ExoFIA: Deep Exogenous Assistance in the Prediction of the Influence of Fake News with Social Media Explainability
Source abstract
Abstract
The growth of social platforms has lowered the barrier of entry into the media sector, allowing for the spread of false information and putting democratic politics and social security at peril. Preliminary analysis shows that posts sharing real news and fake news are disseminated on social media. Moreover, posts pointing to fake news spread faster, so this paper aims to predict the impact of posts citing fake news on social platforms. In this study, we take into account that exogenous factors, in addition to endogenous factors, can potentially determine how influential a post is. For example, the occurrence of social events can generate public resonance and discussion, thereby increasing the impact of relevant posts. Given that Google Trends can obtain search trends that reflect social popularity, this work aims to use Google Trends as the source of our exogenous factors. We propose a deep learning model called the deep exogenous aid in fake news (ExoFIA) model, which combines multi-modal features and utilizes an attention mechanism to provide model interpretability and analyze the influencing factors. Applying the model to real-world data from Twitter demonstrates that our model outperforms existing diffusion models. Furthermore, further examination of the relevant aspects of true and fake news reveals that the two are influenced by distinct variables.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Misinformation and Its Impacts · Complex Network Analysis Techniques · Opinion Dynamics and Social Influence
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, National Cheng Kung University, Tainan 70101, Taiwan
English Language, Tesol and Applied Linguistics, Swansea University, Swansea SA2 8PP, UK
Funding
National Science and Technology Council of Taiwan
References (43)
Show source-provided references
1. Gottfried, J., and Shearer, E. (Pew Research Center, 2016). News use across social media platforms 2016, Pew Research Center.
2. Social media and fake news in the 2016 election10.1257/jep.31.2.211 ↗
3. Thomas, Z. (BBC News, 2020). WHO Says Fake Coronavirus Claims Causing ‘Infodemic’, BBC News.
4. Nguyen, V.H., Sugiyama, K., Nakov, P., and Kan, M.Y. (2020, January 19–23). Fang: Leveraging social context for fake news detection using graph representation. Proceedings of the 29th ACM International Conference on Information & Knowledge Management, Virtual Event.10.1145/3340531.3412046 ↗
5. Ruchansky, N., Seo, S., and Liu, Y. (2017, January 6–10). Csi: A hybrid deep model for fake news detection. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore.
6. Shu, K., Wang, S., and Liu, H. (2019, January 11–15). Beyond news contents: The role of social context for fake news detection. Proceedings of the twelfth ACM International Conference on Web Search and Data Mining, Melbourne, Australia.10.1145/3289600.3290994 ↗
7. Robust dynamic classes revealed by measuring the response function of a social system10.1073/pnas.0803685105 ↗
8. Gao, S., Ma, J., and Chen, Z. (2015, January 2–6). Modeling and predicting retweeting dynamics on microblogging platforms. Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, Shanghai, China.10.1145/2684822.2685303 ↗
9. Mishra, S., Rizoiu, M.A., and Xie, L. (2016, January 24–28). Feature driven and point process approaches for popularity prediction. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, IN, USA.10.1145/2983323.2983812 ↗
10. Shen, H., Wang, D., Song, C., and Barabási, A.L. (2014, January 27–31). Modeling and predicting popularity dynamics via reinforced poisson processes. Proceedings of the AAAI Conference on Artificial Intelligence, Québec City, QC, Canada.10.1609/aaai.v28i1.8739 ↗
11. Zhao, Q., Erdogdu, M.A., He, H.Y., Rajaraman, A., and Leskovec, J. (2015, January 10–13). Seismic: A self-exciting point process model for predicting tweet popularity. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.10.1145/2783258.2783401 ↗
12. Bakshy, E., Hofman, J.M., Mason, W.A., and Watts, D.J. (2011, January 9–12). Everyone’s an influencer: Quantifying influence on twitter. Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, Hong Kong, China.10.1145/1935826.1935845 ↗
13. Zaman, T., Fox, E.B., and Bradlow, E.T. (2014). A bayesian approach for predicting the popularity of tweets. arXiv.10.1214/14-AOAS741 ↗
14. Cheng, J., Adamic, L., Dow, P.A., Kleinberg, J.M., and Leskovec, J. (2014, January 7–11). Can cascades be predicted?. Proceedings of the 23rd International Conference on World Wide Web, Seoul, Republic of Korea.10.1145/2566486.2567997 ↗
15. Gao, S., Ma, J., and Chen, Z. (2014, January 5–7). Popularity prediction in microblogging network. Proceedings of the Web Technologies and Applications: 16th Asia-Pacific Web Conference, APWeb 2014, Changsha, China. Proceedings 16.
