ارائه یک روش مبتنی بر شبکه عصبی پشته‌ای حلقوی برای تشخیص شایعه در شبکه‌های اجتماعی

ایزدخواه, حبیب; بهزادی دوست, رشید

doi:10.22052/scj.2024.253314.1172

ارائه یک روش مبتنی بر شبکه عصبی پشته‌ای حلقوی برای تشخیص شایعه در شبکه‌های اجتماعی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده ریاضی، آمار و علوم کامپیوتر، دانشگاه تبریز، تبریز، ایران.

10.22052/scj.2024.253314.1172

چکیده

امروزه شبکه‌های اجتماعی به عنوان یک ابزار مفید و پراستفاده شناخته می‌شوند. اگرچه جنبه‌های مثبت زیادی همانند تجارت الکترونیک، سرگرمی، افزایش آگاهی و ارتباط جهانی از طریق شبکه‌های اجتماعی وجود دارد، اما وجود شایعات جنبه منفی شبکه‌های اجتماعی است. با کمترین تلاش، یک شایعه می‌تواند به سرعت برای بسیاری از کاربران منتشر شود و منجر به پدیده‌های ناخوشایند اجتماعی شود. در کارهای قبلی، مدل‌هایی مبتنی بر یادگیری ماشین و یادگیری عمیق برای تشخیص خودکار شایعات ارائه شده است. در این مقاله، ما یک مدل چند شبکه عصبی پشته‌ای حلقوی را برای تشخیص شایعات در شبکه‌های اجتماعی ارائه می‌دهیم. از تمامی شبکه عصبی پیچشی پشته‌ای-شبکه عصبی حافظه طولانی کوتاه مدت دوجهته یک ماتریس پیچشی ایجاد می‌شود و سپس از پیچش ایجاد شده، حالت حلقوی ایجاد می‌شود. این مدل یادگیری عمیق فقط متن کاربران شبکه‌های اجتماعی را در نظر می‌گیرد و تشخیص می‌دهد آیا آن متن شایعه است یا خیر. ما مدل پیشنهادی را بر روی مجموعه داده‌های واقعی PHEME و Liar ارزیابی کرده‌ایم. مدل پیشنهادی نسبت به دوازده مدل یادگیری ماشین و یادگیری عمیق از لحاظ دقت بهتر عمل می‌کند.

کلیدواژه‌ها

موضوعات

پردازش زبان طبیعی

عنوان مقاله [English]

Circular multi stacked CNN-BILSTM for rumor detection in social networks

نویسندگان [English]

Habib Izadkhah
Rashid Behzadidoost

Department of Computer Science, University of Tabriz, Tabriz, Iran.

چکیده [English]

Nowadays social networks have emerged as a popular platform for communication, entertainment, news and event updates, and more. While social networks offer several benefits such as e-commerce and easy communication, the presence of rumors is a significant drawback. Rumors can spread quickly to many users with minimal effort and lead to unpleasant social phenomena. In previous works, researchers have proposed machine learning and deep learning approaches for automatic rumor detection. This paper proposes a circular multi-layered CNN-BILSTM model for rumor detection in social networks. The model transforms the multi CNN-BILSTMs into a convolutional matrix and then applies a circular state to the matrix. The model only uses the text of social network users and classifies it as rumor or non-rumor. We tested the model on the real public dataset of PHEME and Liar. The model outperforms twelve state-of-the-art models in terms of accuracy.

کلیدواژه‌ها [English]

Natural Language Processing
Deep Learning
Rumor Detection
Neural network
Social network

