https://github.com/hilarionengarejr/sentiment-analysis-for-movie-recommendations

This project exhibits how sentiment analysis can be used for product review and recommendations. In this case I am targeting movie reviews and then using content based filtering to recommend similar movies.
https://github.com/hilarionengarejr/sentiment-analysis-for-movie-recommendations

jupyter-notebook nlp nltk pandas python

Last synced: 7 months ago
JSON representation

This project exhibits how sentiment analysis can be used for product review and recommendations. In this case I am targeting movie reviews and then using content based filtering to recommend similar movies.

• Host: GitHub
• URL: https://github.com/hilarionengarejr/sentiment-analysis-for-movie-recommendations
• Owner: HilarioNengareJr
• License: mit
• Created: 2024-05-28T10:29:28.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-26T22:34:58.000Z (11 months ago)
• Last Synced: 2025-02-08T03:41:24.336Z (9 months ago)
• Topics: jupyter-notebook, nlp, nltk, pandas, python
• Language: Jupyter Notebook
• Homepage:
• Size: 225 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# 🎬 Sentiment Analysis for Movie Recommendations 🍿

## 🌟 Introduction 🌟

Welcome! 🖐️ This project is designed to make movie recommendations more personalized and accurate by analyzing user reviews. I use **Sentiment Analysis** to understand the emotional tone of reviews, helping me suggest movies that match your preferences. 🎉

## 🚀 Key Features 🚀

- **Sentiment Analysis and Content Based Filtering**: I employ advanced natural language processing techniques to determine the sentiment (positive, negative, neutral) of user reviews. 🎭

- **Enhanced Recommendations**: My system integrates sentiment data into the recommendation algorithm to tailor movie suggestions to your individual tastes. 🍿

- **Model Training and Customization**: You can train and customize your own sentiment analysis model using my provided datasets and scripts. It's like teaching a computer to understand movies! 🤖

- **Data Visualization**: I provide graphical representations of sentiment analysis results to help you gain insights into user opinions and trends. 📊

This project combines machine learning and natural language processing to create a more nuanced and effective movie recommendation system by understanding and incorporating the emotional tone of user reviews.

## Example Use Case Screenshots

## ROOT PAGE

![Screenshot from 2024-10-04 11-07-59](https://github.com/user-attachments/assets/bc5284a9-b81e-440a-bed4-7e66ba8a6d13)

## NEGATIVE REVIEW AND RESPONSE

### 1

![Screenshot from 2024-10-04 11-09-32](https://github.com/user-attachments/assets/c38266b3-a4ff-4ce2-8baf-fd35202977ef)

### 2

![Screenshot from 2024-10-04 11-09-41](https://github.com/user-attachments/assets/9bdfc0b6-e0d8-493a-986e-2051e1f5042c)

## POSITIVE REVIEW AND RESPONSE

### 1

![image](https://github.com/user-attachments/assets/d667384f-3288-4cb8-b554-8d1eda310f53)

### 2

![image](https://github.com/user-attachments/assets/27763f13-6f1d-47bb-9751-01200b0ae0af)

## SEARCH FUNCTIONALITY

![image](https://github.com/user-attachments/assets/e16a478e-220d-4830-8055-968a855c0aad)

## To Use | Modify

1. Clone repo or fork or whatever.

2. Move into enter-at-own-risk/ directory and create venv.

4. Install requirements.txt and then run.

5. Should be live on port 5000.