رویکرد ارزیابی هیجان نوین جهت مراقبت از سرطان مبتنی بر مدل‌های زبانی بزرگ

محورهای موضوعی : مهندسی برق و کامپیوتر

نفیسه فارغ زاده ¹ , محمد قبادی ² , پریسا رحمانی ³ , مهدی بازرگانی ⁴

1 - دانشكده كامپيوتر، واحد خدابنده، دانشگاه آزاد اسلامی، خدابنده، ایران
2 - دانشكده كامپيوتر، واحد الکترونیک، دانشگاه آزاد اسلامی، تهران، ايران
3 - دانشكده كامپيوتر، واحد پردیس، دانشگاه آزاد اسلامی، تهران، ايران،
4 - دانشكده كامپيوتر، واحد زنجان، دانشگاه آزاد اسلامی، زنجان، ايران

تاریخ دریافت : 1404/07/29 تاریخ پذیرش : 1404/11/28 تاریخ انتشار : 1405/02/22

کلید واژه: پردازش زبان طبیعی, تحلیل هیجانات, سرطان, مدل‌های زبان بزرگ, یادگیری عمیق,

چکیده مقاله :

پژوهش حاضر، در راستایرفع دغدغه و مواجهه با چالش کمبود ابزارهای تخصصی بومی در حوزه تحلیل هیجانات بیماران سرطانی و با هدف ارائه یک سیستم نوین برای ارزیابی هیجانات این بیماران آغاز شده است. هدف اصلی این مطالعه، طراحی و پیاده‌سازی یک سیستم ترکیبی مبتنی بر یادگیری عمیق برای شناسایی حضور یک یا چند هیجان به صورت همزمان از میان شش دسته هیجانی (شادی، غم، خشم، ترس، امید، ناامیدی)، در متون فارسی شبکه‌های اجتماعی است. این رویکرد نوین امکان درک بهتر پیچیدگی و هم‌زمانی هیجانات را فراهم می‌نماید. به این منظور، مجموعه‌ای شامل ۱۰,۰۰۰ پست مرتبط با سرطان از پلتفرم‌های اجتماعی برچسب‌گذاری شد. مدل پیشنهادی که از تلفیق هوشمندانه مدل زبان بزرگ بومیParsBERT با شبکه Bi-GRU بهره می‌برد، برای این وظیفه تنظیم دقیق گردید. نتایج ارزیابی، دستاورد قابل توجه این پژوهش را به وضوح نشان می‌دهد؛ روش پیشنهادی به دقت 8_/86% و معیار -Score1 Fمیانگین ۸۴% دست یافت. سیستم پیشنهادی، بهبودی معادل ۲_/۳% در دقت نسبت به مدل‌های پایه نشان داد. سیستم در تشخیص هیجانات پرتکرار مانند غم با معیار -Score1 Fمعادل ۹۲% و ناامیدی با معیار -Score1 Fمعادل ۹۰%، عملکردی موثر و ابزاری خودکار و قدرتمند برای پایش هیجانات بیماران سرطانی و مداخلات روان درمانی موثرتر ارائه می‌دهد.

چکیده انگلیسی:

This research initiated to address the concern and challenge of the lack of specialized native tools in the field of emotion analysis in cancer patients and to provide a new system for assessing the emotions of these patients. The main goal of this study was to design and implement a hybrid system based on deep learning to identify the presence of one or more emotions simultaneously from six emotional categories (happiness, sadness, anger, fear, hope, despair) in Persian texts on social networks. This new approach allows for a better understanding of the complexity and simultaneity of emotions. For this purpose, a set of 10,000 cancer-related posts from social platforms was tagged. The proposed model, which uses the intelligent integration of the large native language model ParsBERT with the Bi-GRU network, was fine-tuned for this task. The evaluation results clearly demonstrate the remarkable achievement of this research; the proposed method achieved an accuracy of 86.8% and an average F1-Score of 84%. The proposed system showed an improvement of 2.3% in accuracy compared to the baseline models. The system performs effectively in detecting frequent emotions such as sadness with an F1-Score of 92% and despair with an F1-Score of 90%, providing an automated and powerful tool for monitoring the emotions of cancer patients and more effective psychotherapy interventions.

