Are AI systems biased against the poor? A machine learning analysis using Word2Vec and GloVe embeddings

Georgina Curto*, Mario Fernando Jojoa Acosta, Flavio Comim, Begoña Garcia-Zapirain

*Autor corresponent d’aquest treball

Producció científica: Article en revista indexadaArticleAvaluat per experts

21 Cites (Scopus)

Resum

Among the myriad of technical approaches and abstract guidelines proposed to the topic of AI bias, there has been an urgent call to translate the principle of fairness into the operational AI reality with the involvement of social sciences specialists to analyse the context of specific types of bias, since there is not a generalizable solution. This article offers an interdisciplinary contribution to the topic of AI and societal bias, in particular against the poor, providing a conceptual framework of the issue and a tailor-made model from which meaningful data are obtained using Natural Language Processing word vectors in pretrained Google Word2Vec, Twitter and Wikipedia GloVe word embeddings. The results of the study offer the first set of data that evidences the existence of bias against the poor and suggest that Google Word2vec shows a higher degree of bias when the terms are related to beliefs, whereas bias is higher in Twitter GloVe when the terms express behaviour. This article contributes to the body of work on bias, both from and AI and a social sciences perspective, by providing evidence of a transversal aggravating factor for historical types of discrimination. The evidence of bias against the poor also has important consequences in terms of human development, since it often leads to discrimination, which constitutes an obstacle for the effectiveness of poverty reduction policies.

Idioma originalAnglès
Pàgines (de-a)617-632
Nombre de pàgines16
RevistaAI and Society
Volum39
Número2
DOIs
Estat de la publicacióPublicada - d’abr. 2024

Fingerprint

Navegar pels temes de recerca de 'Are AI systems biased against the poor? A machine learning analysis using Word2Vec and GloVe embeddings'. Junts formen un fingerprint únic.

Com citar-ho