Volume 27 , Issue 2 , PP: 360-372, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Zokir Mamadiyarov 1 * , Ziyodulla Khakimov 2 , Dilmurad Bekjanov 3 , Hafis Hajiyev 4 , Natalia Falina 5
Doi: https://doi.org/10.54216/IJNS.270230
Neutrosophic Logic is a neonate field of research in which all propositions are considered to have the percentage of truth in a subset I, F, and T. Neutrosophic set (NS) has been positively utilized for indeterminate data processing, and proven benefits for addressing the indeterminacy data information and is still a method nominated for classification application and data analysis. Soft set (SS) is a powerful device for handling the uncertainty of information in a parametric situation. On the other hand, the concept of interval-valued neutrosophic soft sets (IVNSSs) is a novel generality of the neutrosophic soft sets (NSSs) to the NSs once the authors incorporate the important features of IVNS and soft sets (SSs) in one method. Therefore, this method operated to offer decision-makers with flexibility in the procedure of understanding unclear information. From the scientific viewpoint, the procedure of estimating this higher performance IVNSS vanishes. Q-neutrosophic SSs are fundamentally NSSs considered by 3 independent 2D membership functions that represents indeterminacy, falsity and uncertainty. Therefore, it is used to 2D inconsistent, imprecise and indeterminate data, which seem in most real world challenges. The usage of robo-readers for analyzing news texts is the advanced technology trend in financial technology. A considerable effort has been invested to develop refined financial orientation that is applied to inspect how financial sentiments related to future performance of the company. Recently, the financial sentiment analysis (SA) has become a more and more related subfield within text analytics that addresses the computational analysis of subjectivity and opinion in texts. Most of the methods have concentrated on particular fields, utilizing type-based corpora as training data for machine learning (ML) methods that classify the input text as both negative and positive. In this manuscript, we develop a Semantic Orientation Identification Framework in Economic Text Using Q-neutrosophic soft matrix under Interval-valued (SOIFET-IVQNSM) model for financial SA. The aim of the paper is to propose an innovative approach for identifying semantic orientation in economic texts to enhance financial sentiment and prediction accuracy. Primarily, the input text data is preprocessed utilizing diverse preprocessing levels like removal of stop words, tokenization, stemming, spelling correction, and lemmatization to make it suitable for further processing. Besides, the word embedding process is mainly executed by the term frequency-inverse document frequency (TF-IDF) model to transform economic text into meaningful vector representation. For classification purpose, the proposed SOIFET-IVQNSM model designs a Q-neutrosophic soft matrix under Interval-valued (IV-Q-NSM) model. The simulation validation of the SOIFET-IVQNSM algorithm is tested on a benchmark database, and the results are measured under several metrics. The simulation result highlighted the improvement of the SOIFET-IVQNSM system in semantic orientation identification.
Neutrosophic Set , Semantic Orientation Identification , Economic Text , Interval-Valued Neutrosophic Set , Neutrosophic Logic , Financial Sentiment
[1] F. Smarandache, "Neutrosophic set is a generalization of intuitionistic fuzzy set, inconsistent intuitionistic fuzzy set (picture fuzzy set, ternary fuzzy set), pythagorean fuzzy set, spherical fuzzy set, and q-rung orthopair fuzzy set, while neutrosophication is a generalization of regret theory, grey system theory, and three-ways decision (revisited)," Journal of New Theory, no. 29, pp. 1–31, 2019.
[2] A. A. M. et al., "Fuzzy decision-making framework for renewable energy investment," Energy Reports, vol. 6, pp. 123–130, 2021.
[3] J. Smith, R. Johnson, and L. Brown, "An overview of fuzzy logic applications in decision-making processes," Journal of Fuzzy Logic and Applications, vol. 15, no. 3, pp. 45–56, 2023.
[4] S. R. A. et al., "Applications of neutrosophic logic in decision-making," Neutrosophic Sets and Systems, vol. 38, pp. 100–112, 2022.
[5] H. K. M. H. et al., "Soft computing models for predicting market trends," Journal of Computational Intelligence and Applications, vol. 19, no. 1, pp. 77–89, 2024.
[6] A. B. C. et al., "A comparative study of fuzzy and neutrosophic models in operational research," International Journal of Operations Research, vol. 21, no. 2, pp. 134–145, 2023.
[7] Q. H. Ngo, T. Kechadi, and N.-A. Le-Khac, "Domain specific entity recognition with semantic-based deep learning approach," IEEE Access, vol. 9, pp. 152 892–152 902, 2021.
[8] L. Chen, S. Xu, L. Zhu, J. Zhang, X. Lei, and G. Yang, "A deep learning based method for extracting semantic information from patent documents," Scientometrics, vol. 125, no. 1, pp. 289–312, 2020.
