Abstract
During the development of social media, there has been a transformation in social communication. Despite their positive applications in social interactions and news spread, it also provides an ideal platform for spreading rumors. Rumors can endanger the security of society in normal or critical situations. Therefore, it is important to detect and verify the rumors in the early stage of their spreading. Many research works have focused on social attributes in the social network to solve the problem of rumor detection and verification, while less attention has been paid to content features. The social and structural features of rumors develop over time and are not available in the early stage of rumor. Therefore, this study presented a content-based model to verify the Persian rumors on Twitter and Telegram early. The proposed model demonstrates the important role of content in spreading rumors and generates a better-integrated representation for each source rumor document by fusing its semantic, pragmatic, and syntactic information. First, contextual word embeddings of the source rumor are generated by a hybrid model based on ParsBERT and parallel CapsNets. Then, pragmatic and syntactic features of the rumor are extracted and concatenated with embeddings to capture the rich information for rumor verification. Experimental results on real-world datasets demonstrated that the proposed model significantly outperforms the state-of-the-art models in the early rumor verification task. Also, it can enhance the performance of the classifier from 2% to 11% on Twitter and from 5% to 23% on Telegram. These results validate the model's effectiveness when limited content information is available.
- [1] . 2018. Detection and resolution of rumours in social media: A survey. ACM Comput. Surv. 51 (2018), 32.
DOI:
https://doi.org/10.1145/3161603Google Scholar
- [2] . 2013. Efficient estimation of word representations in vector space. In Proceedings of the 1st International Conference on Learning and Representation (ICLR’13) - Work. Track Proc., 2013. http://ronan.collobert.com/senna/. (accessed December 29, 2019).Google Scholar
- [3] . 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods of the Natural Language Processors. Association for Computational Linguistics, Stroudsburg, PA, 2014, pp. 1532–1543.
DOI:
https://doi.org/10.3115/v1/D14-1162Google Scholar
Cross Ref
- [4] . 2017. Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5 (2017), 135–146.
DOI:
https://doi.org/10.1162/tacl_a_00051Google Scholar
Digital Library
- [5] . 2011. Information credibility on twitter. In Proceedings of the 20th International Conference on the World Wide Web (WWW’11). ACM Press, New York, 2011, p. 675.
DOI:
https://doi.org/10.1145/1963405.1963500Google Scholar
Digital Library
- [6] . 2012. Automatic detection of rumor on Sina Weibo. In Proceedings of the ACM SIGKDD Workshop on the Minimum Data Semantics (MDS’12). ACM Press, New York, 2012, pp. 1–7.
DOI:
https://doi.org/10.1145/2350190.2350203Google Scholar
Digital Library
- [7] . 2016. Linguistic predictors of rumor veracity on the Internet. In Proceedings of the 24th International MultiConference of Engineers and Computer Scientists (IMECS'16), Vol I. 387--391. http://www.iaeng.org/IMECS2016/.Google Scholar
- [8] . 2010. The psychological meaning of words: LIWC and computerized text analysis methods. J. Lang. Soc. Psychol. 29 (2010), 24–54.
DOI:
https://doi.org/10.1177/0261927X09351676Google Scholar
Cross Ref
- [9] . 2013. Prominent features of rumor propagation in online social media. In Proceedings of the 2013 IEEE 13th International Conference on Data Mining (ICDM’13). IEEE, 2013, pp. 1103–1108.
DOI:
https://doi.org/10.1109/ICDM.2013.61Google Scholar
Cross Ref
- [10] . 2015. False rumors detection on Sina Weibo by propagation structures. In Proceedings of the 2015 IEEE 31st International Conference on Data Engineering (ICDE’15). IEEE, 2015, pp. 651–662.
DOI:
https://doi.org/10.1109/ICDE.2015.7113322Google Scholar
Cross Ref
- [11] . 2018. Rumors detection in Sina Weibo based on text and user characteristics. In Proceedings of the 2018 2nd IEEE Advances in Information and Managing Automated Control Conference (IMCEC’18). IEEE, 2018, pp. 1380–1386.
DOI:
https://doi.org/10.1109/IMCEC.2018.8469468Google Scholar
Cross Ref
- [12] . 2012. Rumor diffusion purpose analysis from social attribute to social content. In Proceedings of the 2015 International Conference on Asian Language Processes (IALP’15), IEEE, 2015, pp. 107–110.
DOI:
https://doi.org/10.1109/IALP.2015.7451543Google Scholar
- [13] . 2015. Enquiring minds. In Proceedings of the 24th International Conference on the World Wide Web (WWW’15). ACM, New York, 2015, pp. 1395–1405.
