Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases

Walter, Tobias; Kirschner, Celina; Eger, Steffen; Glavaš, Goran; Lauscher, Anne; Ponzetto, Simone Paolo

doi:10.48550/arxiv.2108.06295

Cited by 1 publication

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kozlowski et al [32] use the geometry of static word embeddings trained on Google N-grams over decades of the twentieth century to show that the material markers used to signify social class changed with the economic transformations of the century. Walter et al [68] use diachronic word embeddings trained on German parliamentary proceedings to study the evolution of German political biases over time. Joseph and Morgan [30] show that word embeddings can capture population-level beliefs which correspond to the results of surveys of that population.…”

Section: Impact Of Training Datamentioning

confidence: 99%

American == White in Multimodal Language-and-Image AI

Wolfe

Çalışkan

2022

Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society

View full text Add to dashboard Cite

Three state-of-the-art language-and-image AI models, CLIP, SLIP, and BLIP, are evaluated for evidence of a bias previously observed in social and experimental psychology: equating American identity with being White. Embedding association tests (EATs) using standardized images of self-identified Asian, Black, Latina/o, and White individuals from the Chicago Face Database (CFD) reveal that White individuals are more associated with collective in-group words than are Asian, Black, or Latina/o individuals, with effect sizes > .4 for White vs. Asian comparisons across all models. In assessments of three core aspects of American identity reported by social psychologists, single-category EATs reveal that images of White individuals are more associated with patriotism and with being born in America, but that, consistent with prior findings in psychology, White individuals are associated with being less likely to treat people of all races and backgrounds equally. Additional tests reveal that the number of images of Black individuals returned by an image ranking task is more strongly correlated with state-level implicit bias scores for White individuals (Pearson's 𝜌 = .63 in CLIP, 𝜌 = .69 in BLIP) than are state demographics (𝜌 = .60), suggesting a relationship between regional prototypicality and implicit bias. Three downstream machine learning tasks demonstrate biases associating American with White. In a visual question answering task using BLIP, 97% of White individuals are identified as American, compared to only 3% of Asian individuals. When asked in what state the individual depicted lives in, the model responds China 53% of the time for Asian individuals, but always with an American state for White individuals. In an image captioning task, BLIP remarks upon the race of Asian individuals as much as 36% of the time, but never remarks upon race for White individuals. Finally, provided with an initialization image from the CFD and the text "an American person, " a synthetic image generator (VQGAN) using the text-based guidance of CLIP lightens the skin tone of individuals of all races (by 35% for Black individuals, based on pixel brightness). The results indicate that biases equating American identity with being White are learned by language-and-image AI, and propagate to downstream applications of such models. CCS CONCEPTS• Computing methodologies → Computer vision; Natural language processing.

show abstract

Section: Impact Of Training Datamentioning

confidence: 99%