Collaborative and content based filtering personalized recommender system for book / Hossein Arabi

• Main Author: Hossein, Arabi
• Format: Thesis
• Published: 2018
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://studentsrepo.um.edu.my/8978/1/Hossein.pdf; http://studentsrepo.um.edu.my/8978/6/hossein.pdf; http://studentsrepo.um.edu.my/8978/

Personalized recommendation systems provide end users with suggestions about information items, social elements, products or services that are likely to be of their interest based on users' details such as demographics, location, time, and emotion. Incorporating contextual information in recommendation system is an effective approach to create more accurate and personalized recommendations. Therefore, in this study, a Personalized Hybrid Book Recommender is proposed, which integrates several users’ characteristics, namely their personality traits, demographic details and current location, together with review sentiments and purchase reason, to improve their book recommendations. The system is able to determine user’s personality traits by utilizing the Ten Item Personality Inventory. The proposed recommender system would be evaluated using two metrics, that are, Standardized Root Mean Square Residual and Root Mean Square Error of Approximation. The proposed technique was evaluated by comparing it against baseline models and existing personalized recommendation systems. This study is able to show effectiveness of integrating user’s contextual data (personality trait, demographic data and location) with product’s features (review and purchase reason).