Abstract
The paper is focused on recognition of antisocial behavior in social media. User generated content in the form of discussions is essential to the success of many online platforms. While most users tend to civil accepting the social norms, others engage in antisocial behavior negatively affecting the rest of the community and its goals. Such behavior includes harassment, bullying, flaming, trolling, etc. The contribution is focused on classification of troll posts in online discussions to distinguish them from creditable posts. The work proposes a machine learning approach to build the classification model for toxic posts identification on an extensive dataset. The following machine learning methods were used: k Nearest Neighbors, Naïve Bayes Classifier, Decision Trees, Logistic regression and Support Vector Machine. These machine learning methods were used in combination with three different feature representations of texts of online discussions as a binary vector, a bag of words and the TF-IDF weighting scheme. The paper contains also the results of experiments with all learned models for toxic posts recognition.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Kumar, S., West, Ř., Leskovec, J.: Disinformation on the web. In: Proceedings of the 25th International on Word Wide Web – WWW16. Association for Computing Machinery, pp. 591–602. ACM, Montreal (2016)
Lessne, X., Hermalkar, X.: Student Reports of Bullying and Cyber-Bullying: Results from the 2011 School Crime Supplement to the National Crime Victimization Survey, Web Tables, NCES 2013-329. http://nces.ed.gov/. Accessed 25 May 2019
March, E.: ‘Don’t feed the trolls’ really is good advice – here’s the evidence. https://theconversation.com/dont-feed-the-trolls-really-is-good-advice-heres-the-evidence-63657. Accessed 25 May 2019
Wang, S.E., Garcia-Molina, H.: Disinformation Techniques for Entity resolution. In: Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, New York, USA, pp. 715–720 (2013)
Řimnáč, M.: Detection of a disinformation content – case study Novičok in CR. In: Proceedings of the Conference Data a znalosti & WIKT 2018, Brno, Vysoké učení technické, pp. 65–69 (2018)
Dematis, I., Karapistoli, E., Vakali, A.: Fake review detection via exploitation os spam indicators and reviewer behaviour characteristics. In: Proceedings of the 44th International Conference on Current Trends in Theory and Practice of Computer Science beyond Frontiers - SOFSEM 2018. Lecture Notes in Computer Science, Krems an der Donau, pp. 1–14. Springer, Heidelberg (2018)
Samuel, A.L.: Some studies in machine learning using the game of checkers. IBM J. Res. Dev. 3(3), 210–229 (1959)
Russell, S.J., Norvig, P.: Artificial Intelligence. A Modern Approach, 3rd edn. Prentice Hall, Pearson Education, New Jersey (2010). ISBN-13 978-0-13-604259-4
Tan, S.: Neighbor-weighted K-nearest neighbor for unbalanced text corpus. Expert Syst. Appl. 28(4), 667–671 (2005)
Cunningham, P., Delany, S.J.: k-Neighbour classifiers. Technical report, pp. 1–17, Dublin (2007)
Jiang, S., et al.: An improved k-nearest neighbor algorithm for text categorization. Expert Syst. Appl. 30(1), 1503–1509 (2012)
Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Philadelphia, pp. 79–86 (2002)
Kingsford, C., Salzberg, S.L.: What are decision trees? Nat. Biotechnol. 26(1), 1011–1013 (2008)
Orphanos, G., et al.: Decision Trees and NLP: A Case Study in POS Tagging. Academia, pp. 1–7 (1999)
Magerman, D.M., et al.: Statistical decision-tree models for parsing. In: Proceeding ACL 1995 Proceedings of the 33rd Annual Meeting on Association for Computational Linguistics, pp. 276–283 (1995)
Cox, D.R.: The regression analysis of binary sequences. J. R. Stat. Soc. 20(2), 215–242 (1958)
Zhang, J., et al.: Modified logistic regression: an approximation to SVM and its applications in large-scale text categorization. In: Proceedings of the Twentieth International Conference on Machine Learning, Washington DC, pp. 888–895 (2003)
Ben-Hur, A., et al.: Support vector clustering. J. Mach. Learn. Res. 2(2), 125–137 (2001)
Wulczyn, E., Thain, N., Dixon, L.: Ex machina: personal attacks seen at scale. In: Proceedings of the International World Wide Web Conference (WWW 2017), Perth, Australia, 3–7 April 2017, pp. 1391–1399 (2017)
Hosted by Kaggle.com, Toxic Comment Classification Challenge. https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge. Accessed 26 May 2019
Švec, A., Pikuliak, M., Šimko, M., Bieliková, M.: Improving moderation of online discussions via interpretable neural models. FIIT Slovak University of Technology, Bratislava, Slovakia, pp. 1–6 (2018)
Chandrasekharan, E., Samory, M., Srinivasan, A., Gilbert, E.: The bag of communities: identifying abusive behavior online with preexisting internet data. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 3175–3187. ACM (2017)
Ventirozos, F.K., Varlamis, I., Tsatsaronis, G.: Detecting aggressive behavior in discussion threads using text mining. In: CICLing 2017. LNCS, vol. 10762, pp. 420–431. Springer, Cham (2018)
Seah, C.W., et al.: Troll detection by domain-adapting sentiment analysis. In: Proceedings of the 18th International Conference on Information Fusion Washington, DC, pp. 792–799 (2015). 978-0-9824-4386-6/15/$31.00 ©2015 IEEE
Mutlu, B., et al.: Identifying trolls and determining terror awareness level in social networks using a scalable framework. In: Proceedings of IEEE International Conference on Big Data, pp. 1792–1798 (2016). 978-1-4673-9005-7/16/$31.00 ©2016 IEEE
Saeed, H.H., Shahzad, K., Kamiran, F.: Overlapping toxic sentiment classification using deep neural architectures. In: Proceedings of IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1361–1366 (2018). 2375-9259/18/$31.00 ©2018 IEEE
Saif, M.A., et al.: classification of online toxic comments using the logistic regression and neural networks models. In: Proceedings of the 44th International Conference on Applications of Mathematics in Engineering and Economics, pp. 1–5. AIP Publishing (2018). 978-0-7354-1774-8/$30.00
Fazil, M., Abulaish, M.: A hybrid approach for detecting automated spammers in Twitter. IEEE Trans. Inf. Forensics Secur. 13, 1556–6013 (2018)
Mikula, M., Machová, K.: Combined approach for sentiment analysis in Slovak using a dictionary annotated by particle swarm optimization. In: Acta Elektrotechnica et Informatica, vol. 18, no. 2, pp. 27–34 (2018). ISSN 1335–8243
Acknowledgements
The work presented in this paper was supported by the Slovak Research and Development Agency under the contract No. APVV-017-0267 “Automated Recognition of Antisocial Behavior in Online Communities” and the contract No. APVV-015-0731.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Machová, K., Kolesár, D. (2020). Recognition of Antisocial Behavior in Online Discussions. In: Świątek, J., Borzemski, L., Wilimowska, Z. (eds) Information Systems Architecture and Technology: Proceedings of 40th Anniversary International Conference on Information Systems Architecture and Technology – ISAT 2019. ISAT 2019. Advances in Intelligent Systems and Computing, vol 1051. Springer, Cham. https://doi.org/10.1007/978-3-030-30604-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-30604-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30603-8
Online ISBN: 978-3-030-30604-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)