Drift-Resistant Relation Induction for Early Event Discovery in Multilingual Social Streams

Authors

  • Seung-Min Lim Department of Communication, College of Social Sciences, Gyeongsang National University, Jinju-si, Gyeongsangnam-do, Republic of Korea
  • Jun-Young Kang Department of Communication, College of Social Sciences, Gyeongsang National University, Jinju-si, Gyeongsangnam-do, Republic of Korea

DOI:

https://doi.org/10.66421/int.j.datasci.intell.syst53

Keywords:

Relation Induction, Concept Drift, Multilingual Streams, Early Event Discovery

Abstract

Abstract

The proliferation of multilingual social media platforms has transformed the landscape of real-time information dissemination, making these networks critical sources for early event discovery. However, discovering emerging events across diverse languages in continuous data streams presents formidable challenges, primarily due to the rapid evolution of vocabulary and semantic shifts known as concept drift. Traditional static representation models fail to capture the dynamic nature of multilingual conversations, leading to degraded performance and delayed event detection when linguistic contexts change. This paper proposes a novel framework centered on drift-resistant relation induction to address the pervasive issue of concept drift in streaming multilingual data. By continuously monitoring and adapting to semantic variations across languages without requiring extensive retraining, the proposed methodology maintains robust cross-lingual alignments. We introduce a temporal graph optimization strategy that dynamically adjusts relational weights between emerging entities while penalizing anomalous semantic divergence. Extensive evaluations on simulated and real-world multilingual datasets demonstrate that the proposed framework significantly outperforms existing static and adaptive baseline models in both event detection accuracy and early discovery latency. The findings highlight the critical importance of incorporating drift-awareness into streaming relation extraction pipelines and offer a scalable solution for global crisis monitoring, financial forecasting, and geopolitical trend analysis

References

1. Zhao, R., Tang, J., Zeng, W., Chen, Z., & Zhao, X. (2024, October). Zero-shot knowledge graph question generation via multi-agent llms and small models synthesis. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (pp. 3341-3351).

2. Mo, Z. A Study on Chinese-English Bilingual Question Answering Systems Using Cross-Lingual Pre-Trained Models. October 2025. Image Processing, Electronics and Computers, DOI, 10.

3. Li, P., Yu, X., Peng, H., Xian, Y., Wang, L., Sun, L., ... & Yu, P. S. (2024). Relational prompt-based pre-trained language models for social event detection. ACM Transactions on Information Systems, 43(1), 1-43.

4. Sang, Y. (2025, July). Towards explainable rag: Interpreting the influence of retrieved passages on generation. In 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC) (pp. 397-400). IEEE.

5. Tang, J., Wang, Z., Gong, Z., Yu, J., Zhu, X., & Yin, J. (2025, April). Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 25246-25254).

6. Tang, J., Yang, Y., Yu, J., Wang, Z. X., Liang, H., Yao, L., & Yin, J. (2025, November). Unco: Uncertainty-driven collaborative framework of large and small models for grounded multimodal ner. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 7644-7662).

7. Su, Yiyun, et al. "Agentic-SQL Taxonomy: A Survey of Autonomous and Interactive Text-to-SQL with LLMs." (2026).

8. Cao, Y., Jing, L., Wang, Y., Shi, D., Yu, C., & Xing, J. (2026, June). Dual-Pathway Diffusion for Hand Correction in Synthetic Portraits: Global Context Aware and Local Structure Refinement. In Proceedings of the 2026 International Conference on Multimedia Retrieval (pp. 1899-1907).

9. Qiu, Z., Lyu, H., Xiong, W., & Luo, J. (2025). Can llms simulate social media engagement? a study on action-guided response generation. arXiv preprint arXiv:2502.12073.

10. Tang, J., Yuan, X., Liu, J., Yu, J., Dong, X., Chen, L., ... & Yin, J. (2026). SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition. arXiv preprint arXiv:2604.20146.

11. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT.

12. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

13. Banerjee, S., & Lavie, A. (2005). METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and/or Summarization.

14. Li, Q., Ye, Q., Zhang, N., Zhang, W., & Hu, F. (2025). Digital-twin-enabled industrial IoT: Vision, framework, and future directions. IEEE Wireless Communications, 32(6), 173-181.

15. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.

16. Liang, R., Xu, S., Xie, C., Chen, J., Ren, F., Yang, S., & Yabe, T. (2026). Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency. Advances in Neural Information Processing Systems, 38, 99445-99471.

17. Hu, H., Yang, Y., Zhao, Q., & Zhang, C. (2022, June). On the role of discount factor in offline reinforcement learning. In International conference on machine learning (pp. 9072-9098). PMLR.

18. Yang, Z., Hu, D., Guo, Q., Zuo, L., & Ji, W. (2023). Visual E 2 C: AI-driven visual end-edge-cloud architecture for 6G in low-carbon smart cities. IEEE Wireless Communications, 30(3), 204-210.

19. Li, H., Zheng, T., Peng, Y., & BouDagher-Fadel, M. K. (2023). The fusulinids in a middle-late Permian carbonate platform (from Maokou to Wuchiapingian stage) in eastern Sichuan Basin, China. In Stratigraphy & Timescales (Vol. 8, pp. 413-435). Academic Press.

20. Xing, Z. (2026, May). Design of High-Bandwidth DDR5 MRDIMM Memory Modules for AI Servers. In 2026 IEEE 6th International Conference on Electronic Technology, Communication and Information (ICETCI) (pp. 307-311). IEEE.

21. Emani, M., Xie, Z., Raskar, S., Sastry, V., Arnold, W., Wilson, B., ... & Boyd, M. (2022, November). A comprehensive evaluation of novel AI accelerators for deep learning workloads. In 2022 IEEE/ACM international workshop on performance modeling, benchmarking and simulation of high performance computer systems (PMBS) (pp. 13-25). IEEE.

Downloads

Published

2026-08-17