[9] C. X. Wan and B. Li, "Financial causal sentence recognition based on BERT-CNN text classification," The Journal of Supercomputing, vol. 78, no. 5, pp. 6503–6527, 2022.
[10] A. Onan, "Sentiment analysis on massive open online course evaluations: a text mining and deep learning approach," Computer Applications in Engineering Education, vol. 29, no. 3, pp. 572–589, 2021.
[11] H. Raza, M. Faizan, A. Hamza, A. Mushtaq, and N. Akhtar, "Scientific text sentiment analysis using machine learning techniques," International Journal of Advanced Computer Science and Applications, vol. 10, no. 12, pp. 157–165, 2019.
[12] A. Al Maruf, Z. M. Ziyad, M. M. Haque, and F. Khanam, "Emotion detection from text and sentiment analysis of Ukraine Russia war using machine learning technique," International Journal of Advanced Computer Science and Applications, vol. 13, no. 12, 2022.
[13] Z. Yang, G. Xiong, Z. Cao, Y. Li, and L. Huang, "A decision method for online purchases considering dynamic information preference based on sentiment orientation classification and discrete DIFWA operators," IEEE Access, vol. 7, pp. 77 008–77 026, 2019.
[14] Y. Liu et al., "A Multi-Level Sentiment Analysis Framework for Financial Texts," arXiv preprint arXiv: 2504.02429, 2025.
[15] N. Cai et al., "A Hybrid Intention Recognition Framework with Semantic Inference for Financial Customer Service," Electronics, vol. 14, no. 3, p. 495, 2025.
[16] M. T. Hosain, M. K. Morol, and M. J. Hossen, "A hybrid self attentive linearized phrase structured transformer based RNN for financial sentence analysis with sentence level explainability," Scientific Reports, vol. 15, no. 1, p. 23 893, 2025.
[17] D. Tiwari et al., "A swarm-optimization based fusion model of sentiment analysis for cryptocurrency price prediction," Scientific Reports, vol. 15, no. 1, p. 8119, 2025.
[18] L. Shang, H. Xi, J. Hua, H. Tang, and J. Zhou, "A Lexicon Enhanced Collaborative Network for targeted financial sentiment analysis," Information Processing & Management, vol. 60, no. 2, p. 103 187, 2023.
[19] M. Vijay, G. Deepak, and A. Santhanavijayan, "FSOL: financial document recommendation using hybridized semantics oriented learning," in Proc. International Conference on Electronic Governance with Emerging Technologies, Cham: Springer, 2023, pp. 125–139.
[20] B. Zhang, H. Yang, and X. Y. Liu, "Instruct-fingpt: Financial sentiment analysis by instruction tuning of general-purpose large language models," arXiv preprint arXiv: 2306.12659, 2023.
[21] R. Bhanuse and S. Mal, "An Effective Online Learning Course Recommendation Using Improved Deep Active Convolutional Neural Network Based Sentiment Analysis and Ranking," (no publication details provided).
[22] E. Elhosary and O. Moselhi, "Evaluating Natural Language Processing Algorithms for Improved Hazard and Operability Analysis," Geodata and AI, p. 100 026, 2025.
[23] F. Al-Sharqi, A. Al-Quran, M. U. Romdhini, Z. M. Rodzi, and H. A. E. W. Khalifa, "Distance and similarity measures on interval-valued Q-neutrosophic soft environments and their applications," International Journal of Mathematics, Statistics, and Computer Science, vol. 3, pp. 313–322, 2025.
[24] E. Hazaymeh, Y. Al-Qudah, F. Al-Sharqi, and A. Bataihah, "A novel Q-neutrosophic soft under interval matrix setting and its applications," International Journal of Neutrosophic Science, vol. 25, no. 4, 2025.
[25] S. Bhatti, "Financial Sentiment Analysis Dataset," 2023. [Online]. Available: https://www.kaggle.com/datasets/sbhatti/financial-sentiment-analysis/data
[26] K. Mishev, A. Gjorgjevikj, I. Vodenska, L. T. Chitkushev, and D. Trajanov, "Evaluation of sentiment analysis in finance: from lexicons to transformers," IEEE Access, vol. 8, pp. 131 662–131 682, 2020.
[27] G. Duan, S. Yan, and M. Zhang, "A hybrid neural network model for sentiment analysis of financial texts using topic extraction, pre-trained model, and enhanced attention mechanism methods," IEEE Access, 2024.
[28] M. Adith and D. Gupta, "Effective Complaint Detection in Financial Services through Complaint, Severity, Emotion and Sentiment Analysis," Procedia Computer Science, vol. 258, pp. 2220–2231, 2025.
