ABSTRACT
In recommender systems, an item is recommended to a new user by analyzing purchase history of existing users along with the items’ information. In this area, collaborative filtering is a popular approach to predict user’s preferences from the existing users’ preferences. The user’s preferences are identified from the user rating and/or review data. It is observed in the real-world data that user is not expressing the same feelings in user rating and review text. As a result, the accuracy of the recommender system is affected. In this paper, we address this inconsistency and propose an approach called Emotion-Specific Prediction to refine the user ratings by applying proposed emotion detection algorithm on review text. The emotion detection algorithm extracts the user feelings as emotional features by exploiting the multi-polarity from review text. The proposed approach transforms these features into refined ratings and are used to predict the user ratings using collaborative filtering. The experimental evaluations conducted on real-world Amazon and Yelp data sets, and results show that the proposed approach reduces root mean square error (RMSE) and Normalized RMSE (NRMSE) significantly.
- Silvana Aciar, Debbie Zhang, Simeon Simoff, and John Debenham. 2007. Informed recommender: Basing recommendations on consumer product reviews. IEEE Intelligent systems 22, 3 (2007), 39–47. Google ScholarDigital Library
- Markos Aivazoglou, Antonios O Roussos, Dionisis Margaris, Costas Vassilakis, Sotiris Ioannidis, Jason Polakis, and Dimitris Spiliotopoulos. 2020. A fine-grained social network recommender system. Social Network Analysis and Mining 10, 1 (2020), 8.Google ScholarCross Ref
- Amarajyothi Aramanda, Saifullah Md Abdul, and Radha Vedala. 2020. A Comparison Analysis of Collaborative Filtering Techniques for Recommeder Systems. In Proc. of Int. Conf. on Comm. and Cyber-Physical Engineering. Springer, 87–95.Google Scholar
- Robert M Bell and Yehuda Koren. 2007. Scalable Collaborative Filtering with Jointly Derived Neighborhood Interpolation Weights. In ICDM, Vol. 7. ACM, 43–52. Google ScholarDigital Library
- Jesús Bobadilla, Fernando Ortega, Antonio Hernando, and Abraham Gutiérrez. 2013. Recommender systems survey. Knowledge-based systems 46 (2013), 109–132. Google ScholarDigital Library
- Rajesh Bose, Raktim Kumar Dey, Sandip Roy, and Debabrata Sarddar. 2020. Sentiment Analysis on Online Product Reviews. In Proc. of Info. and Comm. Tech. for Sustainable Development. Springer, 559–569.Google Scholar
- Zhenpeng Chen, Yanbin Cao, Huihan Yao, Xuan Lu, Xin Peng, Hong Mei, and Xuanzhe Liu. 2021. Emoji-powered sentiment and emotion detection from software developers’ communication data. ACM Transactions on Software Engineering and Methodology 30, 2(2021), 1–48. Google ScholarDigital Library
- Keith Cortis, André Freitas, Tobias Daudert, Manuela Huerlimann, Manel Zarrouk, Siegfried Handschuh, and Brian Davis. 2017. Semeval-2017 task 5: Fine-grained sentiment analysis on financial microblogs and news. ACL.Google Scholar
- Lorenzo Gatti, Marco Guerini, and Marco Turchi. 2013. Sentiwords. Retrieved July 19, 2020 from https://hlt-nlp.fbk.eu/technologies/sentiwordsGoogle Scholar
- Lorenzo Gatti, Marco Guerini, and Marco Turchi. 2015. SentiWords: Deriving a high precision and high coverage lexicon for sentiment analysis. IEEE Transactions on Affective Computing 7, 4 (2015), 409–421. Google ScholarDigital Library
- Yelp Group. 2013. Yelp Recruiting Competition. Retrieved November 27, 2020 from https://www.kaggle.com/c/yelp-recruiting/dataGoogle Scholar
- Daniel Kluver, Michael D Ekstrand, and Joseph A Konstan. 2018. Rating-based collaborative filtering: algorithms and evaluation. In Social Inf. Access. Springer, 344–390.Google Scholar
- Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37. Google ScholarDigital Library
- Ralf Krestel, Peter Fankhauser, and Wolfgang Nejdl. 2009. Latent dirichlet allocation for tag recommendation. In Proc. of the third ACM Conf. on Recommender Systems. 61–68. Google ScholarDigital Library
- Mittapally KumaraSwamy and P. Krishna Reddy. 2015. Improving Diversity Performance of Association Rule Based Recommender Systems. In Proc. of Int. Conf. on Database and Expert Systems Applications. Springer, 499–508. Google ScholarDigital Library
- Mittapally KumaraSwamy and P. Krishna Reddy. 2020. A model of concept hierarchy-based diverse patterns with applications to recommender system. International Journal of Data Science and Analytics 10, 2 (2020), 177–191.Google ScholarCross Ref
