Examining Temporal Bias in Abusive Language Detection
This addresses the problem of declining model accuracy for abusive language detection over time, which is crucial for maintaining effective moderation in online platforms, though it is incremental as it focuses on analyzing and highlighting an existing issue rather than introducing a novel solution.
The study investigated temporal bias in abusive language detection models, finding that models trained on historical data experience a significant performance drop over time due to evolving language and social norms.
The use of abusive language online has become an increasingly pervasive problem that damages both individuals and society, with effects ranging from psychological harm right through to escalation to real-life violence and even death. Machine learning models have been developed to automatically detect abusive language, but these models can suffer from temporal bias, the phenomenon in which topics, language use or social norms change over time. This study aims to investigate the nature and impact of temporal bias in abusive language detection across various languages and explore mitigation methods. We evaluate the performance of models on abusive data sets from different time periods. Our results demonstrate that temporal bias is a significant challenge for abusive language detection, with models trained on historical data showing a significant drop in performance over time. We also present an extensive linguistic analysis of these abusive data sets from a diachronic perspective, aiming to explore the reasons for language evolution and performance decline. This study sheds light on the pervasive issue of temporal bias in abusive language detection across languages, offering crucial insights into language evolution and temporal bias mitigation.