A Statistical Learning Approach to Detect Abusive Twitter Accounts

ABSTRACT

The increased use of social media has motivated spammers to post their malicious activities on social network sites. Some of these spammers use adult content to further the distribution of their malicious activities. Moreover, the extensive number of users posting adult content in social media degrades the experience for other users for whom the adult content is not desired or appropriate. In this paper, we aim to detect abusive accounts that post adult content using Arabic language to target Arab speakers. There is limited natural language processing (NLP) resources for the Arabic language, and to the best of our knowledge no research has been done to detect adult accounts with Arabic language in social media. We used a statistical learning approach to analyze Twitter content to detect abusive accounts that use obscenity, profanity, slang, and swearing words in Arabic text format. Our approach achieved a predictive accuracy of 96% and overcomes imitations of the bag-of-word (BOW) approach.

References

1. Abozinadah, E.A. and Jones Jr, J.H. IMPROVED MICROBLOG CLASSIFICATION FOR DETECTING ABUSIVE ARABIC TWITTER ACCOUNTS. International Journal of Data Mining & Knowledge Management Process (IJDKP). 6, 6, 17--28.
2. Abozinadah, E.A., Mbaziira, A.V. and Jones, J.H.J. 2015. Detection of Abusive Accounts with Arabic Tweets. International Journal of Knowledge Engineering-IACSIT. 1, 2 (2015), 113--119.
3. Adult or sexual products and services: https://help.twitter.com/articles/20170427?lang=en. Accessed: 2017--04-03.
4. Alsaleem, S. 2011. Automated Arabic Text Categorization Using SVM and NB. Int. Arab J. e-Technol. 2, 2 (2011), 124--128.
5. Al-Sughaiyer, I.A. and Al-Kharashi, I.A. 2004. Arabic Morphological Analysis Techniques: A Comprehensive Survey. J. Am. Soc. Inf. Sci. Technol. 55, 3 (Feb. 2004), 189--213.
6. Azhagusundari, B. and Thanamani, A.S. 2013. Feature selection based on information gain. International Journal of Innovative Technology and Exploring Engineering (IJITEE). 2, 2 (2013), 18--21.
7. Benevenuto, F., Magno, G., Rodrigues, T. and Almeida, V. 2010. Detecting spammers on twitter. In Collaboration, Electronic messaging, Anti-Abuse and Spam Conference (CEAS (2010).
8. Black, W., Elkateb, S., Rodriguez, H., Alkhalifa, M., Vossen, P., Pease, A. and Fellbaum, C. 2006. Introducing the Arabic wordnet project. Proceedings of the Third International WordNet Conference (2006), 295--300.
9. Brin, S. and Page, L. 1998. The Anatomy of a Large-scale Hypertextual Web Search Engine. Proceedings of the Seventh International Conference on World Wide Web 7 (Amsterdam, The Netherlands, The Netherlands, 1998), 107--117.
10. Bruns, A., Highfield, T. and Burgess, J. 2013. The Arab Spring and Social Media Audiences English and Arabic Twitter Users and Their Networks. American Behavioral Scientist. 57, 7 (Jul. 2013), 871--898.
11. Chaabane, A., Chen, T., Cunche, M., De Cristofaro, E., Friedman, A. and Kaafar, M.A. 2014. Censorship in the Wild: Analyzing Internet Filtering in Syria. Proceedings of the 2014 Conference on Internet Measurement Conference (New York, NY, USA, 2014), 285--298.
12. Cheng, H., Xing, X., Liu, X. and Lv, Q. 2015. ISC: An Iterative Social Based Classifier for Adult Account Detection on Twitter. IEEE Transactions on Knowledge and Data Engineering. 27, 4 (Apr. 2015), 1045--1056.
13. Diab, M. and Habash, N. 2007. Arabic dialect processing tutorial. Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Tutorial Abstracts (2007), 5--6.
