Recommendation with Subjective Tendency Based on Statistical Implicative Analysis

• Published in: Context-Aware Systems and Applications Vol. 409; pp. 283 - 299
• Main Authors: Huynh, Hiep Xuan, Phan, Cang Anh, Tran, Tu Cam Thi, Nguyen, Hai Thanh
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
• Subjects: Collaborative filtering; Interestingness measures; Similarity measures; Statistical implicative analysis; Subjective tendency
• ISBN: 3030931781; 9783030931780
• ISSN: 1867-8211; 1867-822X
• DOI: 10.1007/978-3-030-93179-7_22

The recommendation systems have been investigating and applying in a vast of fields. The core of systems is the similarity measures and the dissimilarity measures. Many scientists have proposed various similarity measurements in different aspects, including the measures between the users and the users, the measures between the items and the items, the measures between users with the items. However, there are not much studies on the effects of statistical implicative in the recommendation system with subjective tendency. We mainly focus on showing the effects of the subjective tendency against the recommendation system’s model through the prism of statistics implicative. Three specific approaches, including Independence, Dependence, and Equilibrium combined with the fifteen measures of the statistical bias are considered in our work. The experimental results evaluated on the Jester5k dataset compare the similarity measures and the interestingness measures based on the subjective tendency in recommendation systems.