Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
To ensure accountability and mitigate harm, it is critical that diverse stakeholders can interrogate black-box automated systems and find information that is understandable, relevant, and useful to them. In this paper, we eschew prior expertise- and role-based categorizations of interpretability...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Association for Computing Machinery (ACM)
2022
|
| Online Access: | https://hdl.handle.net/1721.1/143861 |
| _version_ | 1811080204874940416 |
|---|---|
| author | Suresh, Harini Gomez, Steven R Nam, Kevin K Satyanarayan, Arvind |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Suresh, Harini Gomez, Steven R Nam, Kevin K Satyanarayan, Arvind |
| author_sort | Suresh, Harini |
| collection | MIT |
| description | To ensure accountability and mitigate harm, it is critical that diverse
stakeholders can interrogate black-box automated systems and find information
that is understandable, relevant, and useful to them. In this paper, we eschew
prior expertise- and role-based categorizations of interpretability
stakeholders in favor of a more granular framework that decouples stakeholders'
knowledge from their interpretability needs. We characterize stakeholders by
their formal, instrumental, and personal knowledge and how it manifests in the
contexts of machine learning, the data domain, and the general milieu. We
additionally distill a hierarchical typology of stakeholder needs that
distinguishes higher-level domain goals from lower-level interpretability
tasks. In assessing the descriptive, evaluative, and generative powers of our
framework, we find our more nuanced treatment of stakeholders reveals gaps and
opportunities in the interpretability literature, adds precision to the design
and comparison of user studies, and facilitates a more reflexive approach to
conducting this research. |
| first_indexed | 2024-09-23T11:27:32Z |
| format | Article |
| id | mit-1721.1/143861 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:27:32Z |
| publishDate | 2022 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/1438612023-04-18T18:59:05Z Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs Suresh, Harini Gomez, Steven R Nam, Kevin K Satyanarayan, Arvind Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Lincoln Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science To ensure accountability and mitigate harm, it is critical that diverse stakeholders can interrogate black-box automated systems and find information that is understandable, relevant, and useful to them. In this paper, we eschew prior expertise- and role-based categorizations of interpretability stakeholders in favor of a more granular framework that decouples stakeholders' knowledge from their interpretability needs. We characterize stakeholders by their formal, instrumental, and personal knowledge and how it manifests in the contexts of machine learning, the data domain, and the general milieu. We additionally distill a hierarchical typology of stakeholder needs that distinguishes higher-level domain goals from lower-level interpretability tasks. In assessing the descriptive, evaluative, and generative powers of our framework, we find our more nuanced treatment of stakeholders reveals gaps and opportunities in the interpretability literature, adds precision to the design and comparison of user studies, and facilitates a more reflexive approach to conducting this research. 2022-07-19T15:36:09Z 2022-07-19T15:36:09Z 2021 2022-07-19T15:31:48Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/143861 Suresh, Harini, Gomez, Steven R, Nam, Kevin K and Satyanarayan, Arvind. 2021. "Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs." Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. en 10.1145/3411764.3445088 Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Association for Computing Machinery (ACM) ACM |
| spellingShingle | Suresh, Harini Gomez, Steven R Nam, Kevin K Satyanarayan, Arvind Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs |
| title | Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs |
| title_full | Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs |
| title_fullStr | Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs |
| title_full_unstemmed | Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs |
| title_short | Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs |
| title_sort | beyond expertise and roles a framework to characterize the stakeholders of interpretable machine learning and their needs |
| url | https://hdl.handle.net/1721.1/143861 |
| work_keys_str_mv | AT sureshharini beyondexpertiseandrolesaframeworktocharacterizethestakeholdersofinterpretablemachinelearningandtheirneeds AT gomezstevenr beyondexpertiseandrolesaframeworktocharacterizethestakeholdersofinterpretablemachinelearningandtheirneeds AT namkevink beyondexpertiseandrolesaframeworktocharacterizethestakeholdersofinterpretablemachinelearningandtheirneeds AT satyanarayanarvind beyondexpertiseandrolesaframeworktocharacterizethestakeholdersofinterpretablemachinelearningandtheirneeds |