Stock Trend Direction Forecasting using Machine Learning and Twitter Data

Ashutosh Sharma

Ashutosh Sharma MCA Student, Computer Science Department Lucknow University, India.

Abstract

There has been a surge in interest in the analysis of stock market data as a result of technological developments and the development of new
machine learning models. This is so that dealers and businesspeople have a base from which to select more profitable enterprises. The
movement of stock prices has been significantly influenced by the information gleaned from what are regarded as mainstream media
sources. Platforms for online social networks have, however, recently pushed for an approach that is more effective in disseminating this
information. The data that can be discovered on social networks may be quite helpful in identifying the varied viewpoints and attitudes that
people have on particular subjects. An enhanced machine learning model is one of the possibilities being continuously researched for use
in daily forecasting due to the volume and variety of these data. This has led to a thorough comparison analysis of the stock market models that
have been used in the past being conducted as part of this endeavour. Yahoo Finance and Kaggle are the sources for the information on
Apple stock, respectively. With accuracy rates ranging from 53 to 56 percent, the categorization technique did not offer enough assurance
to be used to link stock movement with emotions stated on Twitter. This made it impossible to use the strategy. Results were better when
the regression strategy was used instead of the classification strategy.

References

1. Diren Archary, Marijke Coetzee: Predicting Stock Price Movement with social media and Deep Learning. 2020
International Conference on Artificial Intelligence, Big Data, Compu- ting and Data Communication Systems
(icABCD), 2020
2. Samuel Olusegun Ojo, Pius Adewale Owolawi, Maredi Mphahlele, Juliana Adeola Adisa.: Stock Market Behaviour Prediction using Stacked LSTM Networks. 2019 International Multidisciplinary Information Technology and Engineering Conference (LIMITED), 2019.
3. Iyad Lahsen Cherif, Abdesselem Kortebi.: On using eXtreme Gradient Boosting (XGBoost) Machine Learning algorithm for Home Network Traffic Classification. 2019 Wireless Days (WD), 2019
4. Vazirani, Sahil, Abhishek Sharma, Pavika Sharma.: Analysis of various machine learn- ing algorithm and
hybrid model for stock market prediction using python. In 2020 Interna- tional Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), pp. 203-207. IEEE, 2020.
5. Ranibaran, Golshid, Mohammad-Shahram Moin, Sasan H. Alizadeh, Abbas Koochari.: Analyzing effect of news
polarity on stock market prediction: a machine learning approach. In 2021 12th International Conference on Information and Knowledge Technology (IKT), pp.
102-106. IEEE, 2021.
6. Lakshminarayanan, Sai Krishna, John P. McCrae.: A Comparative Study of SVM and LSTM Deep Learning Algorithms for Stock Market Prediction. In AICS, pp. 446-457. 2019.
7. Rohatgi, Sachin, Krishna Kumar Singh, Deepmala Jasuja.: Comparative Analysis of Machine Learning
Algorithm to Forecast Indian Stock Market. In 2021 International Con- ference on Advance Computing and
Innovative Technologies in Engineering (ICACITE), pp. 278-283. IEEE, 2021.
8. Sun, Linyu.: Application and improvement of Xgboost algorithm based on multiple param- eter optimization strategy. In 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), pp. 1822-1825. IEEE, 2020.
9. Ma, Zhong, Jiansheng Guo, Sheng Mao, Taoyong Gu.: An Interpretability research of the Xgboost algorithm in
remaining useful life prediction. In 2020 International Conference on Big Data & Artificial Intelligence & Software
Engineering (ICBASE), pp. 433-438. IEEE, 2020.
10. Nabipour, Mojtaba, Pooyan Nayyeri, Hamed Jabani, S. Shahab, Amir Mosavi.: Predict- ing stock market trends
using machine learning and deep learning algorithms via continuous and binary data; a comparative analysis. IEEE Access 8 (2020): 150199-150212.
11. Lin, Yaohu, Shancun Liu, Haijun Yang, Harris Wu.: Stock Trend Prediction Using Can- dlestick Charting
and Ensemble Machine Learning Techniques With a Novelty Feature En- gineering Scheme. IEEE Access 9
(2021): 101433-101446.
12. Li, Qing, Jinghua Tan, Jun Wang, Hsinchun Chen.: A multimodal event-driven lstm model for stock prediction
using online news. IEEE Transactions on Knowledge and Data Engineering 33, no. 10 (2020): 3323-3337.
13. Kilimci, Zeynep Hilal, Ramazan Duvar.: An efficient word embedding and deep learn- ing based model
to forecast the direction of stock exchange market using Twitter and finan- cial news sites: a case of Istanbul
stock exchange (BIST 100). IEEE Access 8 (2020): 188186-188198.
14. Alsubaie, Yazeed, Khalil El Hindi, Hussain Alsalman.: Cost-sensitive prediction of stock price direction: Selection of technical indicators. IEEE Access 7 (2019): 146876- 146892.