Feature Based Opinion Mining for Restaurant Reviews

  • Nithin Y.R
  • Poornalatha G.Email author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 678)


Product reviews or customer feedback has become a platform for retailers to plan marketing strategy and also for new customers to select their appropriate product. Since the trend of e-commerce is increasing, an amount of customer reviews also has been increased to a greater extent. Consequently, it becomes a tough task for retailers as well as customers to read the reviews associated with the product. Sentiment analysis resolves this issue by scanning through free text reviews and providing the opinion summary. However, it does not provide detailed information, such as features on which the product is reviewed. Feature-based sentiment analysis methods increases the granularity of sentiment analysis by analyzing polarity associated with features in the given free text. The main objective of this work is to design a system that predicts polarity at aspect level and to design a score calculating scheme that defines the extent of polarity. Obtained feature - level scores are summarized according to users’ priority of interest.


Natural language processing Aspects Reviews Free text Star rating 


  1. 1.
    Why online store owners should embrace online reviews. Accessed 21 Apr 2017
  2. 2.
    Liu, B.: Sentiment analysis and subjectivity. In: Handbook of Natural Language Processing, pp. 627–666 (2010)Google Scholar
  3. 3.
    Liu, B.: Sentiment analysis and opinion mining. In: Synthesis Lectures on Human Language Technologies, pp. 1–167 (2012)Google Scholar
  4. 4.
    Bagheri, A., Saraee, M., de Jong, F.: Care more about customers: Unsupervised domain-independent aspect detection for sentiment analysis of customer reviews. Knowl.-Based Syst. 52, 201–213 (2013)CrossRefGoogle Scholar
  5. 5.
    Petz, G., Karpowicz, M., Fürschuß, H., Auinger, A., Str̆íteský, V., Holzinger, A.: Computational approaches for mining user’s opinions on the web 2.0. Inf. Process. Manage. 50(6), 899–908 (2014)CrossRefGoogle Scholar
  6. 6.
    Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: Proceedings of the 2008 International Conference on Web Search and Data Mining, pp. 231–240 (2008)Google Scholar
  7. 7.
    Baccianella, S., Esuli, A., Sebastiani, F.: Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of LREC, pp. 2200–2204 (2010)Google Scholar
  8. 8.
    Dongre, A.G., Dharurkar, S., Nagarkar, S., Shukla, R., Pandita, V.: A survey on aspect based opinion mining from product reviews. Int. J. Innovat. Res. Sci. Eng. Technol. 5(2), 1415–1418 (2016)Google Scholar
  9. 9.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168–177 (2004)Google Scholar
  10. 10.
    Zhu, J., Wang, H., Zhu, M., Tsou, B.K., Ma, M.: Aspect-based opinion polling from customer reviews. IEEE Trans. Affect. Comput. 2(1), 37–49 (2011)CrossRefGoogle Scholar
  11. 11.
    Pronouns chart. Accessed 22 May 2017
  12. 12.
    Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S.J., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: Association for Computational Linguistics (ACL) System Demonstrations, pp. 55–60 (2014)Google Scholar
  13. 13.
    De Marneffe, M.-C., Manning, C.D.: Stanford typed dependencies manual (2008)Google Scholar
  14. 14.
    Opinion lexicon. Accessed 22 May 2017
  15. 15.
    Sentiwordnet sample code. Accessed 22 May 2017
  16. 16.
  17. 17.
    Yelp dataset challenge. Accessed 28 May 2017
  18. 18.
    Apache opennlp developer documentation. Accessed 28 May 2017

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Department of Information and Communication Technology, Manipal Institute of TechnologyManipal UniversityManipalIndia

Personalised recommendations