Stock Prices Prediction from Financial News Articles Using LSTM and XAI

Gite, Shilpa; Khatavkar, Hrituja; Srivastava, Shilpi; Maheshwari, Priyam; Pandey, Neerav

doi:10.1007/978-981-16-0733-2_11

Cited by 5 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, only one recent publication by Naila et al (2022) [26] explored both sentiment analysis and emotion detection using a multitask learning framework. Due to the temporal nature of financial data, Explainable AI (XAI) can be utilized to determine the most significant features or inputs that contribute to predicting market trends [27] and making investment decisions [28] thereby mitigating risks [29] associated with financial investments. Until now, no research has specifically focused on identifying and extracting causative factors from tweet texts, especially in scenarios where public sentiment strongly influences investment choices.…”

Section: Related Workmentioning

confidence: 99%

Investigate How Market Behaves: Toward an Explanatory Multitasking Based Analytical Model for Financial Investments

Das,

Chowdhury,

Lijin

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In recent years, the intersection between financial market behaviour and social media has emerged as a sought-after source of information, meeting the requirements of investors, institutions, regulators, researchers, and policymakers. Assessing sentiment and emotions aids in evaluating public psychology on particular stocks, assets, or the overall market, with shifts often aligning with market movements. Previously, machine learning, both traditional and deep learning methods, targeted discerning stock market sentiment and emotion without conducting studies to offer comprehensive explanations for these behavioural factors. This study introduces a multitasking sequence-to-sequence model that integrates financial investment analysis with sentiment and emotion analysis from tweets upheld by an explanation mechanism. We also present the FinEMA dataset, featuring sentiment, emotion, and cause labels on financial stock market changes. Our study highlights how joint learning improves performance in discerning sentiment and emotion by utilizing interrelated features, enhancing task effectiveness. Our proposed model, the Emotion-Sentiment Attention Network (ESAN), achieved 89% accuracy in sentiment identification and 79% accuracy in emotion recognition, outperforming conventional machine learning methods. Furthermore, our findings indicate a positive outlook for the stock market in the latter half of 2023, which has intensified investor optimism, though some individuals still harbour uncertainties. Conclusively, our results suggest that regenerating existing computational tools can open up new research opportunities to address relevant novel tasks. Disclaimer: The primary aim of this study is to elucidate the diverse dimensions of financial market behaviour and offer explanatory insights for the research community. The authors maintain impartiality towards specific stocks. It's essential to note that stock market investments inherently carry market risks and potential losses. The market information within the research findings remains independent of the authors' viewpoints.

show abstract