DOI:
https://doi.org/10.1145/2736277.2741637Google Scholar
Digital Library
- [14] S. Vosoughi. 2015. Automatic detection and verification of rumors on Twitter. https://dspace.mit.edu/handle/1721.1/98553.Google Scholar
- [15] V. Qazvinian, E. Rosengren, D. R. Radev, and Q. Mei. 2011. Rumor has it: Identifying misinformation in microblogs, In Proc. Conf. Empir. Methods Nat. Lang. Process., Association for Computational Linguistics. 1589--1599.Google Scholar
- [16] . 2016. Rumor identification and belief investigation on Twitter. In Proceedings of the 7th Annual Workshop on Computer Approaches to Subjective Sentiment and Social Media Analysis. Association for Computational Linguistics, Stroudsburg, PA, 2016, pp. 3–8.
DOI:
https://doi.org/10.18653/v1/W16-0403Google Scholar
Cross Ref
- [17] . 2016. Arabic rumours identification by measuring the credibility of Arabic tweet content. Int. J. Knowl. Soc. Res. 7 (2016), 72–83.
DOI:
https://doi.org/10.4018/IJKSR.2016040105Google Scholar
Digital Library
- [18] R. Moin, ZU. Rehman, K. Mahmood, M. E. Alzahrani, and M. Q. Saleem. 2018. Framework for rumors detection in social media. Int. J. Adv. Comput. Sci. Appl. 9 (2018), 439--444. https://doi.org/10.14569/IJACSA.2018.090557Google Scholar
- [19] . 2018. All-in-one: Multi-task learning for rumour verification. In Proceedings of the 27th International Conference on Computer Linguistics (2018), pp. 3402–3413.Google Scholar
- [20] . 2017. Exploiting context for rumour detection in social media. In Proceedings of the International Conference on Social Informatics. Springer, 2017, pp. 109–123.Google Scholar
Cross Ref
- [21] . 2019. Rumour veracity detection on Twitter using particle swarm optimized shallow classifiers. Multimed. Tools Appl. 78 (2019), 24083–24101.Google Scholar
Digital Library
- [22] . 2019. Early detection of rumor veracity in social media. In Proceedings of the 52nd Hawaii International Conference on System Science, 2019.Google Scholar
Cross Ref
- [23] . 2017. Rumor detection for Persian Tweets. In Proceedings of the 2017 25th Iranian Conference on Electrical Engineering (ICEE’17), 2017, pp. 1532–1536.
DOI:
https://doi.org/10.1109/IranianCEE.2017.7985287Google Scholar
Cross Ref
- [24] S. D. Mahmoodabad, S. Farzi, and D. B. Bakhtiarvand. 2018. Persian rumor detection on Twitter. In Proceedings of the 9th International Symposium on Telecommunications (IST'18). 597--602.
DOI: 10.1109/ISTEL.2018.8661007Google Scholar - [25] , Persian Stance Classification Dataset, (n.d.).Google Scholar
- [26] . 2020. A speech act classifier for Persian texts and its application in identifying rumors. J. Soft Comput. Inf. Technol. (JSCIT) Vol. 9 (2020).Google Scholar
- [27] . 2020. A model to measure the spread power of rumors. ArXiv Prepr. ArXiv2002.07563. (2020).Google Scholar
- [28] . 2019. Jointly embedding the local and global relations of heterogeneous graph for rumor detection. In Proceedings of the 2019 IEEE International Conference on Data Mining. IEEE, 2019, pp. 796–805.Google Scholar
Cross Ref
- [29] . 2011. Rumor has it: Identifying misinformation in microblogs. In Proceedings of the Conference on Empirical Methods, Natural Language Processes. Association for Computational Linguistics, 2011, pp. 1589–1599.Google Scholar
- [30] . 2015. Automatic detection and verification of rumors on Twitter, (2015). https://dspace.mit.edu/handle/1721.1/98553.Google Scholar
- [31] . 2017. Rumor detection for Persian Tweets. In Proceedings of the 2017 Iranian Conference on Electrical Engineering. IEEE, 2017, pp. 1532–1536.
DOI:
https://doi.org/10.1109/IranianCEE.2017.7985287Google Scholar
Cross Ref
- [32] . 2018. Persian rumor detection on Twitter. In Proceedings of the 2018 9th International Symposium on Telecommunications. IEEE, 2018, pp. 597–602.
DOI:
https://doi.org/10.1109/ISTEL.2018.8661007Google Scholar
Cross Ref
- [33] J. Ma, W. Gao, P. Mitra, S. Kwon, B. J. Jansen, K.-F. Wong, and M. Cha. 2016. Detecting rumors from microblogs with recurrent neural networks. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI'16). AAAI Press, 3818--3824.Google Scholar
- [34] F. Yu, Q. Liu, S. Wu, L. Wang, and T. Tan. 2017. A convolutional approach for misinformation identification. In Proceedings of the 26th International Joint Conference on Artificial Intelligence. 3901--3907. https://doi.org/10.24963/ijcai.2017/545Google Scholar
- [35] . 2018. Predicting stances in Twitter conversations for detecting veracity of rumors: A neural approach. In Proceedings of the 2018 IEEE 30th International Conference Tools with Artificial Intelligence. IEEE, 2018, pp. 65–72.Google Scholar
Cross Ref
- [36] . 2018. A rumor events detection method based on deep bidirectional GRU neural network. In Proceedings of the 2018 3rd IEEE International Conference on Image and Visual Computing (ICIVC’18). IEEE, 2018, pp. 755–759.
