Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/chanmeng666/customer-insight

A Python-based customer review analysis system with sentiment analysis, topic modeling, and interactive visualization capabilities, optimized for Chinese language reviews.
https://github.com/chanmeng666/customer-insight

chinese-nlp customer-insights data-visualization review-analysis sentiment-analysis streamlit text-analysis topic-modeling

Last synced: 8 days ago
JSON representation

A Python-based customer review analysis system with sentiment analysis, topic modeling, and interactive visualization capabilities, optimized for Chinese language reviews.

Awesome Lists containing this project

README

        



CustomerInsight Logo

CustomerInsight


Comprehensive Customer Review Analysis System







![screencapture-chanmeng666-customerinsight-app-oeiu2h-streamlit-app-2024-11-30-16_18_57](https://github.com/user-attachments/assets/8914f8fd-53fd-4c42-b330-a0a5f2100f0e)

![screencapture-localhost-8501-2024-11-22-01_09_52](https://github.com/user-attachments/assets/406d52e0-fdba-4378-bc6b-c1b7ce6237d6)

![screencapture-localhost-8501-2024-11-30-16_29_21](https://github.com/user-attachments/assets/780e1366-ec84-45e6-8217-9fa6afff3344)

![screencapture-localhost-8501-2024-11-30-16_30_20](https://github.com/user-attachments/assets/baef9c1a-c969-4e03-bd44-a97ea05a5c01)

![screencapture-localhost-8501-2024-11-30-16_30_54](https://github.com/user-attachments/assets/04d88137-64ad-4bb6-93ea-38e0b3167c4a)

![screencapture-localhost-8501-2024-11-30-16_31_32](https://github.com/user-attachments/assets/935f01aa-7ad2-4181-ad4c-0895da595045)

# Features

🎯 **Comprehensive Analysis Tools**
- Sentiment Analysis with confidence scoring
- Keyword extraction and trend tracking
- Topic modeling and clustering
- Anomaly detection and deep insights

📊 **Interactive Visualization**
- Real-time data filtering and exploration
- Custom visualization options
- Dynamic trend analysis
- Comparative analytics

🌐 **Multi-language Support**
- Optimized for Chinese text
- English language compatibility
- Bilingual analysis capabilities

⚡ **Performance & Scalability**
- Efficient data processing
- Batch analysis support
- Caching for improved performance
- Error handling and validation

# Getting Started

## Prerequisites

- Python 3.7+
- Required packages:
```bash
pip install -r requirements.txt
```

## Installation

1. Clone the repository:
```bash
git clone https://github.com/ChanMeng666/customer-insight.git
cd customer-insight
```

2. Install dependencies:
```bash
pip install -r requirements.txt
```

3. Set up environment:
```bash
python setup.py install
```

## Usage

Run the Streamlit application:
```bash
streamlit run app.py
```

The application will be available at http://localhost:8501

# Technical Stack

📚 **Core Technologies**
- **Frontend**: Streamlit
- **Data Processing**: Pandas, NumPy
- **Text Analysis**:
- Jieba (Chinese word segmentation)
- Transformers (sentiment analysis)
- scikit-learn (topic modeling)
- **Visualization**: Plotly, Matplotlib
- **Machine Learning**: scikit-learn

# Features in Detail

## Text Analysis
- **Sentiment Analysis**: Evaluate emotional tone of reviews
- **Keyword Extraction**: Identify key terms and phrases
- **Topic Modeling**: Discover underlying themes
- **Anomaly Detection**: Flag unusual patterns

## Visualization
- Interactive time series plots
- Sentiment distribution charts
- Keyword clouds and trends
- Topic distribution maps

## Data Processing
- Flexible data import (CSV, Excel)
- Advanced filtering options
- Text preprocessing
- Statistical analysis

# Contributing

Contributions are welcome! Please feel free to submit pull requests.

# License

This project is licensed under the [Apache-2.0 license](LICENSE) - see the LICENSE file for details.

# Author

- **Chan Meng**
- LinkedIn: [chanmeng666](https://www.linkedin.com/in/chanmeng666/)
- GitHub: [ChanMeng666](https://github.com/ChanMeng666)

# Acknowledgments

- Thanks to all contributors who participated in this project
- Special thanks to the open source communities of Streamlit, Jieba, and other libraries used in this project