Twitter Sentiment Analysis

This project is a sentiment analysis tool that analyzes tweets from Twitter to determine their sentiment (positive, negative, or neutral). Built with Flask, it provides a web interface to interact with the sentiment analysis functionality.

Prerequisites

Ensure you have the following installed:

• Python (3.x recommended)
• pip (Python package installer)

Installation

1. Clone the repository:

git clone https://github.com/leylamemiguven/twitter-sentiment-analysis.git
cd twitter-sentiment-analysis

2. Create a virtual environment (optional but recommended):

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install Dependencies

pip install -r requirements.txt

4. Running the Application

python app.py

Application Overview

Here is what the app preview looks like:

As it can be seen in the picture above, the machine learning model has classified the word "iğrenç" (which translates to "disgusting")as negative with 63% probablitiy . Here are some other examples:

Example 1 --> Positive

Here the phrase "çok güzel olmuş ellerinize sağlık" translates to "This is wonderful good job". As this is a positive sentiment, it is classified as positive.

Example 2 --> Negative

Here the phrase "bok gibi olmuş bir daha olmasın" translates to "This is so bad like s*it, please don't let it happen again". As this is a negative sentiment, it is classified as negative.

Feel free to enhance or customize this project as needed!