Enhancing Multi-Entity Detection and Sentiment Analysis in Financial Texts with Hierarchical Attention Networks

Hafezi, L.; Zarifzadeh, S.; Pajoohan, M. R.

doi:10.22061/jecei.2025.11294.790

فهرست نشریات

دانشگاه تربیت دبیر شهید رجائی

انتشارات دانشگاه تربیت دبیر شهید رجائی

نشریات مستقل دانشگاه در سامانه ارزیابی نشریات علمی وزارت علوم

نشریه معماری وشهرسازی پایدار موفق به اخذ رتبه علمی-پژوهشی شد

تعداد نشریات	11
تعداد شماره‌ها	215
تعداد مقالات	2,169
تعداد مشاهده مقاله	3,023,637
تعداد دریافت فایل اصل مقاله	2,208,640

	Enhancing Multi-Entity Detection and Sentiment Analysis in Financial Texts with Hierarchical Attention Networks
Journal of Electrical and Computer Engineering Innovations (JECEI)
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 15 اسفند 1403 اصل مقاله (961.89 K)
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2025.11294.790
نویسندگان
L. Hafezi؛ S. Zarifzadeh^* ؛ M. R. Pajoohan
Computer Engineering Department, Faculty of Engineering, Yazd University, Yazd, Iran.
تاریخ دریافت: 28 آبان 1403، تاریخ بازنگری: 16 بهمن 1403، تاریخ پذیرش: 17 بهمن 1403
چکیده
Background and Objectives: Detecting multiple entities within financial texts and accurately analyzing the sentiment associated with each is a challenging yet critical task. Traditional models often struggle to capture the nuanced relationships between multiple entities, especially when sentiments are context-dependent and spread across different levels of a document. Addressing these complexities requires advanced models that can not only identify multiple entities but also distinguish their individual sentiments within a broader context. This study aims to introduce and evaluate two novel methods, ENT-HAN and SNT-HAN, built upon the Hierarchical Attention Networks, specifically designed to enhance the accuracy of both entity extraction and sentiment analysis in complex financial documents. Methods: In this study, we design ENT-HAN and SNT-HAN methods to address the tasks of multi-entity detection and sentiment analysis within financial texts. The first method focuses on entity extraction, where capture hierarchical relationships between words and sentences. By utilizing word-level attention, the model identifies the most relevant tokens for recognizing entities, while sentence-level attention helps refine the context in which these entities appear, allowing the model to detect multiple entities with precision. The second method is applied for sentiment analysis, aiming to classify sentiments into positive, negative, or neutral categories. The sentiment analysis model employs hierarchical attention to identify the most important words and sentences that convey sentiment about each entity. This approach ensures that the model not only focuses on the overall sentiment of the text but also accounts for context-specific variations in sentiment across different entities. Both methods were evaluated on FinEntity dataset, and the results demonstrate their effectiveness, with significantly improving the accuracy of both entity extraction and sentiment classification tasks. Results: The ENT-HAN and SNT-HAN demonstrated strong performance in both entity extraction and sentiment analysis, outperforming the methods they were compared against. For entity extraction, ENT-HAN was evaluated against RNN and BERT models, showing superior accuracy in identifying multiple entities within complex texts. In sentiment analysis, SNT-HAN was compared to the best-performing method previously applied to FinEntity dataset. Despite the good performance of the existing methods, SNT-HAN demonstrated superior results, achieving a better accuracy. Conclusion: The outcome of this research highlights the potential of the ENT-HAN and SNT-HAN for improving entity extraction and sentiment analysis accuracy in financial documents. Their ability to model attention at multiple levels allows for a more nuanced understanding of text, establishing them as a valuable resource for complex tasks in financial text analysis.
کلیدواژه‌ها
Hierarchical Attention Network؛ Entity Detection؛ Sentiment Analysis