منابع و مأخذ:

[1] B. Pang and L. Lee, "Opinion mining and sentiment analysis," Foundations and Trends in Information Retrieval, vol. 2, no. 1-2, pp. 1-135, 2008.
[2] J. Winman, "Health psychology," Journal of Philosophy and Theology, vol. 9, no. 33-34, pp. 109-129, May 2004.
[3] R. S. Lazarus and S. Folkman, Stress, Appraisal, and Coping, Springer Publishing Company, 1984.
[4] A. Krebber, et al., "Prevalence of depression in cancer patients: A meta‐analysis of diagnostic interviews and self‐report instruments," Psycho‐Oncology, vol. 23, no. 2, pp. 121-130, Feb. 2014.
[5] C. Strapparava, "WordNet-Affect: an affective extension of WordNet," in Proc. of the 4th Int. Conf. on Language Resources and Evaluation, pp. 1083-1086, Lisbon, Portugal, 26-28 May 2004.
[6] S. Baccianella, A. Esuli, and F. Sebastiani, "Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining," in Proc. of the 7th Int. Conf. on Language Resources and Evaluation, pp. 2200-2204, Valletta, Malta, 17-23 May 2010.
[7] D. Seal, U. Roy, and R. Basak, "Sentence-level emotion detection from text Based on semantic rules," in Information and Communication Technology for Sustainable Development, Advances in Intelligent Systems and Computing, vol. 933, pp. 423-430, Jul. 2020.
[8] M. Bazargani, N. Fareghzadeh, M. Afzali, S. Karimi, "A hybrid cumulative knowledge framework for friend recommendation in social networks", International Journal of Nonlinear Analysis and Applications, vol. 17, no. 1, pp. 43-54, Jan. 2026.
[9] L. Wikarsa and S. N. Thahir, "A text mining application of emotion classifications of Twitter's users using Naïve Bayes method," in Proc. 1st. Int. Conf. on Wireless and Telematics, 6 pp., Manado, Indonesia, 17-18 Nov. 2015.
[10] A. Yazdani, et al., "Use of sentiment analysis for capturing hospitalized cancer patients' experience from free-text comments in the Persian language." BMC Medical Informatics and Decision Making, vol. 23, no. 1, Article ID: 275, Dec. 2023.
[11] Y. K. Meena, P. M. Kumar, V. V. Kumar., "Classification of online patient reviews based on effectiveness using machine learning algorithms," in Proc. 3rd Int. Conf. on Trends in Electronics and Informatics, pp. 838-842, Apr. 2019.
[12] N. Bahrawi., "Sentiment analysis using random forest algorithm-online social media based," Journal of Information Technology and Its Utilization, vol. 2, no. 2, pp. 29-33, Dec. 2019.
[13] L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5-32, Oct. 2001.
[14] س. ذ. هاشمی‌پور، "تشخیص سرطان سینه با استفاده از الگوریتم جنگل تصادفی،" هشتمین کنگره ملی تازه‌های مهندسی برق و کامپیوتر ایران، 6 صص.، تهران، ايران، 28-27 اردیبهشت 1400.
[15] T. M. Cover and P. E. Hart, "Nearest neighbor pattern classification," IEEE Trans. on Information Theory, vol. 13, no. 1, pp. 21-27, Jan. 1967.
[16] A. D. W. Sumari, A. F. Huda, and M. A. Fauzi, "Sentiment analysis of patient’s satisfaction in health services using k-nearest neighbor and Chi-Square," Journal of Computer Science, vol. 17, no. 1, pp. 57-65, Jan. 2021.
[17] ن. فارغ¬زاده، م. بازرگانی ن. جعفری، "تشخیص سرطان سینه با استفاده از الگوریتم جنگل تصادفی،" اسلام شناسی و قرآن پژوهی در جهان معاصر، شناسه مقاله: e734628، بهمن 1404.
[18] T. Young, D. Hazarika, S. Poria, and E. Cambria, "Recent trends in deep learning based natural language processing," IEEE Computational Intelligence Magazine, vol. 13, no. 3, pp. 55-75, Aug. 2018.
[19] Y. Kim, "Convolutional neural networks for sentence classification," in Proc. of the 2014 Conf. on Empirical Methods in Natural Language Processing, pp. 1746-1751, Doha, Qatar, 25-29 Oct. 2014.
[20] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, Nov. 1997. [21] K. Cho, et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation in Proc. of the Conf. on Empirical Methods in Natural Language Processing, pp. 1724-1734, Doha, Qatar, 25-29 Oct. 2014.
[22] C. Wang, J. Yang, M. Yu, L. Lv, and X. Wang, "A hybrid CNN-LSTM model for sentiment analysis of online reviews," in Proc. of the 12th Int. Conf. on Intelligent Computation Technology and Automation, pp. 248-252, Xiangtan, China, 26-27 Oct. 2019.
