An Approach to Utilize E-commerce Product Reviews to Remove Irrelevant Recommendations

Information explosion in the digital era has affected e-commerce users' purchase experience as the users encounter a large number of choices for the item of interest. A recommender system enriches the customers' shopping experience by downsizing the number of alternatives suggested to the user. It suggests the right items to the right customers at the right time, thus, benefiting both the customer and the stakeholders involved. User reviews are a first-hand account of a user's encounter with an item and consist of positive, negative, and neutral feedback. Users' opinion for item(s) of interest can be gauged through this textual feedback. Through this paper, an approach to improve the recommendations has been provided by leveraging the product review functionality. Extracting the product features from user-provided feedback and not recommending products with uninteresting product features to improve the recommendation list is the main idea behind this approach.

[1]  P. Gulati,et al.  COVID-19 pandemic lockdown: An emotional health perspective of Indians on Twitter , 2020, The International journal of social psychiatry.

[2]  Parul Gupta,et al.  A new approach to identify similar users based on customer reviews , 2020, IOP Conference Series: Materials Science and Engineering.

[3]  Payal Gulati,et al.  Implementation and comparison of topic modeling techniques based on user reviews in e-commerce recommendations , 2020, Journal of Ambient Intelligence and Humanized Computing.

[4]  Shuxiang Xu,et al.  An empirical research on sentiment analysis using machine learning approaches , 2019, International Journal of Computers and Applications.

[5]  Kweku-Muata Osei-Bryson,et al.  RecSys Issues Ontology: A Knowledge Classification of Issues for Recommender Systems Researchers , 2019, Information Systems Frontiers.

[6]  Chih-Ya Shen,et al.  A Consumer Review-Driven Recommender Service for Web E-Commerce , 2017, 2017 IEEE 10th Conference on Service-Oriented Computing and Applications (SOCA).

[7]  Palak Desai,et al.  Methods of recommender system: A review , 2017, 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS).

[8]  John K. Debenham,et al.  Recommender System Based on Consumer Product Reviews , 2006, 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06).

[9]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[10]  Dongwon Lee,et al.  $l$ -Injection: Toward Effective Collaborative Filtering Using Uninteresting Items , 2019, IEEE Transactions on Knowledge and Data Engineering.

[11]  Iraklis Varlamis,et al.  Recommender Systems for Large-Scale Social Networks: A review of challenges and solutions , 2018, Future Gener. Comput. Syst..

[12]  Ajeet Kumar Pandey,et al.  Topic Model Based Opinion Mining and Sentiment Analysis , 2018, 2018 International Conference on Computer Communication and Informatics (ICCCI).

[13]  George A. Sielis,et al.  Recommender Systems Review of Types, Techniques, and Applications , 2015 .

[14]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .