Fig. 2: Study 2—ingroup solidarity and outgroup hostility in fine-tuned language models on partisan social media data. | Nature Computational Science

Fig. 2: Study 2—ingroup solidarity and outgroup hostility in fine-tuned language models on partisan social media data.

From: Generative language models exhibit social identity biases

Fig. 2: Study 2—ingroup solidarity and outgroup hostility in fine-tuned language models on partisan social media data.

The plot depicts the results of individual logistic regressions predicting positive (or negative) sentiment based on whether a sentence is ingroup (or outgroup), controlling for the number of words and type-to-token ratio and the party (Republican or Democrat) for partisan models (N = 24,000 sentences). Data are presented as odds ratios with error bars for 95% confidence intervals.

Back to article page