MovieMetrix

  • Unique Paper ID: 168198
  • Volume: 11
  • Issue: 5
  • PageNo: 2557-2561
  • Abstract:
  • In today's digital age, the overwhelming abundance of available movies makes it increasingly challenging for users to find content that matches their preferences and moods, creating a demand for effective recommendation systems. "MovieMetrix" addresses this need by offering a sophisticated movie recommendation system developed using Streamlit, which utilizes advanced natural language processing techniques to deliver personalized and mood-based movie suggestions. Leveraging TF-IDF Vectorizer for text similarity and TextBlob for sentiment analysis, the application processes a comprehensive movie dataset through tokenization, stopword removal, and lemmatization using NLTK. Our system features personalized recommendations based on user input and mood-based recommendations identified through sentiment analysis, supported by a predefined mood-to-genre mapping. Additionally, MovieMetrix includes filtering options by director, actor, or genre to enhance the user discovery experience. The results demonstrate that MovieMetrix effectively tailors recommendations to user inputs and moods, providing a user-centric solution for movie discovery and highlighting its potential applications and future improvements in personalized entertainment recommendations.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 5
  • PageNo: 2557-2561

MovieMetrix

Related Articles