مراجع

[1] R. Behzadidoost, M. Hasheminezhad, M. Farshi, V. Derhami, and F. Alamiyan-Harandi, “A framework for text mining on twitter: A case study on joint comprehensive plan of action (jcpoa)-between 2015 and 2019,” Qual. Quant., pp. 1-32, 2021, doi: 10.1007/s11135-021-01239-y.
[2] A. Rapp, L.S. Beitelspacher, D. Grewal, and D.E. Hughes, “Understanding social media effects across seller, retailer, and consumer interactions,” J. Acad. Market. Sci., vol. 41, no. 5, pp. 547-566, 2013.
[3] A. Bondielli and F. Marcelloni, “A survey on fake news and rumour detection techniques,” Inf. Sci., vol. 497, pp. 38-55, 2019, doi: 10.1007/s11747-013-0326-9.
[4] O. Sagi and L. Rokach, “Ensemble learning: A survey,” Wiley Interdiscipl. Rev.: Data Mining Knowl. Discovery, vol. 8, no. 4, p. e1249, 2018, doi: 10.1002/widm.1249.
[5] T. Lehinevych and H. Andii, “Analysis of Deep Metric Learning Approaches,” in Proc. IEEE Int. Conf. Adv. Trends Inf. Theory (ATIT), 2019, pp. 369-372, doi: 10.1109/ATIT49449.2019.9030440.
[6] C. Kuhnert, M. Baruthio, T. Bernard, C. Steinmetz, and J.-M. Weber, “Cloud-based event detection platform for water distribution networks using machine-learning algorithms,” Procedia Eng., vol. 119, pp. 901-907, 2015, doi: 10.1016/j.proeng.2015.08.963.
[7] W.F. Lamberti, “An overview of explainable and interpretable AI,” in AI Assurance, 2023, pp. 55-123, doi: 10.1016/B978-0-32-391919-7.00015-9.
[8] T. Dietterich, “Overfitting and undercomputing in machine learning,” ACM Comput. Surv., vol. 27, no. 3, pp. 326-327, 1995, doi: 10.1145/212094.212114.
[9] Y. Tan, “An improved KNN text classification algorithm based on K-medoids and rough set,” in Proc. 10th Int. Conf. Intell. Human-Mach. Syst. Cybern. (IHMSC), 2018, vol. 1, pp. 109-113, doi: 10.1109/IHMSC.2018.00032.
[10] M. Goudjil, M. Koudil, M. Bedda, and N. Ghoggali, “A novel active learning method using SVM for text classification,” Int. J. Autom. Comput., vol. 15, pp. 290-298, 2018, doi: 10.1007/s11633-015-0912-z.
[11] A. Bouaziz, C. Dartigues-Pallez, C. da Costa Pereira, F. Precioso, and P. Lloret, “Short text classification using semantic random forest,” in Data Warehous. Knowl. Discov. (DaWaK), 2014, pp. 288-299, doi: 10.1007/978-3-319-10160-6_26.
[12] S. Wang, L. Jiang, and C. Li, “Adapting naive Bayes tree for text classification,” Knowl. Inf. Syst., vol. 44, pp. 77-89, 2015, doi: 10.1007/s10115-014-0746-y.
[13] M.-R. Feizi-Derakhshi, Z. Mottaghinia, and M. Asgari-Chenaghlu, “Persian Text Classification Based on Deep Neural Networks,” Soft Comput. J., vol. 11, no. 1, pp. 120-139, 2022, doi: 10.22052/SCJ.2023.243182.1010 [In Persian].
[14] N. Majma and S. Bashtin, “Detection of plagiarism in scientific texts based on text blocking and cosine similarity criteria,” Soft Comput. J., vol. 11, no. 1, pp. 60-71, 2022, doi: 10.22052/SCJ.2022.243384.1034 [In Persian].
[15] F. Zare Mehrjardi, M. Yazdian-Dehkordi, and A. Latif, “Evaluating Machine learning and Deep-learning methods in Sentiment Analysis on Persian Telegram Message,” Soft Comput. J., vol. 11, no. 1, pp. 88-105, 2022, doi: 10.22052/SCJ.2023.246553.1077 [In Persian].
[16] R. Behzadidoost, F. Mahan, and H. Izadkhah, “Granular computing-based deep learning for text classification,” Inf. Sci., vol. 652, p. 119746, 2024, doi: 10.1016/j.ins.2023.119746.
[17] J. Ma et al., “Detecting rumors from microblogs with recurrent neural networks,” in Proc. 25th Int. Joint Conf. Artif. Intell. (IJCAI), 2016, pp. 3818-3824.
[18] A. Kumar, V. Singh, T. Ali, S. Pal, and J. Singh, “Empirical evaluation of shallow and deep classifiers for rumor detection,” Adv. Comput. Intell. Syst., pp. 239-252, 2020, doi: 10.1007/978-981-15-0222-4_21.
[19] N. Ruchansky, S. Seo, and Y. Liu, “Csi: A hybrid deep model for fake news detection,” in Proc. 2017 ACM Conf. Inf. Knowl. Manage., 2017, pp. 797-806, doi: 10.1145/3132847.3132877.
[20] A.S. Torshizi and A. Ghazikhani, “Automatic Twitter rumor detection based on LSTM classifier,” High-Perform. Comput. Big Data Anal., pp. 291-300, 2019, doi: 10.1007/978-3-030-33495-6_22.
[21] T.T. Nguyen et al., “Judo: Just-in-time rumour detection in streaming social platforms,” Inf. Sci., vol. 570, pp. 70-93, 2021, doi: 10.1016/j.ins.2021.04.018.
[22] F. Xu, V.S. Sheng, and M. Wang, “Near real-time topic-driven rumor detection in source microblogs,” Knowl.-Based Syst., vol. 207, p. 106391, 2020, doi: 10.1016/j.knosys.2020.106391.
