Total views : 194

Sentiment Analysis and Prediction using Text Mining

Affiliations

  • Department of Information and Technology, GRIET, Hyderabad - 500090, Telangana, India

Abstract


Objectives: The main aim of the proposed system is to predict the ratings of a textual review using the concept of sentiment analysis. Prediction is an important process to know about the user sentiment. Methods/Statistical Analysis: This work has a sentiment-based rating prediction method (RPS) to upgrade the prediction accuracy in any recommender system. It basically constitutes of a factor used in predicting the rating. Initially, we calculate user’s sentiment on an item/ product based on user sentimental approach. We apply cosine similarity to find user’s sentiment similarity between the users. By taking user’s sentiment similarity into consideration we can fill the missing values and predict the rating for the products that have not been reviewed by the users. Findings: We assess the above two sentimental factors on a sample dataset collected. Eventually the results show that the sentiment distinguishes user preferences which let a helping hand to enhance the performance of the recommender system. The proposed system is executed and the results show 80% accuracy. This work is efficient in terms of the factors used. Application/Improvements: The system can be enhanced with the addition of other factors and fusing them to the recommender system. The use of matrix factorization can, however, be more efficient while using 2 or more factors.

Keywords

Cosine Similarity, Prediction, Reviews, Sentiment Score, User Sentiment

Full Text:

 |  (PDF views: 118)

