This repository contains the code for performing sentiment analysis on Twitter data related to the movie Adipurush. The sentiment analysis is done using machine learning techniques, and the project includes data preprocessing, exploratory data analysis, and model training.
Python 3.6 or higher Jupyter Notebook (for running the provided code) Libraries listed in requirements.txt
Clone the repository:
bash
git clone https://github.com/your-username/adipurush-sentiment-analysis.git
cd adipurush-sentiment-analysis
bash
pip install -r requirements.txt
Download the Twitter data CSV file (adipurush_tweets.csv) and place it in the project root directory.
bash jupyter notebook Run the cells in the notebook to perform data cleaning, exploratory data analysis, and sentiment analysis.
Optionally, customize the code for further analysis or visualization based on your needs.
The sentiment analysis results are presented in various visualizations, including histograms, pie charts, and word clouds. The overall sentiment distribution and key insights from the analysis are highlighted.
The project includes training models using Naive Bayes and XGBoost classifiers. The accuracy of the models on the test set is reported.
Word clouds are generated for positive, negative, and neutral sentiments to visually represent the most frequent words in each category.
The code in this repository is inspired by real-world sentiment analysis projects. The Twitter data used in this project is not included in the repository and must be obtained separately.
Feel free to reach out with any questions or feedback!