16. Xie, D., Xu, J., and Lu, T.C. (2017, January 11–14). What’s trending tomorrow, today: Using early adopters to discover popular posts on Tumblr. Proceedings of the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA.10.1109/BigData.2017.8258165 ↗
17. Yang, J., and Leskovec, J. (2010, January 13–17). Modeling information diffusion in implicit networks. Proceedings of the 2010 IEEE International Conference on Data Mining, Sydney, Australia.10.1109/ICDM.2010.22 ↗
18. Naveed, N., Gottron, T., Kunegis, J., and Alhadi, A.C. (2011, January 15–17). Bad news travel fast: A content-based analysis of interestingness on twitter. Proceedings of the 3rd International Web Science Conference, Koblenz, Germany.10.1145/2527031.2527052 ↗
19. Anderson, A., Huttenlocher, D., Kleinberg, J., Leskovec, J., and Tiwari, M. (2015, January 18–22). Global diffusion via cascading invitations: Structure, growth, and homophily. Proceedings of the 24th International Conference on World Wide Web, Florence, Italy.10.1145/2736277.2741672 ↗
20. Outtweeting the twitterers-predicting information cascades in microblogs
21. Huberman, B.A., Romero, D.M., and Wu, F. (2008). Social networks that matter: Twitter under the microscope. arXiv.10.5210/fm.v14i1.2317 ↗
22. Chen, X., Zhou, F., Zhang, K., Trajcevski, G., Zhong, T., and Zhang, F. (2019, January 8–11). Information diffusion prediction via recurrent cascades convolution. Proceedings of the 2019 IEEE 35th International Conference on Data Engineering (ICDE), Macao, China.10.1109/ICDE.2019.00074 ↗
23. Li, C., Ma, J., Guo, X., and Mei, Q. (2017, January 3–7). Deepcas: An end-to-end predictor of information cascades. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia.10.1145/3038912.3052643 ↗
24. Wang, J., Zheng, V.W., Liu, Z., and Chang, K.C.C. (2017, January 18–21). Topological recurrent neural network for diffusion prediction. Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA.10.1109/ICDM.2017.57 ↗
25. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
26. Bai, S., Kolter, J.Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv.
27. 1D convolutional neural networks and applications: A survey10.1016/j.ymssp.2020.107398 ↗
28. Comparing information diffusion mechanisms by matching on cascade size10.1073/pnas.2100786118 ↗
29. Shu, K., Mahudeswaran, D., Wang, S., and Liu, H. (2020, January 1–5). Hierarchical propagation networks for fake news detection: Investigation and exploitation. Proceedings of the International AAAI Conference on Web and Social Media, Atlanta, GA, USA.10.1609/icwsm.v14i1.7329 ↗
30. The spread of true and false news online10.1126/science.aap9559 ↗
31. Fakenewsnet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media10.1089/big.2020.0062 ↗
32. A survey of information cascade analysis: Models, predictions, and recent advances10.1145/3433000 ↗
33. Perozzi, B., Al-Rfou, R., and Skiena, S. (2014, January 24–27). Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623732 ↗
34. Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv.
35. Myers, S.A., Zhu, C., and Leskovec, J. (2012, January 19–23). Information diffusion and external influence in networks. Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, UK.10.1145/2339530.2339540 ↗
36. Oghina, A., Breuss, M., Tsagkias, M., and De Rijke, M. (2012, January 1–5). Predicting IMDB Movie Ratings Using Social Media. Proceedings of the ECIR, Barcelona, Spain.10.1007/978-3-642-28997-2_51 ↗
37. Dutta, S., Masud, S., Chakrabarti, S., and Chakraborty, T. (2020, January 6–10). Deep exogenous and endogenous influence combination for social chatter intensity prediction. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event.10.1145/3394486.3403251 ↗
38. Masud, S., Dutta, S., Makkar, S., Jain, C., Goyal, V., Das, A., and Chakraborty, T. (2021, January 19–22). Hate is the new infodemic: A topic-aware modeling of hate speech diffusion on twitter. Proceedings of the 2021 IEEE 37th International Conference on Data Engineering (ICDE), Chania, Greece.10.1109/ICDE51399.2021.00050 ↗
39. Kupavskii, A., Umnov, A., Gusev, G., and Serdyukov, P. (2013, January 8–11). Predicting the audience size of a tweet. Proceedings of the International AAAI Conference on Web and Social Media, Cambridge, MA, USA.
40. Hutto, C., and Gilbert, E. (2014, January 1–4). Vader: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the International AAAI Conference on Web and Social Media, Ann Arbor, MI, USA.10.1609/icwsm.v8i1.14550 ↗
41. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
42. Cao, Q., Shen, H., Cen, K., Ouyang, W., and Cheng, X. (2017, January 6–10). Deephawkes: Bridging the gap between prediction and understanding of information cascades. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore.10.1145/3132847.3132973 ↗
43. Škrlj, B., Džeroski, S., Lavrač, N., and Petkovič, M. (2020). Feature importance estimation with self-attention networks. arXiv.