References


  • Salakhutdinov R, Mnih A. Probabilistic matrix factorization.India: Proceeding in NIPS. 2008; p. 1-8.
  • Jamali M, Ester M. A matrix factorization technique with trust propagation for recommendation in social networks.Barcelona, Spain: Proceedings of 4th ACM conference RecSys’10. 2010; p. 135-42. Crossref.
  • Li F, Liu N, Jin H, Zhao K, Yang Q, Zhu X. Incorporating reviewer and product information for review rating prediction.Proceedings of the 22nd International JointConference on Artificial Intelligence. 2011; p. 1820-5.
  • Yang X, Steck H, Liu Y. Circle-based recommendation in online social networks. Proceedings of 18th ACM SIGKDD International Conference KDD. 2012; p. 1267-75. Crossref.
  • Jiang M, Cui P, Liu R, Yang Q, Wang F, Zhu W, Yang S. Social contextual recommendation. Proceedings of 21stACM International CIKM. 2012; p. 45-54.
  • Fu Z, Sun X, Liu Q. Achieving Efficient Cloud Search Services: Multi-Keyword Ranked Search over Encrypted Cloud Data Supporting Parallel Computing. IEICE Transactions on Communications. 2015; 98(1):190-200.Crossref.
  • Qian X, Feng H, Zhao G, Mei T. Personalized recommendation combining user interest and social circle. IEEE Transactions Knowledge and Data Engineering. 2014; p.1763-77. Crossref.
  • Feng H, Qian X. Recommendation via user’s personality and social contextual. Proceedings of 22nd ACM International Conference on Information and Knowledge Management. 2013; p. 1521-4. Crossref.
  • Ganu G, Elhadad N, Marian A. Beyond the stars: Improving rating predictions using Review text content. Proceeding of 12th International Workshop on the Web and Databases.2009; p. 1-6.
  • Ren Y, Shen J, Wang J, Han J, Lee S. Mutual Verifiable Provable Data Auditing in Public Cloud Storage. Journal of Internet Technology. 2015; 16(2):317-23.
  • Zhang Y, Lai G, Zhang M, Zhang Y, Liu Y, Ma S. Explicit factor models for explainable recommendation based on phraselevel sentiment analysis. Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2014; p. 83-92. Crossref.
  • Lei X, Qian X. Rating prediction via exploring service reputation 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP). 2015; p. 1-6.
  • Qu L, Ifrim G, Weikum G. The bag-of-opinions method for review rating prediction from sparse text patterns.Proceedings of 23rd International Conference on Computational Linguistics. 2010; p. 913-21. PMid: 20473716.
  • Wang B, Min Y, Huang Y, Li X, Wu F. Review rating prediction based on the content and weighting strong social relation of reviewers. Proceedings of the 2013 International Workshop of Mining unstructured big data using natural language processing ACM. 2013; p. 23-30. Crossref.
  • Zhang K, Cheng Y, Liao W, Choudhary A. Mining millions of reviews: a technique to rank products based on importance of reviews. Proceedings of the 13th International Conference on Electronic Commerce. 2011; p. 1-8.
  • Ling G, Lyu RM, King I. Ratings meet reviews, a combined approach to recommend. New York: Proceedings of 8th ACM Conference RecSys’14. 2014; p. 1-8. Crossref.
  • Luo W, Zhuang F, Cheng X, Shi OHZ. Ratable aspects over sentiments: predicting ratings for unrated reviews. IEEE International Conference on Data Mining (ICDM). 2014; p. 380-9. Crossref.
  • Pang B, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques. Proceedings of EMNLP. 2002; p. 79-86.
  • Tang D, Bing Q, Liu T. Learning semantic representations of users and products for document level sentiment classification. Proceedings of 53th Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015; p. 1014-23. Crossref.
  • Nakagawa T, Inui K, Kurohashi S. Dependency tree-based sentiment classification using CRFs with Hidden Variables.2010; p. 786-94.
  • Ma H, Yang H, Lyu MR, King I. SoRec: Social recommendation using probabilistic matrix factorization. Proceedings of 17th ACM CIKM. 2008; p. 931-40.
  • Taboada M, Brooke J, Tofiloski M, Voll K, Stede M. Lexiconbased methods for sentiment analysis. Computational Linguistics. 2011; 37(2):267-307. Crossref.
  • Lu Y, Castellanos M, Dayal U, Zhai C. Automatic construction of a context-aware sentiment lexicon: an optimization approach. World Wide Web Conference Series. 2011; p.347-56. Crossref.
  • Wang H, Lu Y, Zhai C. Latent aspect rating analysis on review text data: a rating regression approach. New York: Proceedings of KDD’10. 2010; p. 783-92. Crossref.
  • Zhang W, Ding G, Chen L, Li C, Zhang C. Generating virtual ratings from Chinese reviews to augment online recommendations. ACM TIST. 2013; 4(1):1-17. Crossref, Crossref, Crossref.
  • Lee K. Using dynamically promoted experts for music recommendation.IEEE Transactions on Multimedia. 2014;16(5):1201-10. Crossref
  • Blei DM, Ng AY, Jordan MI. Latent Dirichlet Allocation. Journal of machine learning research 3. 2003; p. 993-1022.
  • Jiang S, Qian X, Shen J, Fu Y, Mei T. Author topic model based collaborative filtering for personalized POI recommendation. IEEE Transactions Multimedia. 2015; 17(6):907-18. Crossref.
  • Suresh V, Veilumuthu A, Krishnamurthy A. A Nonsyntactic approach for text sentiment classification with stop words. Proceeding of ACM WWW. 2011; p. 137-8.
  • Zhang W, Ding G, Chen L, Li C, Zhang C. Generating virtual ratings from Chinese reviews to augment online recommendations. ACM TIST. 2013; 4(1):1-17. Crossref, Crossref, Crossref.
  • Xiong W, Jin Y, Liu Z. Chinese sentiment analysis using appraiser-degree-negation combinations and PSO. Journal of Computers. 2014; 9(6):1-8. Crossref.
  • Nie H, Rong Z. Review helpfulness prediction research based on review sentiment feature sets. New Technology of Library and Information Service. 2015; 31(7):113-21.
  • Kanayama H, Nasukawa T. Fully automatic lexicon expansion for domain-oriented sentiment analysis. Proceedings of EMNLP’06. 2006; p. 355-63.
  • Ding X, Liu B, Yu PS. A holistic lexicon-based approach to opinion mining. Proceedings of WSDM ‘08. 2008; p. 23140.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.