Elamur Research⌕
☰
home / papers / 2018 / Rumor Detection on Twitter with Tree-structured Recursive Neural Networks

Rumor Detection on Twitter with Tree-structured Recursive Neural Networks

Summary

The paper addresses automatic rumor detection on Twitter. Each claim is a source tweet together with its replies and reposts, and the task is to assign it one of four labels: non-rumor, false rumor, true rumor or unverified rumor. Earlier methods had two main weaknesses. Some treated responses as a flat time series. Others compared propagation trees with kernels, which requires pairwise tree comparison and cannot learn abstract features.

The authors instead feed the propagation tree directly into recursive neural networks (RvNN), where each node is a whole post rather than a word. They design two variants:

  • BU-RvNN aggregates evidence from the leaves up to the source tweet.
  • TD-RvNN follows the direction in which information spreads, from the root down, and then pools over the leaf representations.

The underlying intuition is that a reply mainly reacts to its immediate parent. Patterns such as agreeing with someone who denies a false claim therefore carry veracity signals. On two public datasets, Twitter15 and Twitter16, both models clearly outperform feature-engineering, kernel-based and sequential neural baselines. They also reach good accuracy much earlier in propagation, which supports timely debunking.

Key points

  • Data: the public Twitter15 and Twitter16 corpora, with four-way labels (non-rumor, false, true, unverified rumor).
  • Baselines include SVM-TK (tree kernel), SVM-HK (hybrid kernel), SVM-BOW and the sequential GRU-RNN. SVM-TK is the strongest of these, and SVM-BOW even beats SVM-HK.
  • TD-RvNN performs better than BU-RvNN. The authors attribute this to less information loss and to the pooling over leaf nodes.
  • Early detection: both RvNN models match SVM-TK's best performance after roughly 8 hours or about 90 tweets. SVM-TK, by contrast, only reaches that level once some 36 hours have passed or roughly 300 posts have accumulated.
  • Weakness: the models are less effective on the non-rumor class than some feature-based baselines that also use user metadata. Code is released at github.com/majingCUHK/Rumor_RvNN.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Natural language processing

Cited by

72 papers of our library cite it (of the 140884 whose bibliographies we read); 3 of them have a page here, 69 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p18-1184

@inproceedings{ma2018rumor,
  title = {{Rumor Detection on Twitter with Tree-structured Recursive Neural Networks}},
  author = {Ma, Jing and Gao, Wei and Wong, Kam-Fai},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1184},
  url = {https://doi.org/10.18653/v1/p18-1184}
}

