Sentiment_Analysis_of_Telugu

Sentiment Analysis on Telugu Text Data

This project performs sentiment analysis on Telugu text data using both transformer-based and traditional machine learning models. We leverage models such as ALBERT, RoBERTa, and DistilBERT, as well as SVM, Logistic Regression, Naive Bayes, Decision Tree, Random Forest, and Linear Regression to classify sentiment in Telugu sentences.

Dataset

We use the Telugu Sentiment Dataset from Hugging Face, which contains labeled Telugu text data for sentiment classification.

Project Structure

• data/: Contains the dataset (downloaded or preprocessed)
• notebooks/: Jupyter notebooks for exploratory data analysis and model prototyping
• lexicon/: Contains the Positive and negative Sentence

  Models Implemented

1. Transformer Models:
   • ALBERT
   • RoBERTa
   • DistilBERT
2. Traditional Machine Learning Models:
   • Support Vector Machine (SVM)
   • Logistic Regression
   • Naive Bayes
   • Decision Tree
   • Random Forest
   • Linear Regression

Results

The models are evaluated based on Accuracy and F1 Score.

This site is open source. Improve this page.