# Interactive Event Sifting using Bayesian Graph Neural Networks

arXiv: https://arxiv.org/abs/2410.05359 · HTML: https://mlsanity.com/paper/2410.05359/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 7 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [CrisisMMD: Multimodal Twitter Datasets from Natural Disasters](https://mlsanity.com/paper/1805.00713/) (2018)
- [Multimodal Categorization of Crisis Events in Social Media](https://mlsanity.com/paper/2004.04917/) (2020)
- [Explainable Fact-checking through Question Answering](https://mlsanity.com/paper/2110.05369/) (2021)
- [Deep Active Learning via Open Set Recognition](https://mlsanity.com/paper/2007.02196/) (2020)
- [Few-shot Learning for Multi-modal Social Media Event Filtering](https://mlsanity.com/paper/2211.10340/) (2022)

## Abstract (arXiv)

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.