论文信息 - Preference Based Recommendation System for Apparel E-Commerce Sites

Preference Based Recommendation System for Apparel E-Commerce Sites

Preference Based Recommendation System for Apparel E-Commerce Sites is a new approach for e-commerce sites to come up with more accurate and personalized recommendation. The proposed system will use the reviews that given by users as the base of the system, by using natural language processing methods it will calculate the sentiment score, attributes more concerned and their corresponding values of each items. The outcome of the text mining will be used as input to the recommendation process. The recommendation approach is combination of both collaborative and content based methods. With considering user reviews the module will develop item feature and user preference matrixes from that ratings will be predicted by using Term Frequency-Document Inverse Frequency model.

[1] Thiago R.L.C. Paixão,et al. Information Extraction Techniques in Chemical Sensing , 2017 .

[2] Kuo Zhao,et al. Personalized recommendation algorithm based on preference features , 2014, Tsinghua Science and Technology.

[3] Li Chen,et al. A user-centric evaluation framework for recommender systems , 2011, RecSys '11.

[4] Mehran Sahami,et al. Evaluating similarity measures: a large-scale study in the orkut social network , 2005, KDD '05.

[5] Krys J. Kochut,et al. A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques , 2017, ArXiv.

[6] Muhammad Kashif Hanif,et al. Text Mining: Techniques, Applications and Issues , 2016 .

[7] Li Chen,et al. Recommender systems based on user reviews: the state of the art , 2015, User Modeling and User-Adapted Interaction.

[8] Xavier Amatriain,et al. Data Mining Methods for Recommender Systems , 2011, Recommender Systems Handbook.

[9] F. O. Isinkaye,et al. Recommendation systems: Principles, methods and evaluation , 2015 .