學術產出-期刊論文
題名 | Is this AI sexist? The effects of a biased AI’s anthropomorphic appearance and explainability on users’ bias perceptions and trust |
作者 | 侯宗佑 Hou, Tsung-Yu;Tseng, Yu-Chia;Yuan, Chien Wen (Tina) |
貢獻者 | 傳播學院 |
關鍵詞 | Human-AI interaction; Explainable AI; Trust; Anthropomorphism; Bias; Gender |
日期 | 2024-06 |
上傳時間 | 24-二月-2025 15:36:38 (UTC+8) |
摘要 | Biases in artificial intelligence (AI), a pressing issue in human-AI interaction, can be exacerbated by AI systems’ opaqueness. This paper reports on our development of a user-centered explainable-AI approach to reducing such opaqueness, guided by the theoretical framework of anthropomorphism and the results of two 3 × 3 between-subjects experiments (n = 207 and n = 223). Specifically, those experiments investigated how, in a gender-biased hiring situation, three levels of AI human-likeness (low, medium, high) and three levels of richness of AI explanation (none, lean, rich) influenced users’ 1) perceptions of AI bias and 2) adoption of AI’s recommendations, as well as how such perceptions and adoption varied across participant characteristics such as gender and pre-existing trust in AI. We found that comprehensive explanations helped users to recognize AI bias and mitigate its influence, and that this effect was particularly pronounced among females in a scenario where females were being discriminated against. Follow-up interviews corroborated our quantitative findings. These results can usefully inform explainable AI interface design. |
關聯 | International Journal of Information Management, Vol.76, 102775 |
資料類型 | article |
DOI | https://doi.org/10.1016/j.ijinfomgt.2024.102775 |
dc.contributor | 傳播學院 | |
dc.creator (作者) | 侯宗佑 | |
dc.creator (作者) | Hou, Tsung-Yu;Tseng, Yu-Chia;Yuan, Chien Wen (Tina) | |
dc.date (日期) | 2024-06 | |
dc.date.accessioned | 24-二月-2025 15:36:38 (UTC+8) | - |
dc.date.available | 24-二月-2025 15:36:38 (UTC+8) | - |
dc.date.issued (上傳時間) | 24-二月-2025 15:36:38 (UTC+8) | - |
dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/155766 | - |
dc.description.abstract (摘要) | Biases in artificial intelligence (AI), a pressing issue in human-AI interaction, can be exacerbated by AI systems’ opaqueness. This paper reports on our development of a user-centered explainable-AI approach to reducing such opaqueness, guided by the theoretical framework of anthropomorphism and the results of two 3 × 3 between-subjects experiments (n = 207 and n = 223). Specifically, those experiments investigated how, in a gender-biased hiring situation, three levels of AI human-likeness (low, medium, high) and three levels of richness of AI explanation (none, lean, rich) influenced users’ 1) perceptions of AI bias and 2) adoption of AI’s recommendations, as well as how such perceptions and adoption varied across participant characteristics such as gender and pre-existing trust in AI. We found that comprehensive explanations helped users to recognize AI bias and mitigate its influence, and that this effect was particularly pronounced among females in a scenario where females were being discriminated against. Follow-up interviews corroborated our quantitative findings. These results can usefully inform explainable AI interface design. | |
dc.format.extent | 111 bytes | - |
dc.format.mimetype | text/html | - |
dc.relation (關聯) | International Journal of Information Management, Vol.76, 102775 | |
dc.subject (關鍵詞) | Human-AI interaction; Explainable AI; Trust; Anthropomorphism; Bias; Gender | |
dc.title (題名) | Is this AI sexist? The effects of a biased AI’s anthropomorphic appearance and explainability on users’ bias perceptions and trust | |
dc.type (資料類型) | article | |
dc.identifier.doi (DOI) | 10.1016/j.ijinfomgt.2024.102775 | |
dc.doi.uri (DOI) | https://doi.org/10.1016/j.ijinfomgt.2024.102775 |