Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Robert Chun
Second Advisor
Saptarshi Sengupta
Third Advisor
Rafiq Shaikh
Keywords
recommendation systems, collaborative filtering, psychology, personality detection, user behaviour.
Abstract
Recommendation systems are an integral part of any business, and a crucial factor in determining their success as these systems help businesses in marketing their products to the right kind of audience. Conventional methods of building recommendation systems such as collaborative filtering and content-based recommendation, although effective, suffer from limitations such as cold start and the data sparsity problems. Moreover, these methods aim at finding similar products as user’s past interactions rather than personalizing the recommendations. The upsurge in use of social media, over-the-top content (OTT), and e-commerce platforms has made the task of personalizing recommendations imperative, leading to the advancement of an area of research called psychology aware recommendation systems. This report first surveys the various ways in which these new types of systems incorporate concepts of psychology while making recommendations. Then, a new way of incorporating personality information is proposed that centers around user behavior on a particular platform. People’s personality traits are known to influence their behavior, hence a user’s behavior on social media can be a good indicator of their personality. Users showing similar behavior can be deemed to prefer similar content. Experimental results show that by identifying the right behavioural information to include in recommendations, a performance gain of up to 50% can be achieved compared to existing baseline systems.
Recommended Citation
Shaikh, Uzma Zubair, "Implicit Personality Detection from User Behaviour in Recommendation Systems" (2024). Master's Projects. 1437.
https://scholarworks.sjsu.edu/etd_projects/1437
