DOI QR코드

DOI QR Code

An Ensemble Approach for Cyber Bullying Text messages and Images

  • Zarapala Sunitha Bai (Department of Computer Science and Engineering, R.V.R. and J.C. College of Engineering, Acharya Nagarjuna University) ;
  • Sreelatha Malempati (Department of Computer Science and Engineering, R.V.R. and J.C. College of Engineering)
  • Received : 2023.11.05
  • Published : 2023.11.30

Abstract

Text mining (TM) is most widely used to find patterns from various text documents. Cyber-bullying is the term that is used to abuse a person online or offline platform. Nowadays cyber-bullying becomes more dangerous to people who are using social networking sites (SNS). Cyber-bullying is of many types such as text messaging, morphed images, morphed videos, etc. It is a very difficult task to prevent this type of abuse of the person in online SNS. Finding accurate text mining patterns gives better results in detecting cyber-bullying on any platform. Cyber-bullying is developed with the online SNS to send defamatory statements or orally bully other persons or by using the online platform to abuse in front of SNS users. Deep Learning (DL) is one of the significant domains which are used to extract and learn the quality features dynamically from the low-level text inclusions. In this scenario, Convolutional neural networks (CNN) are used for training the text data, images, and videos. CNN is a very powerful approach to training on these types of data and achieved better text classification. In this paper, an Ensemble model is introduced with the integration of Term Frequency (TF)-Inverse document frequency (IDF) and Deep Neural Network (DNN) with advanced feature-extracting techniques to classify the bullying text, images, and videos. The proposed approach also focused on reducing the training time and memory usage which helps the classification improvement.

Keywords

Acknowledgement

This work is done under the grant received (6/41) by Deanship of research at Islamic University of Madinah (IUM) for research that studies the economic effect of COvid-19 pandemic. We also give special thanks to the administration of IUM for their support in every aspect.

