Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis management
This addresses the problem of crisis managers needing adaptable information extraction from social media, though it is incremental in combining existing techniques.
The paper tackles the challenge of adapting machine learning models to evolving crises by bridging supervised classification and unsupervised topic modeling, showing that BERT embeddings finetuned on crisis tweets outperform traditional topic models in both automatic and human evaluations for a snowstorm dataset.
Social media such as Twitter provide valuable information to crisis managers and affected people during natural disasters. Machine learning can help structure and extract information from the large volume of messages shared during a crisis; however, the constantly evolving nature of crises makes effective domain adaptation essential. Supervised classification is limited by unchangeable class labels that may not be relevant to new events, and unsupervised topic modelling by insufficient prior knowledge. In this paper, we bridge the gap between the two and show that BERT embeddings finetuned on crisis-related tweet classification can effectively be used to adapt to a new crisis, discovering novel topics while preserving relevant classes from supervised training, and leveraging bidirectional self-attention to extract topic keywords. We create a dataset of tweets from a snowstorm to evaluate our method's transferability to new crises, and find that it outperforms traditional topic models in both automatic, and human evaluations grounded in the needs of crisis managers. More broadly, our method can be used for textual domain adaptation where the latent classes are unknown but overlap with known classes from other domains.