Affiliations: [a] Department of Computer Engineering and Interdisciplinary Centre for Artificial Intelligence, Aligarh Muslim University, Aligarh, India
| [b] Department of Computer Science, Aligarh Muslim University, Aligarh, India
| [c] Department of Computer Science, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia
Correspondence:
[*]
Corresponding author. Umar Tahir Kidwai, Department of Computer Engineering and
Interdisciplinary Centre for Artificial Intelligence, Aligarh Muslim
University, Aligarh, 202002, India. E-mail: [email protected].
Abstract: In recent years, the surge in online content has necessitated the development of intelligent recommender systems capable of offering personalized suggestions to users. However, these systems often encapsulate users within a “filter bubble”, limiting their exposure to a narrow range of content. This study introduces a novel approach to address this issue by integrating a novel diversity module into a knowledge graph-based explainable recommender system. Utilizing the Movie Lens 1M dataset, this research pioneers in fostering a more nuanced and transparent user experience, thereby enhancing user trust and broadening the spectrum of recommendations. Looking ahead, we aim to further refine this system by incorporating an explicit feedback loop and leveraging Natural Language Processing (NLP) techniques to provide users with insightful explanations of recommendations, including a comprehensive analysis of filter bubbles. This initiative marks a significant stride towards creating a more inclusive and informed recommendation landscape, promising users not only a wider array of content but also a deeper understanding of the recommendation mechanisms at play.
