Identifying misinformation on Twitter with a support vector machine

Main Article Content

Supanya Aphiwongsophon
Prabhas Chongstitvatana

Abstract

There is a large amount of information from disparate sources around the world. Due to the recent growth of online social media and its impact on society, identifying misinformation is an important activity. Twitter is one of the most popular applications that can deliver engaging data in a timely manner. Developing techniques that can detect misinformation from Twitter has become a challenging yet necessary task. This article proposes a machine learning method that can identify misinformation from Twitter data. The experiment was carried out with three widely used machine learning methods, naïve Bayes, a neural network and a support vector machine, using Twitter data collected from October to November 2017 in Thailand. The results show that all three methods can detect misinformation accurately. The accuracy of the naïve Bayes method was 95.55%, that of the neural network was 97.09%, and that of the support vector machine 98.15%. Furthermore, we analyzed the misinformation and noted some of its characteristics.

Downloads

Download data is not yet available.

Article Details

How to Cite
Aphiwongsophon, S., & Chongstitvatana, P. (2020). Identifying misinformation on Twitter with a support vector machine. Engineering and Applied Science Research, 47(3), 306-312. Retrieved from https://ph01.tci-thaijo.org/index.php/easr/article/view/231341
Section
ORIGINAL RESEARCH

References

[1] Vosoughi S, Roy D, Aral S. The spread of true and false news online. Science. 2018;359:1146-51.

[2] We Are Social Inc. Digital 2020 reports [Internet]. New York: We Are Social Inc; 2020 [cited 2020 March 2]. Available from: https://wearesocial.com/digital-2020.

[3] Alrubaian M, Al-Qurishi M, Hassan MM, Alamri A. A credibility analysis system for assessing information on twitter. IEEE Trans Dependable Secure Comput. 2018;15(4):661-74.

[4] Mahid ZI, Manickam S, Karuppayah S. Fake news on social media: brief review on detection techniques. Proceedings of International Conference on Advances in Computing, Communication & Automation; 2018 Oct 26-28; Subang Jaya. Malaysia. USA: IEEE; 2018. p. 157-61.

[5] Khan SA, Alkawaz MH, Zangana HM. The use and abuse of social media for spreading fake news. Proceedings of International Conference on Automatic Control and Intelligent Systems; 2019 June 29; Selangor, Malaysia. USA: IEEE; 2019. p. 145-8.

[6] BBC. India WhatsApp child abduction rumours: Five more lynched [Internet]. 2018 [cited 2019 Dec 20]. Available from: https://www.bbc.com/news/world-asia-india-44678674.

[7] CNN. India WhatsApp rumors: Mob kills man in latest attack, 30 arrested [Internet]. 2018 [cited 2019 Dec 20]. Available from: https://edition.cnn.com/2018/07/ 16/asia/india-whatsapp-lynching-intl/index.html.

[8] BBC. Social media rumours in India: counting the dead [Internet]. 2018 [cited 2019 Dec 20]. Available from: https://www.bbc.co.uk/news/resources/idt-e5043092-f7f0-42e9-9848-5274ac896e6d.

[9] JS100. Bangchak request to stop sharing or like "fake news refueling for free" (in Thai) [Internet]. 2019 [cited 2019 Dec 20]. Available from: https://www.js100.com /en/site/post_share/view/47205.

[10] Lee MSaY. Taiwan representative in Japan's Osaka commits suicide, Thomson Reuters [Internet]. 2018 [cited 2019 Dec 20]. Available from: https:// www.reuters.com/article/us-japan-taiwan/taiwan-representative-in-japans-osaka-commits-suicide- idUSKCN1LV067.

[11] Everington; K. Breaking News: Director of Taiwan representative office in Osaka commits suicide, Taiwan News [Internet]. 2018 [cited 2019 Dec 20]. Available from: https://www.taiwannews.com.tw/en/ news/3529766.

[12] Gottfried ESaJ. News Use Across Social Media Platforms 2017, Pew Research Center [Internet]. 2017 [cited 2019 Dec 20]. Available from: https:// www.journalism.org/2017/09/07/news-use-across-social-media-platforms-2017.

[13] Allcott H, Gentzkow M. Social media and fake news in the 2016 election. J Econ Perspect. 2017;31(2):211-36.

[14] Parikh SB, Patil V, Atrey PK. On the origin, proliferation and tone of fake news. Proceedings of Conference on Multimedia Information Processing and Retrieval; 2019 Mar 28-30; San Jose, USA. USA: IEEE; 2019. p. 135-40.

[15] Helmstetter S, Paulheim H. Weakly supervised learning for fake news detection on twitter. Proceedings of International Conference on Advances in Social Networks Analysis and Mining; 2018 Aug 28-31; Barcelona, Spain. USA: IEEE; 2018. p. 274-7.

[16] Sample C, Justice C, Darraj E. Fake news: a method to measure distance from fact. Proceedings of International Conference on Big Data; 2018 Dec 10-13; Seattle, USA. USA: IEEE; 2018. p. 4443-52.