14. El Kourdi, M., Bensaid, A. and Rachidi, T. 2004. Automatic Arabic Document Categorization Based on the NaÏVe Bayes Algorithm. Proceedings of the Workshop on Computational Approaches to Arabic Script-based Languages (Stroudsburg, PA, USA, 2004), 51--58.
15. Farghaly, A. and Shaalan, K. 2009. Arabic Natural Language Processing: Challenges and Solutions. 8, 4 (Dec. 2009), 14:1--14:22.
16. Hamdan, H., Bechet, F. and Bellot, P. 2013. Experiments with DBpedia, WordNet and SentiWordNet as re- sources for sentiment analysis in micro-blogging. Second Joint Conference on Lexical and Computational Semantics. 2, (2013).
17. Hatzivassiloglou, V. and McKeown, K.R. 1997. Predicting the Semantic Orientation of Adjectives. Proceedings of the Eighth Conference on European Chapter of the Association for Computational Linguistics (Stroudsburg, PA, USA, 1997), 174--181.
18. Irani, D., Webb, S. and Pu, C. 2010. Study of trend-stuffing on twitter through text classification. In Collaboration, Electronic messaging, Anti-Abuse and Spam Conference (CEAS (2010).
19. Joachims, T. 1998. Text categorization with Support Vector Machines: Learning with many relevant features. Machine Learning: ECML-98. C. Nédellec and C. Rouveirol, eds. Springer Berlin Heidelberg. 137--142.
20. Kirtsy Has Porn, Users Blame Twitter: 2008. https://thenextweb.com/2008/12/23/kirtsy-has-porn-users-blame-twitter/. Accessed: 2017--04-06.
21. Litvak, M., Last, M., Aizenman, H., Gobits, I. and Kandel, A. 2011. DegExt --- A Language-Independent Graph-Based Keyphrase Extractor. Advances in Intelligent Web Mastering -- 3. E. Mugellini, P.S. Szczepaniak, M.C. Pettenati, and M. Sokhn, eds. Springer Berlin Heidelberg. 121--130.
22. Mamoun, R. and Ahmed, M. 2016. Arabic text stemming: Comparative analysis. 2016 Conference of Basic Sciences and Engineering Studies (SGCAC) (Feb. 2016), 88--93.
23. McCord, M. and Chuah, M. 2011. Spam Detection on Twitter Using Traditional Classifiers. Autonomic and Trusted Computing. J.M.A. Calero, L.T. Yang, F.G. Mármol, L.J.G. Villalba, A.X. Li, and Y. Wang, eds. Springer Berlin Heidelberg. 175--186.
24. Mihalcea, R. and Tarau, P. 2004. TextRank: Bringing Order into Texts. (2004), 404--411.
25. Na, S.-H., Lee, Y., Nam, S.-H. and Lee, J.-H. 2009. Improving Opinion Retrieval Based on Query-Specific Sentiment Lexicon. Advances in Information Retrieval (Apr. 2009), 734--738.
26. nltk.stem.isri --- NLTK 3.0 documentation: http://www.nltk.org/_modules/nltk/stem/isri.html. Accessed: 2016--10-07.
27. Page, L. 2001. United States Patent: 6285999 - Method for node ranking in a linked database. 6285999. Sep. 4, 2001.
28. Purohit, H., Hampton, A., Shalin, V.L., Sheth, A.P., Flach, J. and Bhatt, S. 2013. What kind of #conversation is Twitter? Mining #psycholinguistic cues for emergency coordination. Computers in Human Behavior. 29, 6 (Nov. 2013), 2438--2447.
29. PyArabic 0.5: Python Package Index: https://pypi.python.org/pypi/PyArabic/0.5. Accessed: 2016--10-07.
30. Rafter, M.V. 2009. An open letter to Twitter: stop the porn spam. WordCount.
31. Rsheed, N.A. and Khan, M.B. 2014. Predicting the Popularity of Trending Arabic News on Twitter. Proceedings of the 6th International Conference on Management of Emergent Digital EcoSystems (New York, NY, USA, 2014), 3:15--3:19.
32. Saudi govt. agencies struggling to fight porn on social media: http://english.alarabiya.net/en/media/digital/2014/03/19/Saudi-govt-agencies-struggling-to-fight-porn-on-social-media.html. Accessed: 2014--11-21.
33. Singh, M., Bansal, D. and Sofat, S. 2016. Behavioral analysis and classification of spammers distributing pornographic content in social media. Social Network Analysis and Mining. 6, 1 (Jun. 2016), 41.
