Video Content Recommendation System

DOI

10.2991/978-94-6463-858-5_239How to use a DOI?

Keywords

Content-based filtering; video recommendation; machine learning; text vectorization; Bag of words; cosine similarity

Abstract

Every day, video streaming services produce enormous volumes of information, making it difficult for consumers to locate videos that are relevant to their interests. By offering personalized material based on viewing history, preferences, and metadata, recommendation engines improve the user experience. The ability to provide tailored recommendations without depending on user interaction data makes content-based filtering stand out among other strategies. In order to recommend pertinent videos, this study offers a content-based recommendation system that makes use of textual metadata, such as titles, descriptions, and tags. The system converts textual data into numerical form by using the BoW technique for text vectorization. Accurate suggestions are then ensured by measuring the proximity of video representations using cosine similarity.Important measures including precision, recall, and F1-score are examined to evaluate the efficiency of the system. Results from experiments show how well the model works to increase user engagement, decrease manual search efforts, and recommend pertinent material. Our content-based filtering method is appropriate for video streaming services since it provides scalable, personalised suggestions without requiring a large amount of collaborative data. (79.5% MAP, 84.0% F1-score, 82.7% recall, and 85.4% precision).

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - K. Archana
AU  - K. Sindhu Priya
AU  - L. Jagath Simha Reddy
AU  - M. Vikesh Reddy
PY  - 2025
DA  - 2025/11/04
TI  - Video Content Recommendation System
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 2843
EP  - 2853
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_239
DO  - 10.2991/978-94-6463-858-5_239
ID  - Archana2025
ER  -