Enhancing Sentiment Analysis in Noisy Stock Tweets Using Cognitive Particle Swarm Optimization-Based Sophisticated Deep Belief Network (CPSO-SDBN)

Enhancing Sentiment Analysis in Noisy Stock Tweets Using Cognitive Particle Swarm Optimization-Based Sophisticated Deep Belief Network (CPSO-SDBN)
  IJETT-book-cover           
  
© 2024 by IJETT Journal
Volume-72 Issue-6
Year of Publication : 2024
Author : G. Priyadarshini, D. Karthika
DOI : 10.14445/22315381/IJETT-V72I6P135

How to Cite?

G. Priyadarshini, D. Karthika, "Enhancing Sentiment Analysis in Noisy Stock Tweets Using Cognitive Particle Swarm Optimization-Based Sophisticated Deep Belief Network (CPSO-SDBN)," International Journal of Engineering Trends and Technology, vol. 72, no. 6, pp. 397-408, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I6P135

Abstract
In the fast-paced stock market, real-time information is the lifeblood of informed decision-making. Twitter, a prominent platform for disseminating news and opinions, holds a treasure trove of stock-related tweets that reflect market sentiment and trends. However, accurately classifying the sentiment expressed in these stock tweets poses a formidable challenge due to their unstructured nature and inherent noise. To tackle this issue, this research introduces a novel approach, CPSO-SDBN, which harnesses the power of Cognitive Particle Swarm Optimization (CPSO) to optimize a Sophisticated Deep Belief Network (SDBN) for sentiment analysis. CPSO-SDBN dynamically adapts to the ever-evolving and noisy stock tweet data by optimizing SDBN’s architecture and hyperparameters. It achieves this by leveraging CPSO, which guides the model’s configuration towards the most suitable setup for handling the complexities of stock tweet sentiment analysis. Leveraging the “Stock Tweets for Sentiment Analysis and Prediction” dataset, our research demonstrates significant improvements in sentiment analysis accuracy. These advancements empower traders, investors, and financial analysts with more precise sentiment insights, ultimately enhancing decision-making in the stock market.

Keywords
Stock market, Sentiment analysis, Twitter, Tweet, PSO, DBN.

References
[1] Jiahang Zhang, and Chi Zhang, “Do Cryptocurrency Markets React to Issuer Sentiments? Evidence from Twitter,” Research in International Business and Finance, vol. 61, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Cheng Qian et al., “Understanding Public Opinions on Social Media for Financial Sentiment Analysis Using AI-based Techniques,” Information Processing & Management, vol. 59, no. 6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Huihui Ni, Shuting Wang, and Peng Cheng, “A Hybrid Approach for Stock Trend Prediction Based on Tweets Embedding and Historical Prices,” World Wide Web, vol. 24, no. 3, pp. 849-868, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Efstathios Polyzos, “Escalating Tension and the War in Ukraine: Evidence Using Impulse Response Functions on Economic Indicators and Twitter Sentiment,” Research in International Business and Finance, vol. 66, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Daniele Ballinari, Francesco Audrino, and Fabio Sigrist, “When does Attention Matter? The Effect of Investor Attention on Stock Market volatility Around News Releases,” International Review of Financial Analysis, vol. 82, pp. 1-28, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Loukas Ilias, and Ioanna Roussaki, “Detecting Malicious Activity in Twitter using Deep Learning Techniques,” Applied Soft Computing, vol. 107, pp. 1-19, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Duong Phuong Thao Pham, Ngoc Quang Anh Huynh, and Duy Duong, “The Impact of US Presidents on Market Returns: Evidence from Trump’s Tweets,” Research in International Business and Finance, vol. 62, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Rui Fan, Oleksandr Talavera, and Vu Tran, “Information Flows and the Law of One Price,” International Review of Financial Analysis, vol. 85, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Yihong Zhang et al., “Twitter-Aided Decision Making: A Review of Recent Developments,” Applied Intelligence, vol. 52, pp. 13839-13854, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Darren Leitch, and Mohamed Sherif, “Twitter Mood, CEO Succession Announcements and Stock Returns,” Journal of Computational Science, vol. 21, pp. 1-10, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Hera Shaheen, Shikha Agarwal, and Prabhat Ranjan, “MinMaxScaler Binary PSO for Feature Selection,” First International Conference on Sustainable Technologies for Computational Intelligence, Advances in Intelligent Systems and Computing, pp. 705-716, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Daniel Câmara, “4 - Swarm Intelligence (SI),” Bio-inspired Networking, pp. 81-102, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[13] David Valle-Cruz et al., “Does Twitter Affect Stock Market Decisions? Financial Sentiment Analysis During Pandemics: A Comparative Study of the H1N1 and the COVID-19 Periods,” Cognitive Computation, vol. 14, pp. 372-387, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Attila Sóti et al., “Influence of Twitter Activity on the Stock Price of Soccer Clubs,” Social Network Analysis and Mining, vol. 10, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Imen Hamraoui, and Adel Boubaker, “Impact of Twitter Sentiment on Stock Price Returns,” Social Network Analysis and Mining, vol. 12, no. 1, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] N. Deepika, and M. Nirupama Bhat, “An Efficient Stock Market Prediction Method Based on Kalman Filter,” Journal of the Institution of Engineers (India): Series B, vol. 102, no. 4, pp. 629-644, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Tareek Pattewar, and Dinesh Jain, “Stock Prediction Analysis by Customers Opinion in Twitter Data Using an Optimized Intelligent Model,” Social Network Analysis and Mining, vol. 12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[18] T. Swathi, N. Kasiviswanath, and A. Ananda Rao, “An Optimal Deep Learning-based LSTM for Stock Price Prediction Using Twitter Sentiment Analysis,” Applied Intelligence, vol. 52, pp. 13675-13688, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Suparna Dhar, and Indranil Bose, “Emotions in Twitter Communication and Stock Prices of Firms: The Impact of Covid-19 Pandemic,” Decision, vol. 47, pp. 385-399, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Emrah Sitki Yilmaz, Asli Ozpolat, and Mehmet Akif Destek, “Do Twitter Sentiments Really Effective on Energy Stocks? Evidence from the Intercompany Dependency,” Environmental Science and Pollution Research, vol. 29, pp. 78757-78767, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Wasiat Khan et al., “Predicting Stock Market Trends Using Machine Learning Algorithms via Public Sentiment and Political Situation Analysis,” Soft Computing, vol. 24, pp. 11019-11043, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Giovanni Carnazza, “The Impact of the Social Mood on the Italian Sovereign Debt Market: A Twitter Perspective,” Italian Economic Journal, vol. 10, pp. 125-154, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Pooja Mehta, Sharnil Pandya, and Ketan Kotecha, “Harvesting Social Media Sentiment Analysis to Enhance Stock Market Prediction using Deep Learning,” PeerJ Computer Science, vol. 7, pp. 1-21, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[24] J. Kennedy, and R. Eberhart, “Particle Swarm Optimization,” Proceedings of ICNN'95 - International Conference on Neural Networks, Perth, WA, Australia, pp. 1942- 1948, 1995.
[CrossRef] [Google Scholar] [Publisher Link]