Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses
This addresses societal polarization caused by biased news and offensive comments, offering a counterspeech approach to mitigate harm without violating free speech, but it is incremental as it builds on existing counterspeech methods by applying them to a new context.
The study tackled the problem of media bias being reinforced by offensive comments by introducing a dataset linking bias, offensive comments, and counterspeech, finding that over 70% of offensive comments support biased articles. It compared human and LLM-generated counterspeech, improving LLM responses through few-shot learning and news background integration to enhance diversity and relevance.
Biased news contributes to societal polarization and is often reinforced by hostile reader comments, constituting a vital yet often overlooked aspect of news dissemination. Our study reveals that offensive comments support biased content, amplifying bias and causing harm to targeted groups or individuals. Counterspeech is an effective approach to counter such harmful speech without violating freedom of speech, helping to limit the spread of bias. To the best of our knowledge, this is the first study to explore counterspeech generation in the context of news articles. We introduce a manually annotated dataset linking media bias, offensive comments, and counterspeech. We conduct a detailed analysis showing that over 70\% offensive comments support biased articles, amplifying bias and thus highlighting the importance of counterspeech generation. Comparing counterspeech generated by humans and large language models, we find model-generated responses are more polite but lack the novelty and diversity. Finally, we improve generated counterspeech through few-shot learning and integration of news background information, enhancing both diversity and relevance.