An Enhanced Content-based Filtering Using Maximal Marginal Relevance

  • Samantha Gwyn M. Aranzamendez Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines
  • Joshua Caleb D. Bolito Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines
  • Aron Christoper R. Rafe Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines
  • Jamillah S. Guialil Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines
  • Dan Michael A. Cortez Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines
  • Raymund M. Dioses Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Abstract

Purpose – The study aims to enhance Content-based Filtering by diversifying its recommended items to combat overspecialization. It traditionally recommends items that are directly related to the user profile, preventing users from discovering newer sets of items.

Method – Maximal Marginal Relevance is integrated into the algorithm – a re-ranking algorithm, developed by Carbonell and Goldstein that enhances the diversity of items retrieved by information retrieval systems – to enhance Content-based Filtering and address the underlying overspecialization problem.

Results – By integrating Maximal Marginal Relevance, the modified algorithm addressed overspecialization. Out of all the tested values of lambda (λ) for MMR, the enhanced Content-based Filtering (CBF-MMR) with λ = 0.7 showed the most prominence, having a good balance between relevance and diversity of recommendations. On average, it improved upon the original algorithm by 48.51% in Precision, 6.40% in Recall, 28.12% in F-Score, and 275.45% in Diversity.

ConclusionResults show that integrating Maximal Marginal Relevance to Content-based Filtering (CBF-MMR) improves the diversity of recommendations. Due to the re-ranking process added by the Maximal Marginal Relevance, the average Precision, Recall, and F-Score also improved.

Recommendations – The authors of this study suggest further work on Content-based Filtering with faster re-ranking algorithms, application of the enhanced algorithm to other larger datasets such as GroupLens’ MovieLens 10M dataset, application of the enhanced algorithm to a different domain, and enhancement of the Maximal Marginal Relevance algorithm to be applied in Content-based Filtering.

Research Implications – The successful integration of Maximal Marginal Relevance (MMR) in a Content-based Filtering algorithm opens new possibilities for enhancing the diversity and relevance of recommendations of various types of recommender systems.

Practical Implications – Beyond the movie recommender system this study was applied to, this study has profound practical implications on other domains that utilize recommender systems including but not limited to the domains of entertainment, e-commerce, and information retrieval platforms.

Author Biographies

Samantha Gwyn M. Aranzamendez, Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Samantha Gwyn Aranzamendez is a dedicated Computer Science major from Pamantasan ng Lungsod ng Maynila. She has a passionate interest in system analytics, SEO optimization, WordPress development, and software quality assurance. With a sharpened eye for innovation and a drive for continuous learning, she is ready to make major contributions to the constantly evolving scene of technology.

Joshua Caleb D. Bolito, Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Joshua Caleb D. Bolito is a graduating computer science student of Pamantasan ng Lungsod ng Maynila, where he is pursuing a bachelor’s degree. Joshua is set to graduate in September 2024 with Magna Cum Laude honors As a skilled Software Developer, Joshua has honed his expertise in Frontend Development, specializing in the use of cutting-edge technologies such as React and Next.js.

Aron Christoper R. Rafe, Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Aron Christoper Rafe, is a fourth-year student pursuing a bachelor's degree in computer science at Pamantasan ng Lungsod ng Maynila. He's passionate about creating software solutions to benefit the community. He continually hones his soft and technical skills in his free time. He aspires to become an Android developer. Upon graduation, he looks forward to applying his growing skills and knowledge in mobile technology to be able to contribute to the community as an Android Developer.

Jamillah S. Guialil, Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Jamillah Guialil earned her Bachelor of Science in Computer Studies with a major in Computer Science (BSCS-CS) in 2018. Currently, she is pursuing her Master of Information Technology (MIT) degree at Pamantasan ng Lungsod ng Maynila. In addition to her studies, Jamillah is working as a part-time faculty member at the College of Information Systems and Technology Management (CISTM) within Pamantasan ng Lungsod ng Maynila.

Dan Michael A. Cortez, Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Dr. Dan Michael A. Cortez is the Vice President for Research, Academic, and Extension Services at Pamantasan ng Lungsod ng Maynila, with 10 years of teaching experience. He holds a Bachelor of Science in Information Technology and a Master of Science in Information and Communications Technology from the same university. He earned his Doctorate in Information Technology from the Technological Institute of the Philippines-Quezon City Campus. Dr. Cortez is a member of PSITE-NCR and the Computing Society of the Philippines, with research interests focused on cryptography and Data Mining, having authored multiple books and published research both locally and internationally.

Raymund M. Dioses, Computer Science Department, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines

Raymund M. Dioses is currently an Assistant Professor I at Pamantasan ng Lungsod ng Maynila, where he also chairs the Computer Science Department. He previously worked at CORE Gateway College Inc. for 8 years as a College Faculty and Chairperson of the Computer Education Department, and 5 years as a Teacher II at the Department of Education. He holds a Bachelor of Science in Computer Science from St. Jude College and a Master of Arts in Education majoring in Educational Management from CORE Gateway College. He is currently pursuing a Master of Information Technology majoring in Computer Education at Nueva Ecija University of Science and Technology.

Published
2024-08-09
How to Cite
ARANZAMENDEZ, Samantha Gwyn M. et al. An Enhanced Content-based Filtering Using Maximal Marginal Relevance. International Journal of Computing Sciences Research, [S.l.], v. 8, p. 3070-3087, aug. 2024. ISSN 2546-115X. Available at: <//stepacademic.net/ijcsr/article/view/595>. Date accessed: 12 dec. 2024.
Section
Articles