References

  1. Prusa, J.D., Khoshgoftaar, T.M. Improving deep neural network design with new text data representations. J Big Data 4, 7 (2017). https://doi.org/10.1186/s40537-017-0065-8.
  2. S. Ozcan, A. Homayounfard, C. Simms and J. Wasim, "Technology Roadmapping Using Text Mining: A Foresight Study for the Retail Industry," in IEEE Transactions on Engineering Management, vol. 69, no. 1, pp. 228-244, Feb. 2022, doi: 10.1109/TEM.2021.3068310.
  3. Zhang X, LeCun Y. Text understanding from scratch. 2015. arXiv preprint arXiv:1502.01710.
  4. Prusa JD, Khoshgoftaar TM, Dittman DJ. Impact of feature selection techniques for tweet sentiment classification. In: Proceedings of the 28th International FLAIRS Conference; 2015. p. 299-304.
  5. John Hani, Mohamed Nashaat, Mostafa Ahmed, Zeyad Emad, Eslam Amer and Ammar Mohammed, "Social Media Cyberbullying Detection using Machine Learning", International Journal of Advanced Computer Science and Applications(IJACSA), 10(5), 2019. http://dx.doi.org/10.14569/IJACSA.2019.01005
  6. Prusa JD, Khoshgoftaar TM, Dittman DJ. Impact of feature selection techniques for tweet sentiment classification. In: Proceedings of the 28th International FLAIRS Conference; 2015. p. 299-304.
  7. Agarwal A, Xie B, Vovsha I, Rambow O, Passonneau R. Sentiment analysis of twitter data. In: Proceedings of the workshop on languages in social media. Association for Computational Linguistics; 2011. p. 30-8.
  8. K. Maity, S. Saha and P. Bhattacharyya, "Emoji, Sentiment and Emotion Aided Cyberbullying Detection in Hinglish," in IEEE Transactions on Computational Social Systems, 2022, doi:10.1109/TCSS.2022.3183046.
  9. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Info Proc Syst. 2012: 1097-105.
  10. M. Anand and R. Eswari, "Classification of Abusive Comments in Social Media using Deep Learning," 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), 2019, pp. 974-977, doi: 10.1109/ICCMC.2019.8819734.
  11. Y. Li, A. Algarni, M. Albathan, Y. Shen and M. A. Bijaksana, "Relevance Feature Discovery for Text Mining," in IEEE Transactions on Knowledge and Data Engineering, vol. 27, no. 6, pp. 1656-1669, 1 June 2015, doi: 10.1109/TKDE.2014.2373357.
  12. Chikashi Nobata, Joel Tetreault, Achint Thomas, Yashar Mehdad and Yi Chang, "Abusive Language Detection in Online User Content", Proceedings of the 25th International Conference on World Wide Web (WWW '16). International World Wide Web Conferences Steering Committee, pp. 145-153, 2016.
  13. Yoon Kim, "Convolutional neural networks for sentence classification", EMNLP. Association for Computational Linguistics, pp. 1746-1751, 2014.
  14. M.O.Ibrohim, Muhammad Akbar Setiadi, and Indra Budi. 2019. Identification of hate speech and abusive language on indonesian Twitter using the Word2vec, part of speech and emoji features. In Proceedings of the International Conference on Advanced Information Science and System (AISS '19). Association for Computing Machinery, New York, NY, USA, Article 18, 1-5.
  15. Z. Waseem and D. Hovy. 2016. Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In Proceedings of the NAACL Student Research Workshop, 88--93.
  16. F. D. Vigna, A. Cimino, F. Dell'Orletta, M. Petrocchi, and M. Esconi. 2017. Hate me, hate me not: Hate speech detection on facebook. In Proceedings of the First Italian Conference on Cybersecurity (ITASEC17), 86--95.
  17. H. Yenala, A. Jhanwar, M. K. Chinnakotla, and J. Goyal. 2017. Deep learning for detecting inappropriate content in text. In International Journal of Data Science and Analytics.
  18. M. M. Islam, M. A. Uddin, L. Islam, A. Akter, S. Sharmin and U. K. Acharjee, "Cyberbullying Detection on Social Networks Using Machine Learning Approaches," 2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), 2020, pp. 1-6, doi: 10.1109/CSDE50874.2020.9411601.
  19. A. Shekhar and M. Venkatesan, "A Bag-of-Phonetic-Codes Modelfor Cyber-Bullying Detection in Twitter," 2018 International Conference on Current Trends towards Converging Technologies (ICCTCT), 2018, pp. 1-7.
  20. C. Sharma, R. Ramakrishnan, A. Pendse, P. Chimurkar and K. T. Talele, "Cyber-Bullying Detection Via Text Mining and Machine Learning," 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2021, pp. 1-6.
  21. A. Wadhwani, P. Jain and S. Sahu, "Injurious Comment Detection and Removal utilizing Neural Network," 2021 International Conference on Innovative Practices in Technology and Management (ICIPTM), 2021, pp. 165-168.
  22. C. S. Wu and U. Bhandary, "Detection of Hate Speech in Videos Using Machine Learning," 2020 International Conference on Computational Science and Computational Intelligence (CSCI), 2020, pp. 585-590.
  23. Murshed, J. Abawajy, S. Mallappa, M. A. N. Saif and H. D. E. Al-Ariki, "DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform," in IEEE Access, vol. 10, pp. 25857-25871, 2022. https://doi.org/10.1109/ACCESS.2022.3153675
  24. Zarapala Sunitha Bai, Sreelatha Malempati, "An Enhanced Text Mining Approach using Ensemble Algorithm for Detecting Cyber Bullying" International Journal of Engineering Trends and Technology, vol. 70, no. 9, pp. 393-399, 2022. https://doi.org/10.14445/22315381/IJETT-V70I9P240
  25. Y. Bengio, "Learning deep architectures for AI," Foundations and Trends in Machine Learning, vol. 2, no. 1, pp. 1-127, 2009. https://doi.org/10.1561/2200000006
  26. G. E. Hinton, S. Osindero, and Y. W. Teh, "A fast learning algorithm for deep belief nets.," Neural computation, vol. 18, no. 7, pp. 1527-54, 2006. https://doi.org/10.1162/neco.2006.18.7.1527