[Proposal-ML]Enhancing Sentiment Analysis in Financial Markets Using RNNs and Word Embeddings

Ethan Wei Yuxin, Liu Yiyang, Chan Thong Fong

Keywords: AI, ML, RNN, LSTM, Sentiment Analysis

Abstract: This project centers on enhancing sentiment analysis in financial markets by classifying and interpreting sentiment from sources such as news articles and social media. Sentiment analysis offers unique insights valuable for financial predictions as it often aligns closely with stock movements [1, 2]. Using Recurrent Neural Networks (RNNs), particularly Long Short-Term Memory (LSTMs) and Gated Recurrent Units (GRUs), along with word embeddings, this project aims to capture sentiment trends over time, which may benefit investors by improving risk management and investment strategies.

Submission Number: 28