🎮 Steam Game Review Analysis Using NLP and Clustering

Welcome to the Steam Game Review Analysis project! This repository showcases a detailed approach to analyzing user reviews from top-selling games on the Steam platform. By leveraging Natural Language Processing (NLP) and Machine Learning techniques, we aim to uncover valuable insights from user feedback.

🚀 Project Overview

In this project, we focus on several key objectives:

1. Bug Detection: We implement keyword filtering to identify reviews that mention bugs or issues within games. This helps developers understand user concerns and prioritize fixes.

2. Sentiment Analysis: We assess user sentiment, categorizing reviews as positive, neutral, or negative. This analysis provides a clear picture of user satisfaction.

3. Clustering Similar Games: Using clustering methods, we group similar games based on user reviews. This allows for easier comparisons and recommendations.

🛠️ Technologies Used

• Natural Language Processing (NLP): To process and analyze text data.
• Machine Learning: For sentiment analysis and clustering algorithms.
• Python: The primary programming language used in this project.
• Streamlit: For creating an interactive dashboard to visualize results.
• Data Analytics: To derive insights from user reviews.

📂 Repository Structure

Steam-Game-Review-Analysis-Using-NLP-and-Clustering/
│
├── data/
│   ├── raw/
│   ├── processed/
│
├── notebooks/
│   ├── analysis_notebook.ipynb
│   ├── clustering_notebook.ipynb
│
├── src/
│   ├── bug_detection.py
│   ├── sentiment_analysis.py
│   ├── clustering.py
│
├── app/
│   ├── streamlit_app.py
│
├── requirements.txt
└── README.md

📁 Data Folder

• raw/: Contains the original datasets of user reviews.
• processed/: Includes cleaned and processed data for analysis.

📁 Notebooks Folder

• analysis_notebook.ipynb: Exploratory data analysis and visualization.
• clustering_notebook.ipynb: Detailed analysis of clustering methods used.

📁 Source Folder

• bug_detection.py: Script for detecting bug-related reviews.
• sentiment_analysis.py: Script for performing sentiment analysis.
• clustering.py: Script for clustering similar games.

📁 App Folder

• streamlit_app.py: Main application file for the Streamlit dashboard.

📄 requirements.txt

This file lists all the dependencies required to run the project.

📈 Getting Started

To get started with this project, follow these steps:

1. Clone the Repository:

   git clone https://github.com/caiohutis/Steam-Game-Review-Analysis-Using-NLP-and-Clustering.git
   cd Steam-Game-Review-Analysis-Using-NLP-and-Clustering

2. Install Dependencies: Use the following command to install the required libraries:

   pip install -r requirements.txt

3. Run the Streamlit App: Launch the Streamlit dashboard to visualize the analysis:

   streamlit run app/streamlit_app.py

📊 Features

• Interactive Dashboard: Explore the results through an easy-to-use interface.
• Keyword Filtering: Quickly identify bug-related reviews.
• Sentiment Insights: Understand how users feel about different games.
• Game Clustering: Discover similar games based on user feedback.

📝 How to Contribute

We welcome contributions! To contribute to this project, follow these steps:

1. Fork the Repository: Click the "Fork" button on the top right corner of the repository page.

2. Create a New Branch:

   git checkout -b feature/your-feature-name

3. Make Changes: Implement your feature or fix a bug.

4. Commit Your Changes:

   git commit -m "Add your message here"

5. Push to Your Branch:

   git push origin feature/your-feature-name

6. Open a Pull Request: Go to the original repository and click on "New Pull Request."

📥 Releases

For the latest updates and versions of the project, visit the Releases section. Here, you can download the latest files and execute them in your local environment.

🌐 Topics

This project covers a range of topics, including:

• Bug Detection: Identifying issues from user feedback.
• Clustering: Grouping similar games based on reviews.
• Data Analytics: Analyzing and interpreting user data.
• Game Analytics: Understanding trends in gaming feedback.
• Machine Learning: Applying ML techniques to analyze data.
• Natural Language Processing (NLP): Processing text data for insights.
• Sentiment Analysis: Evaluating user sentiment from reviews.
• Streamlit: Building interactive web applications.
• Text Mining: Extracting useful information from text data.

🎨 Visualizations

The project includes various visualizations to help understand the data better. Some examples are:

• Sentiment Distribution: A pie chart showing the proportion of positive, neutral, and negative reviews.
• Bug Mentions Over Time: A line graph illustrating the trend of bug-related mentions in reviews over time.
• Game Clusters: A scatter plot showing how games are grouped based on user reviews.

🤝 Acknowledgments

We would like to thank the contributors of various libraries and tools that made this project possible. Special thanks to the developers of Streamlit for providing a robust platform for building interactive applications.

📞 Contact

For any questions or feedback, feel free to reach out:

• Email: your-email@example.com
• Twitter: @your_twitter_handle

🔗 License

This project is licensed under the MIT License. See the LICENSE file for more information.

---

Thank you for checking out the Steam Game Review Analysis project! We hope you find it useful and insightful. Don't forget to check the Releases section for the latest updates!