تشخيص موضع به زبان فارسی مبتنی بر طبقه بندهای چندگانه
محورهای موضوعی : فناوری اطلاعات و ارتباطاتمژگان فرهودی 1 * , عباس طلوعی اشلقی 2
1 - عضو هیات علمی
2 - دانشگاه آزاد اسلامی واحد علوم و تحقیقات
کلید واژه: تشخیص موضع, طبقه بند چندگانه, يادگيری ماشين, يادگيری عميق, يادگيری انتقالی.,
چکیده مقاله :
تشخيص موضع (که با عناوبن طبقهبندي موضع، تحليل موضع يا پيشبيني موضع نيز شناخته شده است) يک موضوع تحقيقاتي اخير است که به يک پارادايم نوظهور تبديل شده است. هدف از تشخيص موضع، شناسايي موضع نويسنده نسبت به يک موضوع يا ادعاي خاص بوده که به جزء کليدي کاربردهايي مانند تشخيص اخبار جعلي، اعتبارسنجي ادعا يا جستجوي استدلال تبديل شده است. در اين مقاله از سه رويکرد يادگيري ماشين، يادگيري عميق و يادگيري انتقالي براي تشخيص موضع فارسي استفاده شده و سپس با بکارگيری طبقهبندهای چندگانه، مدلی برای اخذ تصميم نهايي در مورد نتايج خروجي پيشنهاد گرديده است. برای اين منظور از روش اکثريت آرا مبتنی بر صحت طبقهبندهای انفرادی براي ترکيب نتايج آنها استفاده گرديد. نتايج آزمايشها نشان داد که عملکرد مدل پيشنهادي نسبت به عملکرد طبقهبندهای انفرادی پيشرفت مناسبی داشته است.
Stance detection (also known as stance classification, stance prediction, and stance analysis) is a recent research topic that has become an emerging paradigm of the importance of opinion-mining. The purpose of stance detection is to identify the author's viewpoint toward a specific target, which has become a key component of applications such as fake news detection, claim validation, argument search, etc. In this paper, we applied three approaches including machine learning, deep learning and transfer learning for Persian stance detection. Then we proposed a framework of multi-classifier fusion for getting final decision on output results. We used a weighted majority voting method based on the accuracy of the classifiers to combine their results. The experimental results showed the performance of the proposed multi-classifier fusion method is better than individual classifiers.
[1] Sobhani, P. (2017). Stance detection and analysis in social media, Ph.D. dissertation, Universite d’Ottawa/University of Ottawa.
[2] Kucuk, D., & Can, F. (2022, February). A Tutorial on Stance Detection. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (pp. 1626-1628).
[3] Schiller, B., Johannes, D., Iryna G. (2021). Stance detection benchmark: How robust is your stance detection? KI-Künstliche Intelligenz, 35 (3), (pp. 329-341)
[4] Du, J., Xu, R., He, Y., & Gui, L. (2017, August). Stance classification with target-specific neural attention networks. International Joint Conferences on Artificial Intelligence.
[5] Lai, M., Cignarella, A. T., Farías, D. I. H., Bosco, C., Patti, V., & Rosso, P. (2020). Multilingual stance detection in social media political debates. Computer Speech & Language, 63, 101075.
[6] Zotova, E., Agerri, R., Nuñez, M., & Rigau, G. (2020, May). Multilingual stance detection in tweets: The Catalonia independence corpus. In Proceedings of the 12th Language Resources and Evaluation Conference (pp. 1368-1375).
[7] Swami, S., Khandelwal, A., Singh, V., Akhtar, S. S., & Shrivastava, M. (2018). An english-hindi code-mixed corpus: Stance annotation and baseline system. arXiv preprint arXiv:1805.11868.
[8] Darwish, K., Magdy, W., & Zanouda, T. (2017, September). Trump vs. Hillary: What went viral during the 2016 US presidential election. In International conference on social informatics (pp. 143-161). Springer, Cham.
[9] Li, Y., He, H., Wang, S., Lau, F., & Song, Y. (2022). Improved Target-specific Stance Detection on Social Media Platforms by Delving into Conversation Threads. arXiv preprint arXiv:2211.03061.
[10] Derczynski, L., Bontcheva, K., Liakata, M., Procter, R., Hoi, G. W. S., & Zubiaga, A. (2017). SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours. arXiv preprint arXiv:1704.05972.
[11] Yuan, C., Qian, W., Ma, Q., Zhou, W., & Hu, S. (2021, July). SRLF: a stance-aware reinforcement learning framework for content-based rumor detection on social media. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
[12] Bar-Haim, R., Bhattacharya, I., Dinuzzo, F., Saha, A., & Slonim, N. (2017, April). Stance classification of context-dependent claims. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers (pp. 251-261).
[13] Wojatzki, M., & Zesch, T. (2016, June). ltl. uni-due at semeval-2016 task 6: Stance detection in social media using stacked classifiers. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016) (pp. 428-433).
[14] Cignarella, A. T., Lai, M., Bosco, C., Patti, V., & Paolo, R. (2020). Sardistance@ evalita2020: Overview of the task on stance detection in italian tweets. EVALITA 2020 Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian, 1-10.
[15] Wei, P., Lin, J., & Mao, W. (2018, June). Multi-target stance detection via a dynamic memory-augmented network. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval (pp. 1229-1232).
[16] Tutek, M., Sekulić, I., Gombar, P., Paljak, I., Čulinović, F., Boltužić, F., ... & Šnajder, J. (2016, June). Takelab at semeval-2016 task 6: Stance classification in tweets using a genetic algorithm based ensemble. In Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016) (pp. 464-468).
[17] Zarharan, M., Ahangar, S., Rezvaninejad, F. S., Bidhendi, M. L., Pilevar, M. T., Minaei, B., & Eetemadi, S. (2019). Persian Stance Classification Data Set. In TTO.
