Applications of Social Attribution Theory in XAI

A major problem facing artificial intelligence ethics is how to give AI the status of the agent and gain the trust of human beings. This is accompanied by the rise of Explanatory AI (XAI). The social attribution theory (SAT) started from the perception experiment of Hyde and others, then psychologis...

Full description

Bibliographic Details
Main Author: Guihong Zhang
Format: Article
Language:English
Published: MDPI AG 2022-04-01
Series:Proceedings
Subjects:
Online Access:https://www.mdpi.com/2504-3900/81/1/101
_version_ 1797483171153969152
author Guihong Zhang
author_facet Guihong Zhang
author_sort Guihong Zhang
collection DOAJ
description A major problem facing artificial intelligence ethics is how to give AI the status of the agent and gain the trust of human beings. This is accompanied by the rise of Explanatory AI (XAI). The social attribution theory (SAT) started from the perception experiment of Hyde and others, then psychologists conducted a long-term analysis of the causes and reasons of human intentional action, and Mahler built a complete social psychological attribution model from this. Because SAT is based on action analysis, it can reflect its vast application potential in XAI, including the interpretation of artificial agent action, interpretation of beliefs and other folk psychology concepts, analysis of group intelligence, and the construction of normative agent action and the corresponding ethical explanation. These explorations can provide new ideas for XAI.
first_indexed 2024-03-09T22:44:05Z
format Article
id doaj.art-fd54f1d508e24c4fbe4cdedb2c8a76f4
institution Directory Open Access Journal
issn 2504-3900
language English
last_indexed 2024-03-09T22:44:05Z
publishDate 2022-04-01
publisher MDPI AG
record_format Article
series Proceedings
spelling doaj.art-fd54f1d508e24c4fbe4cdedb2c8a76f42023-11-23T18:33:56ZengMDPI AGProceedings2504-39002022-04-0181110110.3390/proceedings2022081101Applications of Social Attribution Theory in XAIGuihong Zhang0School of Humanities and Social Sciences, University of Science and Technology of China, Hefei 230026, ChinaA major problem facing artificial intelligence ethics is how to give AI the status of the agent and gain the trust of human beings. This is accompanied by the rise of Explanatory AI (XAI). The social attribution theory (SAT) started from the perception experiment of Hyde and others, then psychologists conducted a long-term analysis of the causes and reasons of human intentional action, and Mahler built a complete social psychological attribution model from this. Because SAT is based on action analysis, it can reflect its vast application potential in XAI, including the interpretation of artificial agent action, interpretation of beliefs and other folk psychology concepts, analysis of group intelligence, and the construction of normative agent action and the corresponding ethical explanation. These explorations can provide new ideas for XAI.https://www.mdpi.com/2504-3900/81/1/101social attribution theoryintentionreasonactionexplanationXAI
spellingShingle Guihong Zhang
Applications of Social Attribution Theory in XAI
Proceedings
social attribution theory
intention
reason
action
explanation
XAI
title Applications of Social Attribution Theory in XAI
title_full Applications of Social Attribution Theory in XAI
title_fullStr Applications of Social Attribution Theory in XAI
title_full_unstemmed Applications of Social Attribution Theory in XAI
title_short Applications of Social Attribution Theory in XAI
title_sort applications of social attribution theory in xai
topic social attribution theory
intention
reason
action
explanation
XAI
url https://www.mdpi.com/2504-3900/81/1/101
work_keys_str_mv AT guihongzhang applicationsofsocialattributiontheoryinxai