Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation
This work addresses the lack of training data for hate speech detection in limited data contexts, which is an incremental improvement for social media moderation in low-resource languages.
The paper tackles the problem of hate speech detection in low-resource languages by generating synthetic training data from high-resource language examples, showing that models trained on this synthetic data perform comparably to or better than those trained on limited real data in Hindi and Vietnamese.
A growing body of work has focused on text classification methods for detecting the increasing amount of hate speech posted online. This progress has been limited to only a select number of highly-resourced languages causing detection systems to either under-perform or not exist in limited data contexts. This is majorly caused by a lack of training data which is expensive to collect and curate in these settings. In this work, we propose a data augmentation approach that addresses the problem of lack of data for online hate speech detection in limited data contexts using synthetic data generation techniques. Given a handful of hate speech examples in a high-resource language such as English, we present three methods to synthesize new examples of hate speech data in a target language that retains the hate sentiment in the original examples but transfers the hate targets. We apply our approach to generate training data for hate speech classification tasks in Hindi and Vietnamese. Our findings show that a model trained on synthetic data performs comparably to, and in some cases outperforms, a model trained only on the samples available in the target domain. This method can be adopted to bootstrap hate speech detection models from scratch in limited data contexts. As the growth of social media within these contexts continues to outstrip response efforts, this work furthers our capacities for detection, understanding, and response to hate speech.