Blocking Abuse Comments in Social Network Using Selection Set Algorithm
Keywords:
abuse comments, hate speech detection, one-against-one, multiclass classification, set algorithmAbstract
Blocking abusive comments on social media is a pressing issue that impacts both individuals and society at large. The challenge of automatically identifying abusive content has become increasingly difficult due to the nuanced language and informal communication styles prevalent on these platforms. The brevity and casual nature of posts often lead to ambiguous expressions, complicating the interpretation of intent. This issue is further exacerbated by the presence of uncertain or contextually vague content. While various methods exist for detecting abusive comments, they often struggle to differentiate between different types of hate speech due to their ambiguous characteristics, resulting in lower accuracy. This paper presents a novel approach for blocking abusive comments by employing a Selection Set Algorithm integrated with a Multi-Layer Perceptron (MLP) model. This approach enhances the classification of abusive comment types by addressing the challenges posed by ambiguity and the overlapping boundaries of different categories. The Selection Set Algorithm is designed to manage uncertainty and vagueness in classification decisions, offering a more robust framework for dealing with complex scenarios. The MLP model, utilizing a one-against-one classification strategy, captures intricate relationships among various types of abusive comments, effectively addressing the overlaps and ambiguities present. The evaluation of this model highlights the effectiveness of the Selection Set Algorithm, employing class probabilities from multiple classifiers to yield comprehensive insights into classification results. The findings indicate a significant performance improvement in blocking abusive comments through the proposed approach.
Downloads
References
T. Ahmed, S. Ivan, M. Kabir, H. Mahmud, and K. Hasan, “Performance analysis of transformer-based architectures and their ensembles to detect trait-based abuse comments,” Social Network Analysis and Mining, vol. 12, no. 1, p. 99, 2022, doi: 10.1007/s13278-022-00830-0.
M. Alotaibi, B. Alotaibi, and A. Razaque, “A multichannel deep learning framework for abuse comments detection on social media,” Electronics, vol. 10, no. 21, p. 2664, 2021, doi: 10.3390/electronics10212664.
M. Arif, “A systematic review of machine learning algorithms in abuse comments detection: Future directions and challenges,” Journal of Information Security and Cybercrimes Research, vol. 4, no. 1, pp. 1–26, 2021, doi: 10.18844/jiscr.v4i1.5583.
R. Bayari and A. Bensefia, “Text mining techniques for abuse comments detection: State of the art,” Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 783–790, 2021, doi: 10.25046/aj050949.
A. Chhabra and D. K. Vishwakarma, “A literature survey on multimodal and multilingual automatic hate speech identification,” Multimedia Systems, vol. 29, no. 3, pp. 1203–1230, 2023, doi: 10.1007/s00530-022-00892-1.
R. K. Chilukuri, H. K. Kakarla, and K. S. Rao, “Radar signal recognition based on multilayer perceptron neural network,” International Journal of Electrical and Computer Engineering Systems, vol. 14, no. 1, pp. 29–36, 2023, doi: 10.11591/ijece.v14i1.8962.
T. D. Cox and J. Raditch, “Teaching online and abuse comments: Exploring abuse comments policies,” Journal of Effective Teaching in Higher Education, vol. 5, no. 1, pp. 71–89, 2022, doi: 10.36021/jethe.v5n1.40.
Y. Guo and A. Şengür, “A novel image segmentation algorithm based on neutrosophic filtering and level set,” Neutrosophic Sets and Systems, vol. 1, no. 49, pp. 46–49, 2013, doi: 10.5281/zenodo.1166145.
M. I. Islam, F. M. Yunus, E. Kabir, and R. Khanam, “Evaluating risk and protective factors for suicidality and self-harm in Australian adolescents with traditional bullying and abuse comments victimizations,” American Journal of Health Promotion, vol. 36, no. 1, pp. 73–83, 2022, doi: 10.1177/08901171211017254.
A. K. Jain, S. R. Sahoo, and J. Kaubiyal, “Online social networks security and privacy: Comprehensive review and analysis,” Complex & Intelligent Systems, vol. 7, no. 5, pp. 2157–2177, 2021, doi: 10.1007/s40747-021-00266-5.
B.-B. Jia, J.-Y. Liu, J.-Y. Hang, and M.-L. Zhang, “Learning label-specific features for decomposition-based multi-class classification,” Frontiers of Computer Science, vol. 17, no. 6, p. 176348, 2023, doi: 10.1007/s11704-022-00283-x.
C. S. Manigandaa, V. D. Ambeth Kumar, G. Ragunath, R. Venkatesan, and N. Senthil Kumar, “De-noising and segmentation of medical images using neutrophilic sets,” Full Length Article, vol. 11, no. 2, pp. 111–111, 2023, doi: 10.11648/j.ijmr.20231102.12.
E. W. Pamungkas, V. Basile, and V. Patti, “A joint learning approach with knowledge injection for zero-shot cross-lingual hate speech detection,” Information Processing & Management, vol. 58, no. 4, p. 102544, 2021, doi: 10.1016/j.ipm.2021.102544.
J. Pyżalski, P. Plichta, A. Szuster, and J. Barlińska, “Abuse comments characteristics and prevention—What can we learn from narratives provided by adolescents and their teachers?,” International Journal of Environmental Research and Public Health, vol. 19, no. 18, p. 11589, 2022, doi: 10.3390/ijerph191811589.
C. Raj, A. Agarwal, G. Bharathy, B. Narayan, and M. Prasad, “Abuse comments detection: Hybrid models based on machine learning and natural language processing techniques,” Electronics, vol. 10, no. 22, p. 2810, 2021, doi: 10.3390/electronics10222810.
J. Rao, L. Peng, J. Rao, and X. Cao, “Modified taxonomy method for double-valued neutrosophic number MADM and applications to physical education teaching quality evaluation in colleges and universities,” Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10581–10590, 2023, doi: 10.3233/JIFS-211314.
T. Wullach, A. Adler, and E. Minkov, “Towards hate speech detection at large via deep generative modeling,” IEEE Internet Computing, vol. 25, no. 2, pp. 48–57, 2020, doi: 10.1109/MIC.2020.2986588.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