[23] Z. Wu, D. Pi, J. Chen, M. Xie, and J. Cao, “Rumor detection based on propagation graph neural network with attention mechanism,” Expert Syst. Appl., vol. 158, p. 113595, 2020, doi: 10.1016/j.eswa.2020.113595.
[24] P. Zhang, H. Ran, C. Jia, X. Li, and X. Han, “A lightweight propagation path aggregating network with neural topic model for rumor detection,” Neurocomputing, vol. 458, pp. 468-477, 2021, doi: 10.1016/j.neucom.2021.06.062.
[25] H. Zhou et al., “MDMN: Multi-task and Domain Adaptation based Multi-modal Network for early rumor detection,” Expert Syst. Appl., vol. 195, p. 116517, 2022, doi: 10.1016/j.eswa.2022.116517.
[26] B. Liu et al., “Nowhere to hide: Online rumor detection based on retweeting graph neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 4, pp. 4887-4898, 2022, doi: 10.1109/TNNLS.2022.3161697.
[27] H. Ran, C. Jia, P. Zhang, and X. Li, “MGAT-ESM: Multi-channel graph attention neural network with event-sharing module for rumor detection,” Inf. Sci., vol. 592, pp. 402-416, 2022, doi: 10.1016/j.ins.2022.01.036.
[28] X. Chen, F. Zhou, G. Trajcevski, and M. Bonsangue, “Multi-view learning with distinguishable feature fusion for rumor detection,” Knowl.-Based Syst., vol. 240, p. 108085, 2022, doi: 10.1016/j.knosys.2021.108085.
[29] P. Zheng, Z. Huang, Y. Dou, and Y. Yan, “Rumor detection on social media through mining the social circles with high homogeneity,” Inf. Sci., vol. 642, p. 119083, 2023, doi: 10.1016/j.ins.2023.119083.
[30] W. Cui and M. Shang, “KAGN: knowledge-powered attention and graph convolutional networks for social media rumor detection,” J. Big Data, vol. 10, no. 1, p. 45, 2023, doi: 10.1186/s40537-023-00725-4.
[31] Z. Guo et al., “Mixed graph neural network-based fake news detection for sustainable vehicular social networks,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 12, pp. 15486-15498, 2022, doi: 10.1109/TITS.2022.3185013.
[32] H. Han, Z. Ke, X. Nie, L. Dai, and W. Slamu, “Multimodal Fusion with Dual-Attention Based on Textual Double-Embedding Networks for Rumor Detection,” Appl. Sci., vol. 13, no. 8, p. 4886, 2023, doi: 10.3390/app13084886.
[33] H. Yuan, Y. Chen, X. Hu, and S. Ji, “Interpreting deep models for text analysis via optimization and regularization methods,” in Proc. AAAI Conf. Artif. Intell., 2019, vol. 33, no. 01, pp. 5717-5724, doi: 10.1609/aaai.v33i01.33015717.
[34] M. Cassel and F. Lima, “Evaluating one-hot encoding finite state machines for SEU reliability in SRAM-based FPGAs,” in Proc. 12th IEEE Int. On-Line Test. Symp. (IOLTS), 2006, p. 6, doi: 10.1109/IOLTS.2006.32.
[35] Y. Goldberg and O. Levy, “word2vec Explained: deriving Mikolov et al.’s negative-sampling word-embedding method,” arXiv preprint arXiv:1402.3722, 2014.
[36] J. Pennington, R. Socher, and C.D. Manning, “Glove: Global vectors for word representation,” in Proc. Conf. Empirical Methods Nat. Lang. Process. (EMNLP), 2014, pp. 1532-1543.
[37] A. Fidalgo, I. Medeiros, P. Antunes, and N. Neves, “Towards a deep learning model for vulnerability detection on web application variants,” in Proc. 2020 IEEE Int. Conf. Softw. Test. Verif. Valid. Worksh. (ICSTW), 2020, pp. 465-476, doi: 10.1109/ICSTW50294.2020.00083.
[38] R.J. Williams and D. Zipser, “Gradient-based learning algorithms for recurrent,” Backpropag. Theory Arch. Appl., vol. 433, p. 17, 1995.
[39] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825-2830, 2011.
[40] N. Ketkar, “Introduction to keras,” in Deep learning with python: a hands-on introduction, 2017, pp. 97-111, doi: 10.1007/978-1-4842-2766-4_7.
[41] W.Y. Wang, “’Liar, liar pants on fire’: A new benchmark dataset for fake news detection,” arXiv preprint arXiv:1705.00648, 2017, doi: 10.18653/v1/P17-2067.
[42] Y. Kim, “Convolutional neural networks for sentence classification,” arXiv preprint arXiv:1408.5882, 2014, doi: 10.3115/v1/D14-1181.
[43] S. Lai, L. Xu, K. Liu, and J. Zhao, “Recurrent convolutional neural networks for text classification,” in Proc. AAAI Conf. Artif. Intell., 2015, vol. 29, no. 1.
[44] J. Ma, W. Gao, Z. Wei, Y. Lu, and K.-F. Wong, “Detect rumors using time series of social context information on microblogging websites,” in Proc. 24th ACM Int. Conf. Inf. Knowl. Manage., 2015, pp. 1751-1754, doi: 10.1142/9789813223615_0006.