Dataset resulting from the user study on comprehensibility of explainable AI algorithms

Abstract This paper introduces a dataset that is the result of a user study on the comprehensibility of explainable artificial intelligence (XAI) algorithms. The study participants were recruited from 149 candidates to form three groups representing experts in the domain of mycology (DE), students w...

Full description

Saved in:
Bibliographic Details
Main Authors: Szymon Bobek, Paloma Korycińska, Monika Krakowska, Maciej Mozolewski, Dorota Rak, Magdalena Zych, Magdalena Wójcik, Grzegorz J. Nalepa
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05167-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222293447344128
author Szymon Bobek
Paloma Korycińska
Monika Krakowska
Maciej Mozolewski
Dorota Rak
Magdalena Zych
Magdalena Wójcik
Grzegorz J. Nalepa
author_facet Szymon Bobek
Paloma Korycińska
Monika Krakowska
Maciej Mozolewski
Dorota Rak
Magdalena Zych
Magdalena Wójcik
Grzegorz J. Nalepa
author_sort Szymon Bobek
collection DOAJ
description Abstract This paper introduces a dataset that is the result of a user study on the comprehensibility of explainable artificial intelligence (XAI) algorithms. The study participants were recruited from 149 candidates to form three groups representing experts in the domain of mycology (DE), students with a data science and visualization background (IT) and students from social sciences and humanities (SSH). The main part of the dataset contains 39 transcripts of interviews during which participants were asked to complete a series of tasks and questions related to the interpretation of explanations of decisions of a machine learning model trained to distinguish between edible and inedible mushrooms. The transcripts were complemented with additional data that includes visualizations of explanations presented to the user, results from thematic analysis, recommendations of improvements of explanations provided by the participants, and the initial survey results that allow to determine the domain knowledge of the participant and data analysis literacy. The transcripts were manually tagged to allow for automatic matching between the text and other data related to particular fragments. In the advent of the area of rapid development of XAI techniques, the need for a multidisciplinary qualitative evaluation of explainability is one of the emerging topics in the community. Our dataset allows not only to reproduce the study we conducted, but also to open a wide range of possibilities for the analysis of the material we gathered.
format Article
id doaj-art-e63ab07ea3aa4c41acc518e5950e13b5
institution OA Journals
issn 2052-4463
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-e63ab07ea3aa4c41acc518e5950e13b52025-08-20T02:06:23ZengNature PortfolioScientific Data2052-44632025-06-0112111210.1038/s41597-025-05167-6Dataset resulting from the user study on comprehensibility of explainable AI algorithmsSzymon Bobek0Paloma Korycińska1Monika Krakowska2Maciej Mozolewski3Dorota Rak4Magdalena Zych5Magdalena Wójcik6Grzegorz J. Nalepa7Jagiellonian Human-Centered AI Lab, Mark Kac Center for Complex Systems Research, Institute of Applied Computer Science, Jagiellonian UniversityInstitute of Information Studies, Faculty of Management and Social Communication, Jagiellonian UniversityInstitute of Information Studies, Faculty of Management and Social Communication, Jagiellonian UniversityJagiellonian Human-Centered AI Lab, Mark Kac Center for Complex Systems Research, Institute of Applied Computer Science, Jagiellonian UniversityInstitute of Information Studies, Faculty of Management and Social Communication, Jagiellonian UniversityInstitute of Information Studies, Faculty of Management and Social Communication, Jagiellonian UniversityInstitute of Information Studies, Faculty of Management and Social Communication, Jagiellonian UniversityJagiellonian Human-Centered AI Lab, Mark Kac Center for Complex Systems Research, Institute of Applied Computer Science, Jagiellonian UniversityAbstract This paper introduces a dataset that is the result of a user study on the comprehensibility of explainable artificial intelligence (XAI) algorithms. The study participants were recruited from 149 candidates to form three groups representing experts in the domain of mycology (DE), students with a data science and visualization background (IT) and students from social sciences and humanities (SSH). The main part of the dataset contains 39 transcripts of interviews during which participants were asked to complete a series of tasks and questions related to the interpretation of explanations of decisions of a machine learning model trained to distinguish between edible and inedible mushrooms. The transcripts were complemented with additional data that includes visualizations of explanations presented to the user, results from thematic analysis, recommendations of improvements of explanations provided by the participants, and the initial survey results that allow to determine the domain knowledge of the participant and data analysis literacy. The transcripts were manually tagged to allow for automatic matching between the text and other data related to particular fragments. In the advent of the area of rapid development of XAI techniques, the need for a multidisciplinary qualitative evaluation of explainability is one of the emerging topics in the community. Our dataset allows not only to reproduce the study we conducted, but also to open a wide range of possibilities for the analysis of the material we gathered.https://doi.org/10.1038/s41597-025-05167-6
spellingShingle Szymon Bobek
Paloma Korycińska
Monika Krakowska
Maciej Mozolewski
Dorota Rak
Magdalena Zych
Magdalena Wójcik
Grzegorz J. Nalepa
Dataset resulting from the user study on comprehensibility of explainable AI algorithms
Scientific Data
title Dataset resulting from the user study on comprehensibility of explainable AI algorithms
title_full Dataset resulting from the user study on comprehensibility of explainable AI algorithms
title_fullStr Dataset resulting from the user study on comprehensibility of explainable AI algorithms
title_full_unstemmed Dataset resulting from the user study on comprehensibility of explainable AI algorithms
title_short Dataset resulting from the user study on comprehensibility of explainable AI algorithms
title_sort dataset resulting from the user study on comprehensibility of explainable ai algorithms
url https://doi.org/10.1038/s41597-025-05167-6
work_keys_str_mv AT szymonbobek datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT palomakorycinska datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT monikakrakowska datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT maciejmozolewski datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT dorotarak datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT magdalenazych datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT magdalenawojcik datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms
AT grzegorzjnalepa datasetresultingfromtheuserstudyoncomprehensibilityofexplainableaialgorithms