References

40 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gordon W Allport and Leo Postman. 1946. An analysis of rumor. Public Opinion Quarterly 10(4):501– 517. find
  2. G.W. Allport and L.J. Postman. 1965. The psychology of rumor. Russell & Russell. find
  3. Adam J. Berinsky. 2017. Rumors and health care reform: Experiments in political misinformation. British Journal of Political Science 47(2):241262. find
  4. Carlos Castillo, Marcelo Mendoza, and Barbara Poblete. 2011. Information credibility on twitter. In Proceedings of WWW. pages 675–684. find
  5. Tong Chen, Lin Wu, Xue Li, Jun Zhang, Hongzhi Yin, and Yang Wang. 2017. Call attention to rumors: Deep attention based recurrent neural networks for early rumor detection. arXiv preprint arXiv:1704.05973 . — [arXiv:1704.05973](https://arxiv.org/abs/1704.05973) find
  6. Kyunghyun Cho, Bart van Merriënboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 . find our card
  7. Nicholas DiFonzo and Prashant Bordia. 2007. Rumor, gossip and urban legends. Diogenes 54(1):19–35. find
  8. Nicholas DiFonzo, Prashant Bordia, and Ralph L Rosnow. 1994. Reining in rumors. Organizational Dynamics 23(1):47–62. find
  9. Pamela Donovan. 2007. How idle is idle talk? one hundred years of rumor research. Diogenes 54(1):59– 82. find
  10. John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12(Jul):2121–2159. find
  11. Adrien Friggeri, Lada A Adamic, Dean Eckles, and Justin Cheng. 2014. Rumor cascades. In Proceedings of ICWSM. find
  12. Christoph Goller and Andreas Kuchler. 1996. Learning task-dependent distributed representations by backpropagation through structure. In Neural Networks, 1996., IEEE International Conference on. IEEE, volume 1, pages 347–352. find
  13. Aniko Hannak, Drew Margolin, Brian Keegan, and Ingmar Weber. 2014. Get back! you don’t know me like that: The social mediation of fact checking interventions in twitter conversations. In Proceedings of ICWSM. find
  14. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9(8):1735–1780. find
  15. Ozan Irsoy and Claire Cardie. 2014. Deep recursive neural networks for compositionality in language. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. NIPS’14, pages 2096–2104. find
  16. Marianne E Jaeger, Susan Anthony, and Ralph L Rosnow. 1980. Who hears what from whom and with what effect: A study of rumor. Personality and Social Psychology Bulletin 6(3):473–478. find
  17. Allan J Kimmel. 2004. Rumors and rumor control: A manager’s guide to understanding and combatting rumors. Routledge. find
  18. Sejeong Kwon, Meeyoung Cha, Kyomin Jung, Wei Chen, and Yajun Wang. 2013. Prominent features of rumor propagation in online social media. In Proceedings of ICDM. pages 1103–1108. find
  19. Xiaomo Liu, Armineh Nourbakhsh, Quanzhi Li, Rui Fang, and Sameena Shah. 2015. Real-time rumor debunking on twitter. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. CIKM ’15, pages 1867–1870. find
  20. Michal Lukasik, PK Srijith, Duy Vu, Kalina Bontcheva, Arkaitz Zubiaga, and Trevor Cohn. 2016. Hawkes processes for continuous time sequence classification: an application to rumour stance classification in twitter. In Proceedings of the 54th Annual Meeting of the Association for Computational Lingui… find
  21. Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard J Jansen, Kam-Fai Wong, and Meeyoung Cha. 2016. Detecting rumors from microblogs with recurrent neural networks. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. IJCAI’16, pages 3818–3824. find
  22. Jing Ma, Wei Gao, Zhongyu Wei, Yueming Lu, and Kam-Fai Wong. 2015. Detect rumors using time series of social context information on microblogging websites. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. CIKM ’15, pages 1751–1754. find
  23. Jing Ma, Wei Gao, and Kam-Fai Wong. 2017. Detect rumors in microblog posts using propagation structure via kernel learning. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). volume 1, pages 708–717. find our card
  24. Jing Ma, Wei Gao, and Kam-Fai Wong. 2018. Detect rumor and stance jointly by neural multi-task learning. In Companion Proceedings of the The Web Conference 2018. WWW ’18, pages 585–593. find
  25. Lili Mou, Hao Peng, Ge Li, Yan Xu, Lu Zhang, and Zhi Jin. 2015. Discriminative neural sentence modeling by tree-based convolution. arXiv preprint arXiv:1504.01106 . find
  26. Vahed Qazvinian, Emily Rosengren, Dragomir R Radev, and Qiaozhu Mei. 2011. Rumor has it: Identifying misinformation in microblogs. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. EMNLP ’11, pages 1589–1599. find our card
  27. Jacob Ratkiewicz, Michael Conover, Mark Meiss, Bruno Gonçalves, Snehal Patil, Alessandro Flammini, and Filippo Menczer. 2011. Truthy: mapping the spread of astroturf in microblog streams. In Proceedings of the 20th International Conference Companion on World Wide Web. WWW ’11, pages 249– 252. find
  28. Ralph L Rosnow and Eric K Foster. 2005. Rumor and gossip research. Psychological Science Agenda 19(4). find
  29. Natali Ruchansky, Sungyong Seo, and Yan Liu. 2017. Csi: A hybrid deep model for fake news detection. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. CIKM ’17, pages 797–806. find
  30. Richard Socher, Brody Huval, Christopher D Manning, and Andrew Y Ng. 2012. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. EMNLP-CoNLL ’12, p… find our card
  31. Richard Socher, Cliff C Lin, Chris Manning, and Andrew Y Ng. 2011. Parsing natural scenes and natural language with recursive neural networks. In Proceedings of the 28th international conference on machine learning (ICML-11). pages 129–136. find
  32. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 conference on empirical methods in natural language processing. pages 1631–1… find
  33. Kai Sheng Tai, Richard Socher, and Christopher D Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 . find
  34. Ke Wu, Song Yang, and Kenny Q Zhu. 2015. False rumors detection on sina weibo by propagation structures. In Data Engineering (ICDE), 2015 IEEE 31st International Conference on. IEEE, pages 651–662. find
  35. Fan Yang, Yang Liu, Xiaohui Yu, and Min Yang. 2012. Automatic detection of rumor on sina weibo. In Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics. MDS ’12, pages 13:1–13:7. find
  36. Zhe Zhao, Paul Resnick, and Qiaozhu Mei. 2015. Enquiring minds: Early detection of rumors in social media from enquiry posts. In Proceedings of the 24th International Conference on World Wide Web. WWW ’15, pages 1395–1405. find
  37. Xiaodan Zhu, Parinaz Sobihani, and Hongyu Guo. 2015. Long short-term memory over recursive structures. In Proceedings of the 32nd International Conference on Machine Learning. pages 1604– 1612. find
  38. Arkaitz Zubiaga, Ahmet Aker, Kalina Bontcheva, Maria Liakata, and Rob Procter. 2017. Detection and resolution of rumours in social media: A survey. arXiv preprint arXiv:1704.00656 . — [arXiv:1704.00656](https://arxiv.org/abs/1704.00656) find
  39. Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, and Michal Lukasik. 2016a. Stance classification in rumours as a sequential task exploiting the tree structure of social media conversations. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Te… find
  40. Arkaitz Zubiaga, Maria Liakata, Rob Procter, Geraldine Wong Sak Hoi, and Peter Tolmie. 2016b. Analysing how people orient to and spread rumours in social media by looking at conversational threads. PloS one 11(3):e0150989. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ma-2018-rumor-detection-twitter-tree-structured/