- Bing Liu. 2020. Sentiment analysis: Mining opinions, sentiments, and emotions. Cambridge university press.Google Scholar
- Julian McAuley. 2014. Amazon product data. Retrieved November 28, 2019 from http://jmcauley.ucsd.edu/data/amazon/Google Scholar
- Andriy Mnih and Russ R Salakhutdinov. 2008. Probabilistic matrix factorization. In Proc. of Advances in neural information processing systems. 1257–1264. Google ScholarDigital Library
- Saif M. Mohammad. 2016. The Sentiment and Emotion Lexicons. Retrieved July 19, 2020 from http://sentiment.nrc.ca/lexicons-for-researchGoogle Scholar
- Kaitlyn Mulcrone. 2012. Detecting Emotion in Text. In UMM CSci Senior Seminor Conf.Google Scholar
- Cataldo Musto, Marco de Gemmis, Giovanni Semeraro, and Pasquale Lops. 2017. A multi-criteria recommender system exploiting aspect-based sentiment analysis of users’ reviews. In Proc. of Eleventh Conf. on Recommender Systems. ACM, 321–325. Google ScholarDigital Library
- Maria Pontiki, Dimitrios Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad Al-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, 2016. Semeval-2016 task 5: Aspect based sentiment analysis. In Int. workshop on semantic evaluation. 19–30.Google ScholarCross Ref
- Paul Resnick, Neophytos Iacovou, Mitesh Suchak, Peter Bergstrom, and John Riedl. 1994. Grouplens: An open architecture for collaborative filtering of netnews. In Proc. of the 1994 ACM Conf. on Computer supported cooperative work. 175–186. Google ScholarDigital Library
- J Sangeetha and V Sinthu Janita Prakash. 2018. Improved Feature-Specific Collaborative Filtering Model for the Aspect-Opinion Based Product Recommendation. In Proc. of Advances in Big Data and Cloud Computing. Springer, 275–289.Google Scholar
- Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2000. Analysis of recommendation algorithms for e-commerce. In Proc. of the 2nd ACM Conf. on EC. ACM, 158–167. Google ScholarDigital Library
- Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2001. Item-based collaborative filtering recommendation algorithms. In Proc. of the 10th Int. Conf, WWW. ACM, 285–295. Google ScholarDigital Library
- Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2002. Incremental singular value decomposition algorithms for highly scalable recommender systems. In Proc. of Fifth Int. Conf. on computer and information science. 27–32.Google Scholar
- Badrul M Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2002. Recommender systems for large-scale e-commerce: Scalable neighborhood formation using clustering. In Proc. of the fifth Int. Conf. on computer and Inf. Technol., Vol. 1. ACM, 291–324.Google Scholar
- Rong-Ping Shen, Heng-Ru Zhang, Hong Yu, and Fan Min. 2019. Sentiment based matrix factorization with reliability for recommendation. Expert Systems with Applications 135 (2019), 249–258.Google ScholarDigital Library
- Shuo Wang, Aishan Maoliniyazi, Xinle Wu, and Xiaofeng Meng. 2020. Emo2Vec: Learning emotional embeddings via multi-emotion category. ACM Transactions on Internet Technology 20, 2 (2020), 1–17. Google ScholarDigital Library
- Jiyao Wei, Jian Liao, Zhenfei Yang, Suge Wang, and Qiang Zhao. 2020. BiLSTM with multi-polarity orthogonal attention for implicit sentiment analysis. Neurocomputing 383(2020), 165–173.Google ScholarDigital Library
Index Terms
- Refining User Ratings Using User Emotions for Recommender Systems
Recommendations
Acquiring User Information Needs for Recommender Systems
WI-IAT '13: Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 03Most recommender systems attempt to use collaborative filtering, content-based filtering or hybrid approach to recommend items to new users. Collaborative filtering recommends items to new users based on their similar neighbours, and content-based ...
User Personality and User Satisfaction with Recommender Systems
In this study, we show that individual users' preferences for the level of diversity, popularity, and serendipity in recommendation lists cannot be inferred from their ratings alone. We demonstrate that we can extract strong signals about individual ...
Cross-representation mediation of user models
Personalization is considered a powerful methodology for improving the effectiveness of information search and decision making. It has led to the dissemination of systems capable of suggesting relevant and personalized information (or items) to the users,...
Comments