This project implements a sentiment and emotion detection system using LSTM (Long Short-Term Memory), BERT (Bidirectional Encoder Representations from Transformers), React, and Flask. The system provides an intuitive user interface for inputting text and obtaining sentiment and emotion analysis results. It recommends medicine if the predicted emotion is negative.
Sentiment and emotion detection is a task of analyzing the sentiment and emotional tone expressed in a given text. This project leverages the power of LSTM and BERT models to perform sentiment and emotion analysis on user-provided texts.
The LSTM model is a type of recurrent neural network (RNN) that can capture long-term dependencies in sequential data. It has been trained on a sentiment analysis dataset to predict the sentiment of a given text as positive, negative, or neutral.
BERT, on the other hand, is a pre-trained transformer model that excels at understanding the contextual meaning of words and sentences. It has been fine-tuned on an emotion analysis dataset to predict the emotion associated with a given text.
The frontend of the system is built using React, a popular JavaScript library for building user interfaces. It provides an interactive and user-friendly interface for users to enter text and receive sentiment and emotion analysis results.
The backend of the system is implemented using Flask, a lightweight web framework in Python. It serves as the server-side component responsible for handling incoming requests from the frontend, processing the text, and invoking the LSTM and BERT models for sentiment and emotion analysis.
- Sentiment analysis using LSTM model
- Emotion analysis using BERT model
- Recommend ayurvedic medicine for negative emotions
- User-friendly and responsive frontend interface
- Quick and accurate sentiment and emotion analysis results