International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/3117 2020 2020 Department of Mathematics, Hindustan Institute of Technology, Chennai-603103, India Vediyappan Vediyappan Department of Mathematics, Hindustan Institute of Technology, Chennai-603103, India Vediyappan Govindan School of Science, University of Phayao, Phayao 56000, Thailand Mana Donganont Laboratory of Information Processing, Faculty of Science Ben M’Sik, University Hassan II, Casablanca, Morocoo; STIE team, Regional Center for the Professions of Education and Training (C.R.M.E.F), Casablanca-Settat, Morocco Broumi Said In this paper, we present sentiment analysis on Twitter data by employing Neutrosophic Sentiment Analysis (NSA). NSA captures sentiments by considering three aspects: truth, falsehood, and indeterminacy, offering a more nuanced understanding of sentiment in tweets. To enhance this analysis, we integrate the results from Neutrosophic logic (NL) sentiment analysis into a Bi-directional Long Short-Term Memory (LSTM) model. This integration takes use of NL's capacity to manage uncertainty and indeterminacy in social media material, as well as the Bi-directional LSTM's capability to capture temporal relationships in sequential data. Our combined NL-Bidirectional LSTM technique attempts to increase the precision of forecasting, particularly when it comes to predicting stock market patterns based on Twitter sentiment. Through comprehensive evaluation, we demonstrate the effectiveness of this approach, highlighting its potential to address the inherent uncertainties and indeterminacies in social media data and thereby provide more reliable predictions for stock market movements. 2025 2025 84 92 10.54216/IJNS.250208 https://www.americaspg.com/articleinfo/21/show/3117