polling has been traditionally done via customer satisfaction studies in which questions are carefully designed to gather customer opinions about target products or services. This paper studies aspect-based opinion polling from unlabeled free-form textual customer reviews without requiring customers to answer any questions. First, a multi-aspect bootstrapping method is proposed to learn aspect-related terms of each aspect that are used for aspect identification. Second, an aspect-based segmentation model is proposed to segment a multi-aspect sentence into multiple single-aspect units as basic units for opinion polling. Finally, an aspect-based opinion polling algorithm is presented in detail. Experiments on real Chinese restaurant reviews demonstrated that our approach can achieve 75.5 percent accuracy in aspect-based opinion polling tasks. The proposed opinion method does not require labeled training data. It is thus easy to implement and can be applicable to other languages (e.g. English) or other domains such as product or movie reviews. Copyright © 2011 IEEE.
Original languageEnglish
Pages (from-to)37-49
JournalIEEE Transactions on Affective Computing
Issue number1
Publication statusPublished - Jan 2011


Zhu, J., Wang, H., Zhu, M., Tsou, B. K., & Ma, M. (2011). Aspect-based opinion polling from customer reviews. IEEE Transactions on Affective Computing, 2(1), 37-49.


  • Opinion mining
  • Aspect-based analysis
  • Opinion polling
  • Sentiment analysis


Dive into the research topics of 'Aspect-based opinion polling from customer reviews'. Together they form a unique fingerprint.