34. Sriram, B., Fuhry, D., Demir, E., Ferhatosmanoglu, H. and Demirbas, M. 2010. Short Text Classification in Twitter to Improve Information Filtering. Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval (New York, NY, USA, 2010), 841--842.
35. stop-words - Stop words - Google Project Hosting: https://code.google.com/p/stop-words/. Accessed: 2014--11-22.
36. Tai, Y.-J. and Kao, H.-Y. 2013. Automatic Domain-Specific Sentiment Lexicon Generation with Label Propagation. Proceedings of International Conference on Information Integration and Web-based Applications & Services (New York, NY, USA, 2013), 53:53--53:62.
37. Thabtah, F., Eljinini, M., Zamzeer, M. and Hadi, W. 'el 2009. Naïve Bayesian Based on Chi Square to Categorize Arabic. IBIMA. 10, (2009), 158--163.
38. The Arab Spring: A Year Of Revolution: http://www.npr.org/2011/12/17/143897126/the-arab-spring-a-year-of-revolution. Accessed: 2017--03-01.
39. Tong, S. and Koller, D. 2001. Support Vector Machine Active Learning with Applications to Text Classification. Journal of Machine Learning Research. 2, Nov (2001), 45--66.
40. Tong, S. and Koller, D. 2002. Support Vector Machine Active Learning with Applications to Text Classification. J. Mach. Learn. Res. 2, (Mar. 2002), 45--66.
41. Turney, P.D. 2001. Mining the Web for Synonyms: PMI-IR Versus LSA on TOEFL. Proceedings of the 12th European Conference on Machine Learning (London, UK, UK, 2001), 491--502.
42. Turney, P.D. 2002. Thumbs Up or Thumbs Down?: Semantic Orientation Applied to Unsupervised Classification of Reviews. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (Stroudsburg, PA, USA, 2002), 417--424.
43. Wahsheh, H.A., Al-kabi, M.N. and Alsmadi, I.M. 2012. Evaluating Arabic Spam Classifiers Using Link Analysis. Proceedings of the 3rd International Conference on Information and Communication Systems (New York, NY, USA, 2012), 12:1--12:5.
44. Wahsheh, H.A., Al-Kabi, M.N. and Alsmadi, I.M. 2013. SPAR: A system to detect spam in Arabic opinions. 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT) (Dec. 2013), 1--6.
45. Wang, A.H. 2010. Don't follow me: Spam detection in Twitter. Proceedings of the 2010 International Conference on Security and Cryptography (SECRYPT) (Jul. 2010), 1--10.
46. Wiley: An Introduction to Categorical Data Analysis, 2nd Edition - Alan Agresti: http://www.wiley.com/WileyCDA/WileyTitle/productCd-EHEP000369.html. Accessed: 2017--03-16.
47. Winter, S. 2015. Do social media likes & followers = popularity?
48. Wu, S., Hofman, J.M., Mason, W.A. and Watts, D.J. 2011. Who Says What to Whom on Twitter. Proceedings of the 20th International Conference on World Wide Web (New York, NY, USA, 2011), 705--714.
49. Yoon, T., Park, S.-Y. and Cho, H.-G. 2010. A Smart Filtering System for Newly Coined Profanities by Using Approximate String Alignment. 2010 IEEE 10th International Conference on Computer and Information Technology (CIT) (Jun. 2010), 643--650.

Index Terms

• Computing methodologies

  • Machine learning

    • Learning paradigms

      • Supervised learning

• Information systems

  • Data management systems

    • Information integration

      • Data cleaning

  • Information systems applications

    • Collaborative and social computing systems and tools

      • Social networking sites

  • World Wide Web

    • Web applications

      • Social networks

• Security and privacy

  • Human and societal aspects of security and privacy

    • Privacy protections

    • Social aspects of security and privacy