Scholarlink

This paper presents a content-based movie recommendation system leveraging natural language processing techniques on the TMDB 5000 dataset. The frontend was developed using Streamlit for real-time user interaction, while the backend methodology was implemented in Python via Jupyter Notebook. The system integrates feature extraction, text preprocessing, and cosine similarity to recommend similar movies based on user input. Additionally, the application includes a wishlist feature and search history tracking to enhance user experience. Results and visual demonstrations are presented within the Streamlit application, showcasing its effectiveness in generating relevant recommendations. This work aims to simplify recommendation pipelines by combining intuitive frontends with robust natural language models.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Hybrid Approach to Movie Recommendation Using Content-Based and Collaborative Filtering

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ajay Talele,
  • Saundarya Nair,
  • Isha Sahasrabuddhe,
  • Praneel Jain,
  • Kshitij Sahane,
  • Sarthak Salunkhe,
  • Pranav Pendse,
  • Ishan Ranadive,
  • Sanskar Vilas,
  • Sanyam Kothari

摘要

This paper presents a content-based movie recommendation system leveraging natural language processing techniques on the TMDB 5000 dataset. The frontend was developed using Streamlit for real-time user interaction, while the backend methodology was implemented in Python via Jupyter Notebook. The system integrates feature extraction, text preprocessing, and cosine similarity to recommend similar movies based on user input. Additionally, the application includes a wishlist feature and search history tracking to enhance user experience. Results and visual demonstrations are presented within the Streamlit application, showcasing its effectiveness in generating relevant recommendations. This work aims to simplify recommendation pipelines by combining intuitive frontends with robust natural language models.