Movies Review System | Spoiler-Free Sentiment-Analysis based Movies Review System) |
Date:
Role: Team Lead + Backend (AI/ML)
Vision/Goal: To provide an interface to allow users to read spoiler-free reviews along with a touch of sentiment analysis (on reviews) for a better viewing experience
Solution: Made use of the a Machine Learning model(sentiment analysis) using Voting Classifier(SVC+Logistic Regression) and Deep learning model(spoiler v/s non-spoiler) using Bi-LSTMs after thorough preprocessing and custom trained Word2Vec.
Results Successfully built the said WebApp with Streamlit as front-end. Achieved an accuracy of 91 % with precision 91 % and recall 90 %.
Tools: Keras, Tensorflow, Word2Vec (Word Embeddings), Bi-LSTMs, NLTK, Spacy, Streamlit, Render