ABSTRACT
The penetration of social media has had deep and far-reaching consequences in information production and consumption. Widespread use of social media platforms has engendered malicious users and attention seekers to spread rumors and fake news. This trend is particularly evident in various microblogging platforms where news becomes viral in a matter of hours and can lead to mass panic and confusion. One intriguing fact regarding rumors and fake news is that very often rumor stories prompt users to adopt different stances about the rumor posts. Understanding user stances in rumor posts is thus very important to identify the veracity of the underlying content. While rumor veracity and stance detection have been viewed as disjoint tasks we demonstrate here how jointly learning both of them can be fruitful. In this paper, we propose RumorSleuth, a multitask deep learning model which can leverage both the textual information and user profile information to jointly identify the veracity of a rumor along with users' stances. Tests on two publicly available rumor datasets demonstrate that RumorSleuth outperforms current state-of-the-art models and achieves up to 14% performance gain in rumor veracity classification and around 6% improvement in user stance classification.
- M. Amoruso et al. Contrasting the spread of misinformation in online social networks. In AAMAS, pages 1323--1331, 2017.Google Scholar
- S. R. Bowman et al. Generating sentences from a continuous space. arXiv preprint arXiv:1511.06349, 2015.Google Scholar
- C. Budak, D. Agrawal, and A. El Abbadi. Limiting the spread of misinformation in social networks. In WWW, pages 665--674, 2011.Google ScholarDigital Library
- C. Castillo, M. Mendoza, and B. Poblete. Information credibility on twitter. In WWW, pages 675--684, 2011.Google ScholarDigital Library
- W.-F. Chen and L.-W. Ku. UTCNN: a deep learning model of stance classification on social media text. In COLING, pages 1635--1645, 2016.Google Scholar
- N. Difonzo and P. Bordia. Rumors influence: Toward a dynamic social impact theory of rumor. In Science of social influence: Advances and future progress, pages 271--296, 2007.Google Scholar
- J. Du, R. Xu, Y. He, and L. Gui. Stance classification with target-specific neural attention networks. In IJCAI, 2017.Google ScholarCross Ref
- A. Friggeri, L. Adamic, D. Eckles, and J. Cheng. Rumor cascades. In ICWSM, pages 101--110, 2014.Google Scholar
- K. Gregor et al. DRAW: A recurrent neural network for image generation. arXiv preprint arXiv:1502.04623, 2015.Google Scholar
- K. Hasan and V. Ng. Stance classification of ideological debates: Data, models, features, and constraints. In IJCNLP, pages 1348--1356, 2013.Google Scholar
- Z. Jin et al. Multimodal fusion with recurrent neural networks for rumor detection on microblogs. In ACM MM Conf., pages 795--816, 2017.Google ScholarDigital Library
- M. A. Kamins, V. S. Folkes, and L. Perner. Consumer responses to rumors: Good news, bad news. J Consum Psychol, 6(2):165--187, 1997.Google ScholarCross Ref
- D. P. Kingma and M. Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.Google Scholar
- E. Kochkina, M. Liakata, and A. Zubiaga. All-in-one: Multi-task learning for rumour verification. arXiv preprint arXiv:1806.03713, 2018.Google Scholar
- S. Kwon, M. Cha, and K. Jung. Rumor detection over varying time windows. PloS one, 12(1):e0168344, 2017.Google ScholarCross Ref
- Q. Le and T. Mikolov. Distributed representations of sentences and documents. In ICML, pages 1188--1196, 2014.Google ScholarDigital Library
- X. Li and J. She. Collaborative variational autoencoder for recommender systems. In KDD, pages 305--314, 2017.Google ScholarDigital Library
- P. Liu, X. Qiu, and X. Huang. Recurrent neural network for text classification with multi-task learning. In IJCAI, pages 2873--2879, 2016.Google ScholarDigital Library
- X. Liu et al. Real-time rumor debunking on twitter. In CIKM, pages 1867--1870, 2015.Google ScholarDigital Library
- M. Lukasik et al. Hawkes processes for continuous time sequence classification: an application to rumour stance classification in twitter. In ACL, volume 2, pages 393--398, 2016.Google ScholarCross Ref
- J. Ma et al. Detecting rumors from microblogs with recurrent neural networks. In IJCAI, pages 3818--3824, 2016.Google ScholarDigital Library
- J. Ma, W. Gao, and K.-F. Wong. Detect rumor and stance jointly by neural multi-task learning. In WWW, pages 585--593, 2018.Google Scholar
- V. Qazvinian, E. Rosengren, D. R. Radev, and Q. Mei. Rumor has it: Identifying misinformation in microblogs. In EMNLP, pages 1589--1599, 2011.Google ScholarDigital Library
- R. L. Rosnow. Inside rumor: A personal journey. American Psychologist, 46(5):484, 1991.Google ScholarCross Ref
- S. Vosoughi, D. Roy, and S. Aral. The spread of true and false news online. Science, 359(6380):1146--1151, 2018.Google ScholarCross Ref
- K. Wu, S. Yang, and K. Q. Zhu. False rumors detection on sina weibo by propagation structures. In ICDE, pages 651--662, 2015.Google ScholarCross Ref
- W. Xu, H. Sun, C. Deng, and Y. Tan. Variational autoencoder for semi-supervised text classification. In AAAI, pages 3358--3364, 2017.Google ScholarCross Ref
- Z. Zhao, P. Resnick, and Q. Mei. Enquiring minds: Early detection of rumors in social media from enquiry posts. In WWW, pages 1395--1405, 2015.Google ScholarDigital Library
- A. Zubiaga et al. Analysing how people orient to and spread rumours in social media by looking at conversational threads. PloS one, 11(3), 2016.Google Scholar
- RumorSleuth: joint detection of rumor veracity and user stance
Recommendations
A survey on rumor detection and prevention in social media using deep learning
AbstractIn the current digital era, massive amounts of unreliable, purposefully misleading material, such as texts and images, are being shared widely on various web platforms to deceive the reader. Most of us use social media sites to exchange or obtain ...
Finding news-topic oriented influential twitter users based on topic related hashtag community detection
Recently, more and more users would like to collect and provide information about news topics in Twitter, which is one of the most popular microblogging services. Virtual communities defined by hashtags in Twitter are created for exchanging information ...
Measuring influence on Twitter
i-KNOW '11: Proceedings of the 11th International Conference on Knowledge Management and Knowledge TechnologiesThere are currently over 175 million Twitter accounts worldwide, making Twitter one of the most popular and most observed Social Media platform. But Twitter is not so much a social network where the exchange of personal information is facilitated -- in ...
Comments