The challenges of temporal alignment on Twitter during crises
This addresses the challenge of maintaining NLP effectiveness for crisis responders and analysts on social media, though it is incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of rapid language change on Twitter during crises, which degrades NLP system performance, and proposes domain adaptation methods to mitigate this, showing improvements over baselines in diverse crisis datasets.
Language use changes over time, and this impacts the effectiveness of NLP systems. This phenomenon is even more prevalent in social media data during crisis events where meaning and frequency of word usage may change over the course of days. Contextual language models fail to adapt temporally, emphasizing the need for temporal adaptation in models which need to be deployed over an extended period of time. While existing approaches consider data spanning large periods of time (from years to decades), shorter time spans are critical for crisis data. We quantify temporal degradation for this scenario and propose methods to cope with performance loss by leveraging techniques from domain adaptation. To the best of our knowledge, this is the first effort to explore effects of rapid language change driven by adversarial adaptations, particularly during natural and human-induced disasters. Through extensive experimentation on diverse crisis datasets, we analyze under what conditions our approaches outperform strong baselines while highlighting the current limitations of temporal adaptation methods in scenarios where access to unlabeled data is scarce.