Sistemas fuzzy complementam a detecção de socialbots por aprendizado de máquina / Fuzzy systems complement machine learning socialbot detection

Authors

  • Carla Chrystina de Castro Pacheco Ferreira Brazilian Journals Publicações de Periódicos, São José dos Pinhais, Paraná
  • Alex de Vasconcellos Garcia
  • Ronaldo Moreira Salles
  • Raphael Carlos dos Santos Machado

DOI:

https://doi.org/10.34117/bjdv5n12-308

Keywords:

Redes Sociais, Detecção de Socialbot, Aprendizado de Máquina, Lógica Fuzzy, Comitê de Classificação.

Abstract

A detecção de socialbots em Redes Sociais Online tem sido objeto de diversos estudos baseados em aprendizado de máquina. Este trabalho apresenta o uso de um comitê de classificadores para melhorar a acurácia da identificação de socialbots. O comitê associa o conhecimento obtido por algoritmos de aprendizado de máquina ao conhecimento heurístico humano, obtido por entrevistas e formalizado por regras fuzzy. Os resultados mostram que estas abordagens são complementares, uma vez que o uso conjunto destes algoritmos em um comitê apresenta uma acurácia acima de 93%, maior do que os mesmos algoritmos utilizados isoladamente.

 

 

References

Freitas, C. A. et al.; Reverse engineering socialbot infiltration strategies in Twitter. IEEE/ACM ASONAM, 2015.

Tumasjan, A. et al.; Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment. AAAI ICWSM, Washington, DC, EUA, 2010.

Dickerson, J. P. et al.; Using sentiment to detect bots on twitter: Are humans more opinionated than bots? IEEE/ACM ASONAM, p. 620–627, 2014.

Bollen, J. et al.; Twitter mood predicts the stock market. Journal of Computational Science, Vol. 2, p. 1–8, 2011.

Edwards, C. et al.; Is that a bot running the social media feed? Testing the differences in perceptions of communication quality for a human agent and a bot agent on Twitter. Computers in Human Behavior, Vol. 33, p.372–376, 2014.

Mander, J. e McGrath, F.; GWI Social GlobalWebIndex’s quarterly report on the latest trends in social networking,https://cdn2.hubspot.net/hubfs/304927/Downloads/GWI-Social-Summary-Q1-2017.pdf , acessado em agosto de 2018.

Pacheco, C. et al.; A Methodology for Constructing Labeled Data Sets for Socialbots Detection. Revista IEEE América Latina, submetido, 2017.

Pacheco, C. et al.; Building Reference Datasets to Support Socialbots Detection. Metrology for Industry 4.0 and IoT. IEEE, 2018.

Zadeh, L. A.; Fuzzy logic. Computer, Vol. 21, N. 4, p. 83–93, Abril, 1988.

Benevenuto, F. et al.; Detecting spammers on Twitter. Collaboration, electronic messaging, anti-abuse and spam conference (CEAS), Vol 6, p.12, 2010.

Joachims, T.; Text categorization with support vector machines: Learning with many relevant features. Nédellec C., Rouveirol C. (eds) Machine Learning: ECML. Lecture Notes in Computer Science, Vol 1398, Springer Berlin Heidelberg, 1998.

Freitas, C. et al.; Socialbots: Implicações na segurança e na credibilidade de serviços baseados no Twitter. SBRC, Santa Catarina, Brasil. p. 603–616, 2014.

Zhang, C. M. e Paxson, V.; Detecting and analyzing automated activity on twitter. Passive and Active Measurement, p.102–111. Springer, 2011.

Cha, M. et al.; Measuring User Influence in Twitter: The Million Follower Fallacy. AAAI ICWSM, Menlo Park, CA, EUA. AAAI Press. p.10-17, 2010.

Breiman, L.; Machine Learning (2001) 45: 5, Kluwer Academic Publisher, doi:10.1023/A:1010933404324

Lee, K. et al.; Seven Months with the Devils: A Long-Term Study of Content Polluters on Twitter. AAAI ICWSM, 2011.

Cresci, S. et al.; A Fake Follower Story: improving fake accounts detection on Twitter. IIT-CNR, Relatório Técnico TR-03, 2014.

Cresci, S. et al.; A Criticism to Society (As Seen by Twitter Analytics). IEEE International Conference on Distributed Computing Systems Workshops (2014), doi:10.1109/ICDCSW.2014.31.

Cresci, S. et al.; Fame for sale: Efficient detection of fake Twitter followers. Decision Support Systems, Vol. 80, p. 56–71, 2015.

Ferrara, E. et al.; The Rise of Social Bots. Communications of the ACM, 2016.

Varol, O. et al.; Online human-bot interactions: Detection, Estimation, and Characterization. AAAI ICWSM, 2017.

OSoMe project, CNetS, IUNI. Botometer. https://botometer.iuni.iu.edu/#!/, acessado em agosto de 2018.

Haustein, S. et al.; Tweets as impact indicators: Examining the implications of automated “bot” accounts on Twitter. Association for Information Science and Technology, 2015.

Wikipedia. Twitterbot; https://en.wikipedia.org/wiki/Twitter_bot, acessado em agosto de 2018.

Prime, M.; The best Twitter bots of 2015 – Quartz (2015); https://qz.com/572763/the-best-twitter-bots-of-2015/, acessado em agosto de 2018.

Gilani, Z. et al.; Of Bots and Humans (on Twitter). ASONAM IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, p. 349-354, 2017.

Alarifi, A. et al.; Twitter turing test: Identifying social machines. Information Sciences – Informatics and Computer Science, Intelligent Systems, Applications. Vol. 372, p. 332–346, 2016.

Pacheco, C. et al.; Detecção de Socialbots em Redes Sociais baseada em atributos quantitativos; Tese de Doutorado, Instituto Militar de Engenharia, Rio de Janeiro, Brasil, 2018.

Sadiq, S. et al.; Aafa: Associative affinity factor analysis for bot detection and stance classification in twitter. IEEE IRI (2017), doi:10.1109/IRI.2017.25.

Hühn, J. e Hüllermeier, E.; Furia: an algorithm for unordered fuzzy rule induction. Data Mining and Knowledge Discovery, Springer US. Vol 19, p. 293, 2009.

Twitter. GET statuses/user timeline — Twitter Developers, 2017. https://developer.twitter.com/en/docs/tweets/timelines/api-reference/get-statuses-user_timeline.html, acessado em agosto de 2018.

Cingolani, P. e Alcalá-Fdez, J.; jfuzzylogic: a robust and flexible fuzzy-logic inference system language implementation. IEEE International Conference on Fuzzy Systems, p. 1–8, 2012.

Kohavi, R.; The Power of Decision Tables. ECML, Creta, Grécia (1995). Springer-Verlag, p. 174–189, doi: 10.1007/3-540-59286-5_57.

Liu, D. C. e Nocedal, J.; On the Limited Memory BFGS Method for Large Scale Optimization. Mathematical Programming, Vol. 45, p.503, Springer-Verlag, 1989.

Frank, E. et al.; Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann, Fourth Edition, 2016.

Published

2019-12-20

How to Cite

Ferreira, C. C. de C. P., Garcia, A. de V., Salles, R. M., & Machado, R. C. dos S. (2019). Sistemas fuzzy complementam a detecção de socialbots por aprendizado de máquina / Fuzzy systems complement machine learning socialbot detection. Brazilian Journal of Development, 5(12), 32413–32426. https://doi.org/10.34117/bjdv5n12-308

Issue

Section

Original Papers