Skip to main navigation Skip to search Skip to main content

Hybrid Dataset Trained LSTM Model for Forecasting Stock Market Trends: Analyzing Sentiment of Tweets and Nifty 50 Index Values

  • Anupkumar M. Bongale*
  • , Heeral Gandhi
  • , Eshita Upadhyaya
  • , Akshay Sangwan
  • , Aniket Anand
  • , Deepak Dharrao
  • , Raguru Jaya Krishna
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This research paper proposes a hybrid method that combines historical stock data with sentiment analysis of Twitter data to predict the stock market index. Twitter has become a popular platform for expressing public opinion and sentiment about various events, including the stock market. The study employs various steps such as preprocessing, hyperparameter tuning, and Long Short-Term Memory (LSTM) modeling to analyze the sentiment of tweets and forecast Nifty 50 index values. The proposed approach provides a promising direction for predicting stock market indices, particularly based on short-term prediction using social media data. The hybrid dataset combining historical stock index values with Twitter text data leads to improved accuracy in forecasting stock market indices and trends.

Original languageEnglish
Title of host publicationSmart Systems
Subtitle of host publicationInnovations in Computing - Proceedings of SSIC 2023
EditorsArun K. Somani, Ankit Mundra, Rohit Kumar Gupta, Subhajit Bhattacharya, Arka Prokash Mazumdar
PublisherSpringer Science and Business Media Deutschland GmbH
Pages399-412
Number of pages14
ISBN (Print)9789819736898
DOIs
Publication statusPublished - 2024
Event4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023 - Jaipur, India
Duration: 26-10-202327-10-2023

Publication series

NameSmart Innovation, Systems and Technologies
Volume392 SIST
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023
Country/TerritoryIndia
CityJaipur
Period26-10-2327-10-23

All Science Journal Classification (ASJC) codes

  • General Decision Sciences
  • General Computer Science

Fingerprint

Dive into the research topics of 'Hybrid Dataset Trained LSTM Model for Forecasting Stock Market Trends: Analyzing Sentiment of Tweets and Nifty 50 Index Values'. Together they form a unique fingerprint.

Cite this