Sentiment Analysis on Tweets

Overview

The dataset can be downloaded from the below link. http://cs.stanford.edu/people/alecmgo/trainingandtestdata.zip

This project performs sentiment analysis on a dataset of tweets. The dataset contains labeled sentiments (0: Negative, 4: Positive), and the goal is to clean, analyze, and visualize the sentiment distribution.

Features

Data preprocessing (removal of unnecessary columns, text length calculations)

Exploratory Data Analysis (EDA)

Sentiment classification using basic machine learning techniques

Visualization of results

Prerequisites

Ensure you have the following installed before running the notebook:

Python 3.x

Jupyter Notebook

Required Python libraries:

pip install pandas numpy matplotlib seaborn scikit-learn

Dataset

You need to download the dataset manually since it is not included in the repository.

Download training.csv from Sentiment140 Dataset

Place the file in the appropriate directory (update the notebook path if needed)

How to Run

Clone this repository:

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

Open Jupyter Notebook:

jupyter notebook

Run Sentiment Analysis on Tweets.ipynb step by step.

Expected Outputs

Summary statistics of sentiment classes

Preprocessed tweet samples

Visualizations of sentiment distribution

Contributing

Feel free to submit pull requests or report issues.