Are generative AI text annotations systematically biased?

This paper investigates bias in GLLM annotations by conceptually replicating manual annotations of Boukes (2024). Using various GLLMs (Llama3.1:8b, Llama3.3:70b, GPT4o, Qwen2.5:72b) in combination with five different prompts for five concepts (political content, interactivity, rationality, incivility, and ideology). We find GLLMs perform adequate in terms of F1 scores, but differ from manual annotations in terms of prevalence, yield substantively different downstream results, and display systematic bias in that they overlap more with each other than with manual annotations. Differences in F1 scores fail to account for the degree of bias.

Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues

In the contemporary media landscape, with the vast and diverse supply of news, it is increasingly challenging to study such an enormous amount of items without a standardized framework. Although attempts have been made to organize and compare news items on the basis of news values, news genres receive little attention, especially the genres in a news consumer's perception. Yet, perceived news genres serve as an essential component in exploring how news has developed, as well as a precondition for understanding media effects. We approach this concept by conceptualizing and operationalizing a non-discrete framework for mapping news items in terms of genre cues. As a starting point, we propose a preliminary set of dimensions consisting of "factuality" and "formality". To automatically analyze a large amount of news items, we deliver two computational models for predicting news sentences in terms of the said two dimensions. Such predictions could then be used for locating news items within our framework. This proposed approach that positions news items upon a multidimensional grid helps in deepening our insight into the evolving nature of news genres.