[17] Xu K, Wang F, Wang H, Yang B. Detecting fake news over online social media via domain reputations and content understanding. Tsinghua Sci Tech. 2020;25(1):20-7.

[18] Dey A, Rafi RZ, Parash SH, Arko SK, Chakrabarty A. Fake news pattern recognition using linguistic analysis. Proceedings of Joint International Conference on Informatics, Electronics & Vision and International Conference on Imaging, Vision & Pattern Recognition; 2018 Jun 25-29; Fukuoka, Japan. USA: IEEE; 2018. p. 305-9.

[19] Thu PP, New N. Implementation of emotional features on satire detection. Proceedings of International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing; 2017 Jun 26-28; Kanazawa, Japan. USA: IEEE; 2017. p. 149-54.

[20] Benamara F, Bosco C, Fersini E, Pasi G, Patti V, Viviani M. SeCredISData. Proceedings of International Conference on Data Science and Advanced Analytics; 2018 Oct 1-4; Turin, Italy. USA: IEEE; 2018. p. 638-40.

[21] Chandra YU, Surjandy, Ernawaty. Higher education student behaviors in spreading fake news on social media: a case of LINE group. Proceedings of International Conference on Information Management and Technology; 2017 Nov 15-17; Yogyakarta, Indonesia. USA: IEEE; 2017. p. 54-9.

[22] Alrubaian M, Al-Qurishi M, Al-Rakhami M, Rahman SMM, Alamri A. A multistage credibility analysis model for microblogs. Proceedings of International Conference on Advances in Social Networks Analysis and Mining 2015; 2015 Aug 25-28; Paris, France: USA; IEEE; 2015. p. 1434-40.

[23] Jin Z, Cao J, Zhang Y, Zhou J, Tian Q. Novel visual and statistical image features for microblogs news verification. IEEE Trans Multimed. 2017;19(3):598-608.

[24] El Ballouli R, El-Hajj W, Ghandour A, Elbassuoni S, Hajj H, Shaban K. CAT: credibility analysis of arabic content on twitter. Proceedings of Arabic Natural Language Processing Workshop; 2017 Apr 3; Valencia, Spain. USA: Association for Computational Linguistics; 2017. p. 62-71.

[25] Conroy NJ, Rubin VL, Chen Y. Automatic deception detection: Methods for finding fake news. Proc Assoc Inf Sci Technol. 2015;52(1):1-4.

[26] Lorek K, Suehiro-Wiciński J, Jankowski-Lorek M, Gupta A. Automated credibility assessment on twitter. Comput Sci. 2015;16(2):157-68.

[27] Vedova MLD, Tacchini E, Moret S, Ballarin G, DiPierro M, Alfaro LD. Automatic online fake news detection combining content and social signals. Proceedings of Conference of Open Innovations Association; 2018 May 15-18; Jyväskylä, Finland. USA: IEEE; 2018. p. 272-9.

[28] Krishnan S, Chen M. Identifying tweets with fake news. Proceedings of International Conference on Information Reuse and Integration; 2018 Jul 6-9; Salt Lake City, USA. USA: IEEE; 2018. p. 460-4.

[29] Granik M, Mesyura V. Fake news detection using naïve Bayes classifier. Proceedings of Ukraine Conference on Electrical and Computer Engineering; 2017 May 29- Jun 2; Kyiv, Ukraine. USA: IEEE; 2017. p. 900-3.

[30] Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273-97.

[31] Poddar K, D GBA, Umadevi KS. Comparison of various machine learning models for accurate detection of fake news. Proceedings of Innovations in Power and Advanced Computing Technologies; 2019 Mar 22-23; Vellore, India. p. 1-5.

[32] Oriola O, Kotzé E. Evaluating machine learning techniques for detecting offensive and hate speech in South African Tweets. IEEE Access. 2020;8:21496-509.

[33] Shahi TB, Pant AK. Nepali news classification using Naïve Bayes, support vector machines and neural networks. Proceedings of International Conference on Communication information and Computing Technology; 2018 Feb 2-3; Mumbai, India. USA: IEEE; 2018. p. 1-5.

[34] Abdullah All T, Mahir EM, Akhter S, Huq MR. Detecting fake news using machine learning and deep learning algorithms. Proceedings of International Conference on Smart Computing & Communications; 2019 Jun 28-30; Miri, Malaysia. USA: IEEE; 2019. p. 1-5.

[35] Ajao O, Bhowmik D, Zargari S. Fake news identification on twitter with hybrid CNN and RNN models. Proceedings of International Conference on Social Media and Society; 2018 Jul; Copenhagen, Denmark. New York: ACM; 2018. p. 226-30.

[36] Girgis S, Amer E, Gadallah M. Deep learning algorithms for detecting fake news in online text. Proceedings of International Conference on Computer Engineering and Systems; 2018 Dec 18-19; Cairo, Egypt. USA: IEEE; 2018. p. 93-7.

[37] Balwant MK. Bidirectional LSTM based on POS tags and CNN architecture for fake news detection. Proceedings of International Conference on Computing, Communication and Networking Technologies; 2019 Jul 6-8; Kanpur, India. USA: IEEE; 2019. p. 1-6.