On detecting urgency in short crisis messages using minimal supervision and transfer learning

Abstract

Humanitarian disasters have been on the rise in recent years due to the effects of climate change and socio-political situations such as the refugee crisis. Technology can be used to best mobilize resources such as food and water in the event of a natural disaster, by semi-automatically flagging tweets and short messages as indicating an urgent need. The problem is challenging not just because of the sparseness of data in the immediate aftermath of a disaster, but because of the varying characteristics of disasters in developing countries (making it difficult to train just one system) and the noise and quirks in social media. In this paper, we present a robust, low-supervision social media urgency system that adapts to arbitrary crises by leveraging both labeled and unlabeled data in an ensemble setting. The system is also able to adapt to new crises where an unlabeled background corpus may not be available yet by utilizing a simple and effective transfer learning methodology. Experimentally, our transfer learning and low-supervision approaches are found to outperform viable baselines with high significance on myriad disaster datasets.

Explaining population variation after the 2016 Central Italy earthquake using Call Data Records and Twitter

“…Crisis informatics is the term that describes the analysis and processing of real-world data, in particular, social media, to support policymakers and optimize resources during crisis (Kejriwal & Zhou, 2020). It is possible to extrapolate from Twitter data the sentiments to assess post-disaster recovery.…”

Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm

“…Several articles have reported how to retrieve beneficial information from websites in the event of a disaster [25][26][27]. These techniques are mainly based on the characteristics used to identify crisis-related information.…”

“…They conducted experiments with quakes, flood, storm, and wildfire datasets. In order to detect emergency tweets, Kejriwal and Zhou [27] utilized low-supervision and transfer learning-based methods. They conducted experiments with datasets from the earthquakes in Kerala, Macedonia, and Nepal.…”

Word embeddings and deep learning for location prediction: tracking Coronavirus from British and American tweets

“…During the last decade, the computer science field witnessed a considerable resort to word embedding models Arora and Kansal (2019), Tshimula et al (2020), Guellil et al (2020), Kejriwal and Zhou (2020).The principle of these models (also referred to as distributed word representation) is to map related words to nearby points in the space given a corpus of relationships. That is to say, words occurring in similar contexts have similar vector representations and geometric distances between them reflect the degree of their relationships.…”