Research Article
Sentiment Based Stock Price Analysis Using Deep Learning
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357969, author={Arpit Lamichhane and Atul Kumar Gupta and Sagar Gupta and N. Kathirvel}, title={Sentiment Based Stock Price Analysis Using Deep Learning}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={deep neural network financial markets lstm nlp sentiment analysis stock price prediction technical indicators}, doi={10.4108/eai.28-4-2025.2357969} }- Arpit Lamichhane
Atul Kumar Gupta
Sagar Gupta
N. Kathirvel
Year: 2025
Sentiment Based Stock Price Analysis Using Deep Learning
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2357969
Abstract
Stock price prediction is a difficult problem considering that financial markets are influenced by various entities such as company performance, economic indicators, and investor’s attitude. Towards this goal, we propose a multimodal approach which combines technical indicators and an investor sentiment score to an LSTM model and then uses the combined model to predict the future price of stock. Sentiment analysis is achieved using Natu- ral Language Processing (NLP), while technical indicators such as Moving Averages and Momentum Os- cillators invest further market features. Our model achieved AGM accuracy of 0.0018 and 91% respectively, compared to conventional methods. The findings indicate that the combination of deep learning with technical and sentiment analysis is beneficial for enhancing stock market decisions.