DOI:
https://doi.org/10.1109/ICIVC.2018.8492819Google Scholar
Cross Ref
- [37] . 2018. Call attention to rumors: Deep attention based recurrent neural networks for early rumor detection. In Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining Springer, 2018, pp. 40–52.
DOI:
https://doi.org/10.1007/978-3-030-04503-6_4Google Scholar
Cross Ref
- [38] . 2018. Neural user response generator: Fake news detection with collective user intelligence. In Proceedings of IJCAI, 2018, pp. 3834–3840.Google Scholar
Cross Ref
- [39] . 2017. Content representation for microblog rumor detection. In Adv. Intell. Syst. Comput. Springer-Verlag, 2017, pp. 245–251.
DOI:
https://doi.org/10.1007/978-3-319-46562-3_16Google Scholar
- [40] . 2019. Rumor detection on social media: A multi-view model using self-attention mechanism. In Lecture Notes in Computer Science (Including the Subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics. Springer-Verlag, 2019, pp. 339–352.
DOI:
https://doi.org/10.1007/978-3-030-22734-0_25Google Scholar
Digital Library
- [41] . 2019. SpotFake: A multi-modal framework for fake news detection. In Proceedings of the 2019 IEEE 5th International Conference on Multimedia and Big Data (BigMM’19). IEEE, 2019, pp. 39–47.
DOI:
https://doi.org/10.1109/BigMM.2019.00-44Google Scholar
Cross Ref
- [42] . 2019. Early rumour detection. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL'19). 1614–1623.Google Scholar
Cross Ref
- [43] . 2021. Detection of rumor conversations in Twitter using graph convolutional networks. Appl. Intell. (2021), 1–14.
DOI:
https://doi.org/10.1007/s10489-020-02036-0Google Scholar
- [44] . 2021. Detecting fake news with capsule neural networks. Appl. Soft Comput. 101 (2021), 106991.
DOI:
https://doi.org/10.1016/j.asoc.2020.106991Google Scholar
Cross Ref
- [45] . 2021. Fake news detection and analysis using multitask learning with BiLSTM CapsNet model. In Proceedings of the 2021 11th International Conference on Cloud Computing and Data Science and Engineering. IEEE, 2021, pp. 905–911.
DOI:
https://doi.org/10.1109/Confluence51648.2021.9377080Google Scholar
Cross Ref
- [46] . 2020. A semi-supervised model for Persian rumor verification based on content information. Multimed. Tools Appl. (2020), 1–29.Google Scholar
- [47] . 2019. Future Internet: An improved approach for text sentiment classification based on a deep neural network via a sentiment attention mechanism. Futur. Internet. 11 (2019).
DOI:
https://doi.org/10.3390/fi11040096Google Scholar
- [48] . 2018. Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018.Google Scholar
Cross Ref
- [49] . 2019. Fake news detection using deep learning models: A novel approach. Trans. Emerg. Telecommun. Technol. (2019), e3767.Google Scholar
- [50] . 2017. Separating facts from fiction: Linguistic models to classify suspicious and trusted news posts on Twitter. In Proceedings of the 55th Annual Meeting of the Association of Computational Linguistics (Volume 2: Short Papers). 2017, pp. 647–653.Google Scholar
Cross Ref
- [51] . 2017. IKM at SemEval-2017 Task 8: Convolutional neural networks for stance detection and rumor verification. In Proceedings of the 11th International Workshop on Semantics Evaluation. Association for Computational Linguistics, Stroudsburg, PA, 2017, pp. 465–469.
DOI:
https://doi.org/10.18653/v1/S17-2081Google Scholar
Cross Ref
- [52] . 2020. Pretrained embeddings for stance detection with hierarchical capsule network on social media. ACM Trans. Inf. Syst. 39 (2020), 1–32.
DOI:
https://doi.org/10.1145/3412362Google Scholar
Digital Library
- [53] . 2019. Sepehr_RumTel01, 1 (2019).
