| Full text | |
| Author(s): |
Nascimento, Jose
;
Jacobs, Nathan
;
Rocha, Anderson
Total Authors: 3
|
| Document type: | Journal article |
| Source: | 2024 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY, WIFS 2024; v. N/A, p. 5-pg., 2024-01-01. |
| Abstract | |
Forensic analysts often use social media imagery and texts to understand important events. A primary challenge is the initial sifting of irrelevant posts. This work introduces an interactive process for training an event-centric, learning-based multimodal classification model that automates sanitization. We propose a method based on Bayesian Graph Neural Networks (BGNNs) and evaluate active learning and pseudo-labeling formulations to reduce the number of posts the analyst must manually annotate. Our results indicate that BGNNs are useful for social-media data sifting for forensics investigations of events of interest, the value of active learning and pseudo-labeling varies based on the setting, and incorporating unlabelled data from other events improves performance. (AU) | |
| FAPESP's process: | 23/12865-8 - Horus: artificial intelligence techniques to detect and forestall synthetic realities |
| Grantee: | Anderson de Rezende Rocha |
| Support Opportunities: | Research Projects - Thematic Grants |