This repository contains code for sentiment analysis using BERT-based model and Transformers library to predict sentiments from text reviews. The model is fine-tuned for sentiment classification and can be used to analyze sentiments of reviews in multiple languages.
Sentiment analysis is the process of determining the emotional tone behind a series of words, and it has various applications in natural language processing. This project demonstrates how to perform sentiment analysis using a pre-trained BERT-based model and Transformers library. The BERT model used here is 'nlptown/bert-base-multilingual-uncased-sentiment', which is specifically designed for multilingual sentiment analysis tasks.
To run this project, you need to have the following dependencies installed:
- Python 3.7 or higher
- torch==1.8.1+cu101
- torchvision==0.9.1+cu101
- torchaudio==0.8.1
- transformers
- requests
- beautifulsoup4
- pandas
- numpy
This project was inspired by the need for a simple yet effective sentiment analysis solution using BERT-based models and the Transformers library. Special thanks to the open-source community for providing valuable tools and resources that make projects like this possible.
you can download the amazon reviews data set through the below link. It contains approx 500k reviews .or you can collect the data from the online review website as shown in the code. kaggle link :https://www.kaggle.com/code/robikscube/sentiment-analysis-python-youtube-tutorial/input