DOI:
https://doi.org/10.17632/JW3ZWF8RDP.1Google Scholar
- [54] . 2020. ParsBERT: Transformer-based model for Persian language understanding. ArXiv Prepr. ArXiv2005.12515. (2020).Google Scholar
- [55] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL'19). 4171--4186.Google Scholar
- [56] . 2017. Dynamic routing between capsules. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 3859--3869.Google Scholar
Digital Library
- [57] . 2019. Design and investigation of capsule networks for sentence classification. Appl. Sci. 9 (2019), 2200.Google Scholar
Cross Ref
- [58] . 2018. Investigating capsule networks with dynamic routing for text classification. In Proceedings of the 2018 Conference on Empirical Methods of Natural Language Processes. Association for Computational Linguistics, 3110–3119.Google Scholar
Cross Ref
- [59] . 2020. Text classification using capsules. Neurocomputing. 376 (2020), 214–221.Google Scholar
Digital Library
- [60] . 2019. Parallel capsule neural networks for sound event detection. In Proceedings of the 2019 Asia-Pacific Signal Information Processing Association Summit Conference (APSIPA ASC). IEEE, 2019, pp. 1933–1936.Google Scholar
Cross Ref
- [61] . 1975. How to Do Things with Words. Oxford University Press, 1975.Google Scholar
Cross Ref
- [62] . 1970. Speech acts: An essay in the philosophy of language. Language (Baltim). 46 (1970), 217.
DOI:
https://doi.org/10.2307/412428Google Scholar
Cross Ref
- [63] J. R. Searle. 1979. A taxonomy of illocutionary acts. In Expression and Meaning: Studies in the Theory of Speech Acts. Cambridge University Press, 1--29.
DOI: 10.1017/CBO9780511609213.003Google Scholar - [64] . 2010. Speech acts classification of Persian language texts using three machine learning methods. International Journal of Information and Communication Technology Research 2, 1 (2010), 65--71. https://www.sid.ir/en/journal/ViewPaper.aspx?id=208218.Google Scholar
- [65] . 2004. Automating linguistics-based cues for detecting deception in text-based asynchronous computer-mediated communications. Gr. Decis. Negot. 13 (2004), 81–106.
DOI:
https://doi.org/10.1023/B:GRUP.0000011944.62889.6fGoogle Scholar
Cross Ref
- [66] . 2020. Fake news early detection: A theory-driven model. Digit. Threat. Res. Pract. 1 (2020), 1–25.Google Scholar
Digital Library
- [67] . 2011. Ravanshenasy-e shayee [Psychological Bases of Rumor], Islamic Culture Publishing Office, Tehran, 2011.Google Scholar
- [68] . 2018. Ravanshenasi-e shayee [Rumor psychology]. Vania, 2018.Google Scholar
- [69] . 2010. Automatic spell checking in Persian language. Supreme Council Inf. Commun. Technol. (SCICT), Tehran, Iran (2010).Google Scholar
- [70] . 2017. A hybrid approach for Persian-named entity recognition. Iran. J. Sci. Technol. Trans. A Sci. 41 (2017), 215–222.Google Scholar
Cross Ref
- [71] . 2006. Creating a Feasible Corpus for Persian POS Tagging. Department of Electrical Computer Engineering. University of Tehran. (2006), 1–9. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.103.2154&rep=rep1&type=pdf.Google Scholar
- [72] . 2014. Conceptualization of the Persian simple verbs of motion: A cognitive approach. J. Lang. West. Iran. Dialects. 1 (2014), 103–122. http://jlw.razi.ac.ir/article_275_en.html.Google Scholar
- [73] . 2013. Crowdsourcing: A word-emotion association lexicon. In Computer Intelligence 2013, pp. 436–465.
DOI:
https://doi.org/10.1111/j.1467-8640.2012.00460.xGoogle Scholar
Cross Ref
- [74] . 2019. A challenge dataset and effective models for aspect-based sentiment analysis. In Proceedings of the 2019 Conference on Empirical Methods Natural Language Processing and 9th International Joint Conference on Natural Processing. 2019, pp. 6281–6286.Google Scholar
Cross Ref
Index Terms
A Deep Content-Based Model for Persian Rumor Verification
Recommendations
A semi-supervised model for Persian rumor verification based on content information
AbstractRumor is a collective attempt to interpret a vague but attractive situation by using the power of words. In social networks, false-rumors may have significantly different contextual characteristics from true-rumors at lexical, syntactic, semantic ...
Rumor Verification on Social Media with Stance-Aware Recursive Tree
Knowledge Science, Engineering and ManagementAbstractSince rumors have affected real society harmfully, automatic rumor verification attracts much attention from researchers. Incorporating the stance-aware knowledge into rumor verification is a hot direction, because its great potential to boost ...
Rumor Gauge: Predicting the Veracity of Rumors on Twitter
Special Issue on KDD 2016 and Regular PapersThe spread of malicious or accidental misinformation in social media, especially in time-sensitive situations, such as real-world emergencies, can have harmful effects on individuals and society. In this work, we developed models for automated ...






Comments