International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 06 | Jun 2025
p-ISSN: 2395-0072
www.irjet.net
Movie Recommendation Using TF-IDF Vectorization and Cosine Similarity Raviraj Wandhekar1, Keshav Nandane2, Dr. Meenakshi Garg3 1Dept of Master of Computer Applications, VES’s Institute of Technology, Chembur- 400074 2Dept of Master of Computer Applications, VES’s Institute of Technology, Chembur- 400074
3Assistant Professor, Dept of Master of Computer Applications, VES’s Institute of Technology, Chembur- 400074
---------------------------------------------------------------------***--------------------------------------------------------------------this project, I focused on building a content-based Abstract recommendation system. This method uses the actual features of a movie—like its plot, genre, or cast—to find similar titles. By converting movie descriptions into numerical vectors using TF-IDF and then measuring the similarity between them with cosine similarity, we can recommend films that are thematically close. This system is particularly useful when we don’t have any user history to work with.
In today’s digital age, recommendation systems significantly enhance user experience by delivering personalized content. This research presents a contentbased movierecommendation system that leverages cosine similarity to suggest relevant films based on movie descriptions and metadata. The system performs data preprocessing, vectorizes textual content using the Term Frequency-Inverse Document Frequency (TF-IDF) method, and calculates similarity scores to rank recommendations.
2. LITERATURE REVIEW Researchers have proposed different techniques for movie recommendations over the years. The most popular ones include collaborative filtering, contentbased filtering, and hybrid systems that combine both.[1] Collaborative filtering, while effective, has known issues like the cold-start problem—it needs a lot of user interaction data to work well.[2] Content-based filtering is a practical alternative. It looks at item features to make suggestions. For example, Lops et al. (2011) emphasized how useful text analysis
Developed using Python libraries such as Pandas, NumPy, and Scikit-learn, the system features an interactive interface created with Streamlit. Unlike collaborative filtering, which depends on user behavior and suffers from cold-start issues, the content-based approach offers consistent results without requiring prior user data. While deep learning models provide improved accuracy, they demand high computational resources and large datasets, which may not be feasible in many real-world applications. Experimental results, presented through tables, graphs, and Venn diagrams, validate the system’s effectiveness. The paper also discusses limitations in tracking evolving user preferences and proposes future enhancements using hybrid models and transformer-based NLP techniques to improve recommendation accuracy.
techniques like TF-IDF and word embeddings are in these systems.[3] Musto et al. (2017) found that combining deep learning with content-based filtering improved accuracy.[4] Other studies, like the one by Zhang et al. (2020), showed that cosine similarity works better than other methods such as Jaccard or Euclidean distance, especially when dealing with highdimensional text data.[5] This paper builds on these studies by using TF-IDF and cosine similarity to recommend movies based on their descriptions.[6]
Key-Words: A Cosine Similarity, Scikit Learn, Movie Recommendation, NLP, Collaborative Filtering, Contentbased, TF-IDF, Hybrid Models, Deep learning, Neural Network
3. PROPOSED FRAMEWORK
1. INTRODUCTION
Workflow Overview: The system follows a clear process:
With so many movies available online, finding something worth watching can be overwhelming. That's where movie recommendation systems come in—they help users discover films that match their preferences. Traditionally, systems like collaborative filtering have been used, which rely on user behavior and ratings. But these systems often struggle when there’s little or no user data, especially for new users or new movies. In
© 2025, IRJET
|
Impact Factor value: 8.315
|
●
Data Collection: Collect movie information such as descriptions, genres, and cast.
●
Preprocessing: Clean the data by removing unnecessary elements like stopwords and special characters.
ISO 9001:2008 Certified Journal
|
Page 1113