NATURAL LANGUAGE PROCESSING PROJECTS
Sentiment Analysis of Amazon Reviews using BERT
Implemented a sentiment analysis system utilizing a pretrained BERT model from Hugging Face to analyze over half a million Amazon reviews. Engineered a robust data preprocessing pipeline, fine-tuned the BERT model for sentiment analysis, and trained it on the extensive review dataset. Achieved optimal performance and deployed the model to predict ratings for new reviews, enhancing decision-making and user experience.
Stock Price Sentiment Analysis using News Headlines
Engineered a Word2Vec model to meticulously extract word embedding features from diverse news headlines. Leveraged a Random Forest classifier for precise prediction of stock price movements across multiple companies, addressing the challenging task of gauging market dynamics. Demonstrated exceptional model performance, attaining a remarkable accuracy rate of 85%, underscoring the model's efficacy in forecasting stock price fluctuations and aiding investment decisions.
Multilingual AI-powered Chatbot for Customer Support
Developed a cutting-edge multilingual AI-powered chatbot for customer support at One Energy, North America's largest wind energy supplier. This innovative solution will significantly enhance customer engagement, streamline support processes, and reduce response times, resulting in an improvement in customer satisfaction and operational efficiency. The chatbot's seamless multilingual capabilities will further expand One Energy's reach and service accessibility, cementing its position as an industry leader.
