https://github.com/hafidaso/tv-shows-dataset-analysis-project

This project involves comprehensive data analysis and application development using a dataset of approximately 160K TV shows.
https://github.com/hafidaso/tv-shows-dataset-analysis-project

ntlk python tv-shows

Last synced: about 2 months ago
JSON representation

This project involves comprehensive data analysis and application development using a dataset of approximately 160K TV shows.

• Host: GitHub
• URL: https://github.com/hafidaso/tv-shows-dataset-analysis-project
• Owner: hafidaso
• License: other
• Created: 2024-01-26T18:10:55.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-01-26T18:20:51.000Z (11 months ago)
• Last Synced: 2024-01-26T19:28:51.301Z (11 months ago)
• Topics: ntlk, python, tv-shows
• Language: Jupyter Notebook
• Homepage:
• Size: 11.2 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# TV Shows Dataset Analysis Project

## Project Overview

This project involves comprehensive data analysis and application development using a dataset of approximately 160K TV shows. The analyses aim to uncover trends in TV show popularity, predict show success, develop a recommendation system, and more.

## Objectives

- Explore trends in TV show popularity.

- Predict the success of TV shows based on features like vote count, average, and popularity.

- Build a recommendation system based on user's favorite genres or languages.

- Investigate TV show production trends across countries and networks.

- Analyze overviews of TV shows for sentiment and themes.

## Data Sources

- TV Shows Dataset: A collection of data about 160K TV shows, including details like air dates, genres, languages, production companies, and voting data.

## Analyses and Models

1. **Language Analysis of TV Show Overviews**: Using NLP techniques to identify prevalent themes and sentiments in TV show descriptions.

2. **Success Prediction Model**: A machine learning model predicting a TV show's success based on popularity, vote count, and average rating.

3. **Recommendation System**: A system suggesting TV shows based on user preferences in genres and languages.

4. **Production Trends Analysis**: Analyzing production trends to identify the most active countries and networks in TV show production.

## Technologies Used

- Python for data analysis and machine learning.

- Libraries: pandas, sklearn, NLTK/spaCy (for NLP).

- Jupyter Notebook for interactive development and analysis.

## Key Insights

- Diverse themes and sentiments in TV show overviews.

- High potential for predicting show success using popularity metrics.

- Effective genre-based recommendations, with scope for enhanced personalization.

- Dominance of specific countries and networks in TV show production.

## Author Information

### [Hafida Belayd](https://www.linkedin.com/in/hafida-belayd/)

## License

### [LICENSE](LICENSE)