[23] B. K. Crannell, E. Clark, C. C. Jones, and D. G. T. III, "Characterizing cancer-related patient-reported comments on Twitter," in Proc. of the IEEE Int. Conf. on Healthcare Informatics, pp. 526-532, Chicago, IL, USA, 4-7 Oct. 2016.
[24] A. C. Sosea and C. Caragea, "CancerEmo: A dataset for fine-grained emotion detection," in Proc. of the 28th Int. Conf. on Computational Linguistics, pp. 5987-6000, Barcelona, Spain, 8-13 Dec. 2020.
[25] A. Vaswani, et al., "Attention is all you need," in Proc. of the 31st Annual Conf. on Neural Information Processing Systems, pp. 5998-6008, Long Beach, CA, USA, 4-9 Dec. 2017.
[26] J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of deep bidirectional transformers for language understanding," in Proc. of the Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171-4186, Minneapolis, MN, USA, 2-7 Jun. 2019.
[27] A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, "Language models are unsupervised multitask learners," OpenAI Blog, vol. 1, no. 8, 2019.
[28] J. Lee, et al., "BioBERT: a pre-trained biomedical language representation model for biomedical text mining," Bioinformatics, vol. 36, no. 4, pp. 1234-1240, Feb. 2020.
[29] Z. Wang, K. E. Daniel, L. E. Barnes, and P. I. Chow, CALLM: Understanding Cancer Survivors' Emotions and Intervention Opportunities via Mobile Diaries and Context-Aware Language Models, arXiv preprint arXiv:2503.10707, 2025.
[30] H. Guo, Y. Zhang, and J. Luo, “ClinicalBERT for sentiment analysis and entity extraction in electronic health records,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 4, pp. 1821-1832, Apr. 2023.
[31] A. Allam, G. T. Jones, K. E. Stewart, and D. J. L. Jones, "Sentiment analysis of clinical narratives to identify patients with depression and anxiety: A systematic review," JMIR Medical Informatics, vol. 9, no. 7, Article ID: e25860, Jul. 2021.
[32] J. Li, R. Wang, and S. Zhao, "A transformer-based multi-task framework for sentiment analysis in digital health applications," Expert Systems with Applications, vol. 201, Article ID: 117091, Sept. 2022.
[33] H. Sharifi, H. Faili, and M. Asad, "Challenges and opportunities in Persian natural language processing," Journal of Signal and Data Processing, vol. 16, no. 1, pp. 3-28, Mar. 2019.
[34] M. Rasooli, M. Kouhpaee, and O. Fehresti, "Linguistic challenges of Persian-English machine translation," in Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics, pp. 24-33, Avignon, France, 23-27 Apr. 2012.
[35] A. Roshanfekr, M. A. M. Abadi, and S. A. Mirroshandel, "Deep learning for sentiment analysis of Persian texts," in Proc. 3rd Int. Conf. on Web Research, pp. 101-106, Tehran, Iran, 19-20 Apr. 2017.
[36] H. Asgarian, H. S. Aghdasi, and M. H. Sadreddini, "ArmanEmo: A New Dataset for Emotion Detection in Persian Texts," in Proc. of the 5th Int. Conf. on Web Research, pp. 136-141, Tehran, Iran, 24-25 Apr. 2019.
[37] M. Yazdani, A. R. Hamidi, and S. Kohan, "Sentiment analysis of hospitalized patients' comments in Persian using machine learning," Journal of Health and Biomedical Informatics, vol. 10, no. 2, pp. 123-134, Sept. 2023.
[38] S. M. H. Ghavanini, M. R. H. Ghavanini, and A. M. E. Moghadam, "Sentiment analysis of Persian social media texts: A survey," in Proc. of the 26th Int. Computer Conf. Computer Society of Iran, 6 pp., Tehran, Iran, 3-4 Mar. 2021.
[39] E. Bagheri, M. H. Saraee, and F. de la Prieta, "Challenges of sentiment analysis in informal Persian texts: a survey," Artificial Intelligence Review, vol. 55, no. 1, pp. 1-36, Jan. 2022.
[40] H. Sharifi, H. Faili, and M. Asad, "A survey on the state of resources and tools for Persian natural language processing," Journal of Advances in Computer Research, vol. 11, no. 1, pp. 15-32, Feb. 2020.
[41] A. Jafer, "A survey on sentiment analysis for low-resource languages," ACM Trans. on Asian and Low-Resource Language Information Processing, vol. 20, no. 4, Article ID: 65, Jul. 2021.
[42] R. Plutchik, "The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice," American Scientist, vol. 89, no. 4, pp. 344-350, Jul./Aug. 2001.

اشتراک گذاری

آدرس مقاله

رویکرد ارزیابی هیجان نوین جهت مراقبت از سرطان مبتنی بر مدل‌های زبانی بزرگ