مراجع
[1] K. Du, F. Xing, e “Financial sentiment analysis: Techniques and applications,” ACM Comput. Surv., 56(9): 1-42, 2024. [2] J. Yu, J. Jiang, R. Xia, "Entity-sensitive attention and fusion network for entity-level multimodal sentiment classification," IEEE/ACM Trans. Audio Speech Lan. Process., 28: 429-439, 2020. [3] Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, E. Hovy, “Hierarchical attention networks for document classification,” in Proc. the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: 1480-1489, 2016. [4] L. Deng et al., “Joint prediction for entity/event-level sentiment analysis using probabilistic soft logic models,” in Proc. 2015 Conf. Empirical Methods in Natural Language Processing: 179-189, 2015. [5] Y. Tang et al., “FinEntity: Entity-level sentiment classification for financial texts,” in Proc. 2023 Conference on Empirical Methods in Natural Language Processing: 15465-15471, 2023. [6] C. Liu et al., "Large language models and sentiment analysis in financial markets: A review, datasets, and case study," IEEE Access, 12: 134041-134061, 2024. [7] M. Kraus, S. Feuerriegel, “Decision support from financial disclosures with deep neural networks and transfer learning,” Decis. Support Syst., 104: 38-48, 2017. [8] S. Sohangir et al., “Big data: Deep learning for financial sentiment analysis,” J. Big Data, 5(1), 2018. [9] B. Lutz et al., “Sentence-level sentiment analysis of financial news using distributed text representations and multi-instance learning,” arXiv preprint arXiv:1901.00400, 2018. [10] M. Maia, et al., “FinSSLx: A sentiment analysis model for the financial domain using text simplification,” in Proc. 12th International Conf. Semantic Computing (ICSC): 318-319, 2018. [11] Z. Liu et al., “FinBERT: A pre-trained financial language representation model for financial text mining,” in Proc. International Joint Conf. Artificial Intelligence: 4513-4519, 2021. [12] G. Fatouros et al., “Transforming sentiment analysis in the financial domain with ChatGPT”, Mach. Learn. Appl., 14, 100508, 2023. [13] A. M. Ardekani et al. “FinSentGPT: A universal financial sentiment engine,” int. Rew. Financ. Anal., 94, 103291, 2024. [14] M. Luo, X. Mu, “Entity sentiment analysis in the news: A case study based on Negative Sentiment Smoothing Model (NSSM),” Int. J. Inf. Manage. Data Insights, 2(1), 2022. [15] S. Poria, E. Cambria, A. Gelbukh, “Aspect extraction for opinion mining with a deep convolutional neural network,” Knowledge-Based Syst., 108: 42-49, 2016. [16] L. Zhao, L. Li, X. Zheng, J. Zhang, "A BERT based sentiment analysis and key entity detection approach for online financial texts," in Proc. CSCWD 2021: 1233-1238, 2021. [17] Z. Li, Y. Song, X. Lu, M. Liu, “Twin towers end to end model for aspect-based sentiment analysis,” Expert Syst. Appl., 249, 2024. [18] Q. Wan et al., “A span-based multi-modal attention network for joint entity-relation extraction,” Knowledge-Based Syst., 262, 2023. [19] A. Thomas et al., “Investigating the impact of pre-trained word embeddings on memorization in neural networks,” in Proc. Text, Speech, and Dialogue, Lecture Notes in Computer Science, 2020. [20] C. Wang et al., “A comparative study on word embeddings in deep learning for text classification,” in Proc. 4th Int. Conf. Natural Language Processing and Information Retrieva: 37-46, 2021. [21] K. Cho et al.,“On the properties of neural machine translation: encoder-decoder approaches,” in Proc. English Workshop on Syntax, Semantics and Structures in Statistical Translation, 2014. [22] J. Chung, C. Gulcehre, K. Cho, Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,” Workshop on Deep Learning, 2014. [23] J. Devlin et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1: 4171-4186, 2019. [24] D. E. Rumelhart, J. L. McClelland, "Learning internal representations by error propagation," in Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations, MIT Press, 318-362, 1987. [25] P. He, X. Liu, J. Gao, W. Chen, “DeBERTa: Decoding enhanced BERT with Disentangled Attention,” in Proc. ICLR, 2021. [26] H. Dalianis, “Evaluation metrics and evaluation,” Clinical Text Mining, Springer, Cham, 2018. [27] Y. Yang, M. C. Uy, A. Huang, “FinBert: A pretrained language model for financial communications,” arXiv:2006.08097, 2020. [28] C. Sutton, A. McCallum, “An introduction to conditional random fields,” Found. Trends Mach. Learn., 4(4): 267-373, 2011. [29] U. Lee et al., “Few-shot is enough: exploring ChatGPT prompt engineering method for automatic question generation in English education,” Educ. Inf. Technol., 29: 11483-11515, 2024. [30] F. H. Shubho et al., “ChatGPT-guided Semantics for Zero-shot Learning,” in Proc. 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA): 418-425, 2023.
آمار تعداد مشاهده مقاله: 37 تعداد دریافت فایل اصل مقاله: 12

سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب

پیوندهای مفید

پیوندهای مفید

اخبار و اعلانات

آمار

Enhancing Multi-Entity Detection and Sentiment Analysis in Financial Texts with Hierarchical Attention Networks