[18] Umer, M., Imtiaz, Z., Ullah, S., Mehmood, A., Choi, G. S., & On, B. W. (2020). Fake news stance detection using deep learning architecture (CNN-LSTM). IEEE Access, 8, 156695-156706.
[19] Vaswani, A., Bengio, S., Brevdo, E., Chollet, F., Gomez, A. N., Gouws, S., ... & Uszkoreit, J. (2018). Tensor2tensor for neural machine translation. arXiv preprint arXiv:1803.07416.
[20] Nasiri, H., & Analoui, M. (2022, February). Persian Stance Detection with Transfer Learning and Data Augmentation. In 2022 27th International Computer Conference, Computer Society of Iran (CSICC) (pp. 1-5). IEEE.
[21] Karande, H., Walambe, R., Benjamin, V., Kotecha, K., & Raghu, T. S. (2021). Stance detection with BERT embeddings for credibility analysis of information on social media. PeerJ Computer Science, 7, e467.
[22] Vychegzhanin, S., & Kotelnikov, E. (2021). A New Method for Stance Detection Based on Feature Selection Techniques and Ensembles of Classifiers. IEEE Access, 9, 134899-134915.
[23] Lozhnikov, N., Derczynski, L., & Mazzara, M. (2018, June). Stance prediction for russian: data and analysis. In International Conference in Software Engineering for Defence Applications (pp. 176-186). Springer, Cham.
[24] Cignarella, A. T., Lai, M., Bosco, C., Patti, V., & Paolo, R. (2020). Sardistance@ evalita2020: Overview of the task on stance detection in italian tweets. EVALITA 2020 Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian, 1-10.
[25] Mi, A., Wang, L., & Qi, J. (2016). A multiple classifier fusion algorithm using weighted decision templates. Scientific Programming, 2016.
[26] Liang, S. Y., Han, D. Q., & Han, C. Z. (2014). A novel diversity measure based on geometric relationship and its application to design of multiple classifier systems. Acta Automatica Sinica, 40(3), 449-458.
[27] Darwish, K., Stefanov, P., Aupetit, M., & Nakov, P. (2020, May). Unsupervised user stance detection on twitter. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 14, pp. 141-152).
[28] Rashed, A., Kutlu, M., Darwish, K., Elsayed, T., & Bayrak, C. (2021, May). Embeddings-based clustering for target specific stances: The case of a polarized turkey. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 15, pp. 537-548).
[29] Chen, S., Lu, X., Chen, X., Chen, M., Chen, J., Wang, D., & Zhu, S. (2020). Object Tracking with Multi-Classifier Fusion Based on Compressive Sensing and Multiple Instance Learning. Mathematical Problems in Engineering, 2020.
[30] Bagheri, M. A., Hu, G., Gao, Q., & Escalera, S. (2014, August). A framework of multi-classifier fusion for human action recognition. In 2014 22nd International Conference on Pattern Recognition (pp. 1260-1265). IEEE.
[31] Pan, Y., Zhang, L., Wu, X., & Skibniewski, M. J. (2020). Multi-classifier information fusion in risk analysis. Information Fusion, 60, 121-136.
[32] Huang, J. T., Wang, M. H., Li, W. J., & Gu, B. (2012). Multiple classifier fault diagnosis system based on dynamic weight. ACTA ELECTONICA SINICA, 40(4), 734.
[33] Yu, Z., Nam, M. Y., Sedai, S., & Rhee, P. K. (2009). Evolutionary fusion of a multi-classifier system for efficient face recognition. International Journal of Control, Automation and Systems, 7(1), 33-40.
[34] Maharana, K., Mondal, S., & Nemade, B. (2022). A Review: Data Pre-Processing and Data Augmentation Techniques. Global Transitions Proceedings.
[35] Qader, W. A., Ameen, M. M., & Ahmed, B. I. (2019, June). An overview of bag of words; importance, implementation, applications, and challenges. In 2019 International Engineering Conference (IEC) (pp. 200-204). IEEE.
[36] Aizawa, A. (2003). An information-theoretic perspective of tf–idf measures. Information Processing & Management, 39(1), 45-65.
[37] d'Sa, A. G., Illina, I., & Fohr, D. (2020, February). Bert and fasttext embeddings for automatic detection of toxic speech. In 2020 International Multi-Conference on:“Organization of Knowledge and Advanced Technologies”(OCTA) (pp. 1-5). IEEE.
[38] Joulin, A., Grave, E., Bojanowski, P., Douze, M., Jégou, H., & Mikolov, T. (2016). Fasttext. zip: Compressing text classification models. arXiv preprint arXiv:1612.03651.
[39] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
[40] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
[41] Farahani, M., Gharachorloo, M., Farahani, M., & Manthouri, M. (2021). Parsbert: Transformer-based model for persian language understanding. Neural Processing Letters, 53(6), 3831-3847.
[42] Kuncheva, L. I. (2014). Combining pattern classifiers: methods and algorithms. John Wiley & Sons.
[43] Moreno-Seco, F., Inesta, J. M., León, P. J., & Micó, L. (2006, August). Comparison of classifier fusion methods for classification in pattern recognition tasks. In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) (pp. 705-713). Springer, Berlin, Heidelberg.
[44] Du, P., Xia, J., Zhang, W., Tan, K., Liu, Y., & Liu, S. (2012). Multiple classifier system for remote sensing image classification: A review. Sensors, 12(4), 4764-4792.
[45] Kingma, Diederik P., and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980, 2014
[46] Abadi, Martin, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado et al. Tensorow: Largescale machine learning on heterogeneous distributed systems, arXiv preprint arXiv:1603.04467, 2016