Authors:
Mohammad Saad Rafeeq
1
;
Narendra Bijarniya
2
and
Chandramani Chaudhary
1
Affiliations:
1
National Institute of Technology, Calicut, India
;
2
Birla Institute of Technology and Science, Pilani, India
Keyword(s):
Temporal Event Scene Graphs, Event Prediction, Cybercrime, Sequence Modeling, BART, T5, GPT-2.
Abstract:
Cybercrime complaint narratives encompass complex sequences of criminal activities that challenge conventional sequence modeling techniques. This work introduces a framework that employs dynamic temporal event scene graphs to represent each narrative as an evolving, structured network of entities and events. Our approach converts complaint texts into temporal event scene graphs in which nodes symbolize key entities and edges capture interactions, annotated with their sequential order. This structured representation provides a richer and more intuitive understanding of how cybercrime incidents unfold over time. To forecast missing or forthcoming events, we fine-tune a pre-trained BART model using a masked sequence-to-sequence paradigm.Our experiments are performed on a dataset comprising thousands of real-world cybercrime reports, containing roughly 76,000 distinct event descriptions—a scale that introduces significant sparsity and generalization challenges. Our results demonstrate th
at while models such as GPT-2 and T5 struggle to capture robust patterns in this diverse domain, the BART-based approach achieves modest yet promising improvements.
(More)