Programs
- M. Tech. in Automotive Engineering -
- Fellowship In Interventional Pulmonology and Pulmonary Critical care - Fellowship
Publication Type : Conference Paper
Publisher : 2017 International Conference on Intelligent Sustainable Systems (ICISS)
Source : 2017 International Conference on Intelligent Sustainable Systems (ICISS), IEEE, Palladam, India (2017)
Url : https://ieeexplore.ieee.org/document/8389433
Keywords : Collaboration, Dictionaries, Feature extraction, Recommender systems, Sentiment analysis, Tagging
Campus : Coimbatore
School : School of Engineering
Center : Technology Enabling Centre
Department : Computer Science
Year : 2017
Abstract : A system that recommends an item to a user that he/she is likely to be interested in is said to be a recommender system. Collaborative Filtering(CF) is a technique used to implement recommender systems. CF uses numeric ratings given by users to find the nearest neighbors to the target user and generates recommendations. An upgraded collaborative filtering algorithm that uses credible user-reviews to generate accurate recommendations is proposed in this paper. While in the earlier CF approaches, mere numerical ratings are used for making recommendations, but overall ratings alone cannot properly reflect user's opinion about an item. Another deficiency associated with the existing rating based CF approaches is sparseness in rating database. Data sparsity problem can be got rid of, only if we have an alternate way of filling up the empty ratings. The proposed approach tries to do this by inferring numeric ratings from text reviews. Rating inference involves a sentiment analysis problem of finding the sentiment orientation and strength of opinion words expressed in user-reviews. Some existing recommender systems have already incorporated user-reviews for making better recommendations, but they did not take into account the credibility of those reviews. The proposed CF approach grades the credibility of user-reviews by considering the factors such as reputation of the reviewer and quality of the contents in review. Experimentation of the proposed framework is done and results are validated.
Cite this Research Publication : Dr. Anbazhagan M and Arock, M., “Credible user-review incorporated collaborative filtering for video recommendation system”, in 2017 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, India, 2017.