Sentimentinator is a web-based sentiment analysis tool that utilizes natural language processing (NLP) techniques to analyze and determine the sentiment (positive, neutral, or negative) of textual content. The project aims to help users understand the emotional tone and polarity of text data, making it useful for various applications, such as social media monitoring, customer feedback analysis, and more.
Link to the Website
Project Flowchart
Graphs for Test Data
Confusion Matrix
Accuracy Graph
Tech Stack
- Python (3.10.4)
- Flask
- HTML
- CSS
- JavaScript
- Natural Language Processing (NLP) Stack:
- NLTK (Natural Language Toolkit)
- Scikit-learn
- Matplotlib
- Pandas
- Numpy
- Regular Expressions (Regex)
Features
-
Sentiment Prediction: Sentimentinator provides the ability to predict the sentiment of text input, categorizing it as positive, neutral, or negative.
-
Web Interface: Users can interact with the sentiment analysis tool through a user-friendly web interface.
-
Sample Text Prompts: The website offers sample text prompts for easy testing and demonstration of the sentiment analysis tool.
-
Data Visualization: Sentimentinator provides data visualization tools to help users understand the performance of the sentiment analysis model.
Model Training
To know more about the model training process, please refer to the Sentiment_Analysis.ipynb.
Installation
-
Clone the repo
git clone https://github.com/Hardvan/Sentimentinator.git
-
Navigate to the folder
-
Create a virtual python environment by typing the following in the terminal
-
Activate the virtual environment
Windows:
Linux:
source .venv/bin/activate -
Install dependencies by typing the following in the terminal
pip install -r requirements.txt
-
Run the app
-
Click on the link in the terminal to open the website
It will look something like this:
Running on http://127.0.0.1:5000