We will welcome Einoshin Suzuki, professor at Kyushy University for our LIRIS seminar around AI and ethics, Monday, March 20th, at 10:30am, room C5 (Nautibus) : Judging Instinct Exploitation in Statistical Data Explanations Based on Phrase Embedding.

Abstract:

We have proposed 18 types of statistical data explanations and three kinds of procedures to investigate credibility in unethical and biased explanations due to exploitation of the 10 instincts proposed by Rosling et al. The explanation “women have lower math scores than men” accompanied with the averages and the distributions of their scores is an example of such an explanation, as it exploits the gap instinct, i.e., our tendency to divide all kinds of things into two distinct and often conflicting groups. It becomes much less credible if we replace the word “math” with “English”, even if we keep the data as they are, as the exploitation seems to fail. Our judging procedures are based on phrase embedding and carefully designed comparisons to judge the credibility. The results of our experiments comparing the 18 types with their variants show promising results and clues for further developments.

Keywords: Factfulness, AI and ethics, Subjectivity

Abstract:

We have proposed 18 types of statistical data explanations and three kinds of procedures to investigate credibility in unethical and biased explanations due to exploitation of the 10 instincts proposed by Rosling et al. The explanation “women have lower math scores than men” accompanied with the averages and the distributions of their scores is an example of such an explanation, as it exploits the gap instinct, i.e., our tendency to divide all kinds of things into two distinct and often conflicting groups. It becomes much less credible if we replace the word “math” with “English”, even if we keep the data as they are, as the exploitation seems to fail. Our judging procedures are based on phrase embedding and carefully designed comparisons to judge the credibility. The results of our experiments comparing the 18 types with their variants show promising results and clues for further developments.

[Reference] K. Zhang, H. Shinden, T. Mutsuro, E. Suzuki: "Judging Instinct Exploitation in Statistical Data Explanations Based on Word Embedding", Proc. Fifth AAAI/ACM Conference on AI, Ethics, and Society (AIES 2022), pp. 867-879, 2022.

Bio: Einoshin Suzuki has been a professor in Kyushu University since 2006. He has been working on AI since 1988.