Characterizing Latent Perspectives of Media Houses Towards Public Figures
This work addresses the need for understanding media biases in news reporting, which is incremental as it applies an existing method (GPT-2 fine-tuning) to a new domain of subjective summarization.
The paper tackled the problem of characterizing media biases towards public figures by proposing a zero-shot generative approach using GPT-2, which generated simple sentences about entities with encouraging results compared to actual corpus characterizations.
Media houses reporting on public figures, often come with their own biases stemming from their respective worldviews. A characterization of these underlying patterns helps us in better understanding and interpreting news stories. For this, we need diverse or subjective summarizations, which may not be amenable for classifying into predefined class labels. This work proposes a zero-shot approach for non-extractive or generative characterizations of person entities from a corpus using GPT-2. We use well-articulated articles from several well-known news media houses as a corpus to build a sound argument for this approach. First, we fine-tune a GPT-2 pre-trained language model with a corpus where specific person entities are characterized. Second, we further fine-tune this with demonstrations of person entity characterizations, created from a corpus of programmatically constructed characterizations. This twice fine-tuned model is primed with manual prompts consisting of entity names that were not previously encountered in the second fine-tuning, to generate a simple sentence about the entity. The results were encouraging, when compared against actual characterizations from the corpus.