International Journal of Computer Science & Network Security

국제컴퓨터통신보호논문지학회 (International Journal of Computer Science & Network Security)
권호 표지
DOI QR코드

DOI QR Code

Federated Learning and LLM-based Social Media Comment Classification System Using Crowdsourcing Techniques

  • 투고 : 2024.10.05
  • 발행 : 2024.10.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Currently, on social media, malicious comments have emerged as a serious issue. Existing artificial intelligence-based comment classification systems have limitations due to data bias and overfitting. To address this, this study proposed a novel comment classification system that combines crowdsourcing and federated learning. This system collects data from various users and utilizes a large language model like KoBERT through federated learning to classify comments accurately while protecting user privacy. It is expected to provide higher accuracy than existing methods and improve significantly the efficiency of detecting malicious comments. The proposed system can be applied to social media platforms and online communities.

키워드

과제정보

This work was financially supported by Baewha Women's University.

참고문헌

  1. Wang, Jyun-Cheng, Gabriel Indra Widi Tamtama, and Retnani Latifah. "Civil or Uncivil: Seeing the Role of User Actors and Providing Comments on Social Media." 2024 21st International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON). IEEE, pp.001-006, 2024. 
  2. M Behnke, N Briner, D Cullen, K Schwerdtfeger, J Warren, R Basnet, T Doleck, "Feature engineering and machine learning model comparison for malicious activity detection in the dns-over-https protocol.", IEEE Access, 9, 12, pp.129902-129916, 2021. 
  3. VG Tarun, R Sivasakthivel, G Ramar, M Rajagopal, G Sivaraman, "Exploring BERT and Bi-LSTM for Toxic Comment Classification: A Comparative Analysis." 2024 Second International Conference on Data Science and Information System (ICDSIS). IEEE, pp.001-006, 2024. 
  4. https://github.com/SKTBrain/KoBERT 
  5. Hasani, Muhammad Fikri, "Investigating the Combination between Pre-processing Technique and Text Vectorization for Machine Learning Model in Investor Comment Classification." 2023 International Workshop on Artificial Intelligence and Image Processing (IWAIIP). IEEE, pp.001-005, 2023. 
  6. Niharika Prasanna Kumar, Kishore Srinivasan, Dhanesh Ramesh, "Analyzing Public Sentiment Towards LLM: A Twitter-Based Sentiment Analysis", 2023 International Conference on the Confluence of Advancements in Robotics, Vision and Interdisciplinary Technology Management (IC-RVITM). IEEE, pp.001-008, 2023. 
  7. H Zhao, H Chen, TA Ruggles, Y Feng, D Singh, HJ Yoon, "Improving Text Classification with Large Language Model-Based Data Augmentation." Electronics, 13,13, pp.001-014, 2024. 
  8. M Mishra, P Kumar, R Bhat, R Murthy V, D Contractor, S Tamilselvam, "Prompting with Pseudo-Code Instructions", The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.001-020, 2023. 
  9. Kadija M. Tahlil, Ucheoma Nwaozuru, Donaldson F. Conserve, Ujunwa F. OnyeamaID, Victor OjoID, Suzanne Day, Jason J. Ong, Weiming Tang, Nora E. Rosenberg, Titi Gbajabiamila, Susan Nkengasong, Chisom Obiezu-Umeh, David Oladele, Juliet Iwelunmor, Oliver EzechiID, Joseph D. Tucker, "Crowdsourcing to support training for public health: A scoping review." PLOS global public health, 3, 7, pp.001-017, 2023. 
  10. Wonsik Shim, Jeayeon Byun, Minjung Kim, "Analysis of Wikipedia Citations in Peer-Reviewed Journal Articles", Journal of the Korean Society for Library and Information Science, 42, 2, pp.247-264, 2013. 
  11. H Zhu, N Wang, SCK Chau, M Khonji, "Blockchain-enabled Decentralized Anonymous Crowdsourcing Based on Anonymous Payments." 2023 IEEE International Conference on Blockchain and Cryptocurrency (ICBC). IEEE, pp.001-002, 2023. 
  12. Ang, Kenneth Li Minn, Jasmine Kah Phooi Seng, Ericmoore Ngharamike, "Towards crowdsourcing internet of things (crowd-iot): Architectures, security and applications." Future Internet, 14, 2, pp.001-050, 2022. 
  13. Hanna Abi Akl, "A ML-LLM pairing for better code comment classification", Forum for Information Retrieval Evaluation 2023, pp001-011, 2023. 
  14. Hao Li, Chengcheng Li, Jian Wang, Aimin Yang, Zezhong Ma, Zunqian Zhang, Dianbo Hua, "Review on security of federated learning and its application in healthcare", Future Generation Computer Systems, 144, pp.271-290, 2023. 
  15. Shubham, Gagandeep, Vidushi Agarwal, Sujata Pal, "IoT Data Security: An Integration of Blockchain and Federated Learning", 2023 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, pp.001-006, 2023. 
  16. Nair, Akarsh K., Jayakrushna Sahoo, and Ebin Deni Raj, "Privacy preserving Federated Learning framework for IoMT based big data analysis using edge computing." Computer Standards & Interfaces 86, 103720, pp.001-020, 2023. 
  17. Juyal, Prachi, and Amit Kundaliya. "A Comparative Study of Hybrid Deep Sentimental Analysis Learning Techniques with CNN and SVM." 2023 IEEE World Conference on Applied Intelligence and Computing (AIC). IEEE, pp.001-005, 2023. 
  18. PG Shambharkar, H Singh, HR Raghav, H Verma, "Exploring the Efficacy of Deep Learning Models for Multiclass Toxic Comment Classification in Social Media Using Natural Language Processing." 2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI). IEEE, pp.001-008, 2023. 
  19. Feng, Xinyue, Niwat Angkawisittpan, and Xiaoqing Yang, "A CNN-BiLSTM algorithm for Weibo emotion classification with attention mechanism." Mathematical Models in Engineering, 10, 2, pp.001-011, 2024. 
  20. Lior Zoref, "Mindsharing: The Art of Crowdsourcing Everything", Penguin Putnam, 2015. 
  21. Heeji Park, Jimin Ha, Hyaelim Park, Jungho Kang, "Comment Classification System using Deep Learning Classification Algorithm based on Crowdsourcing", Proceedings of the Korea Information Processing Society Conference, 11a, pp.864-867, 2021.