A Design Space for Explainable Ranking and Ranking Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916925527818240 |
|---|---|
| author | Hazwani, I. Al Schmid, J. Sachdeva, M. Bernard, J. |
| author_facet | Hazwani, I. Al Schmid, J. Sachdeva, M. Bernard, J. |
| contents | Item ranking systems support users in multi-criteria decision-making tasks. Users need to trust rankings and ranking algorithms to reflect user preferences nicely while avoiding systematic errors and biases. However, today only few approaches help end users, model developers, and analysts to explain rankings. We report on the study of explanation approaches from the perspectives of recommender systems, explainable AI, and visualization research and propose the first cross-domain design space for explainers of item rankings. In addition, we leverage the descriptive power of the design space to characterize a) existing explainers and b) three main user groups involved in ranking explanation tasks. The generative power of the design space is a means for future designers and developers to create more target-oriented solutions in this only weakly exploited space. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_15305 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | A Design Space for Explainable Ranking and Ranking Models Hazwani, I. Al Schmid, J. Sachdeva, M. Bernard, J. Machine Learning Information Retrieval Item ranking systems support users in multi-criteria decision-making tasks. Users need to trust rankings and ranking algorithms to reflect user preferences nicely while avoiding systematic errors and biases. However, today only few approaches help end users, model developers, and analysts to explain rankings. We report on the study of explanation approaches from the perspectives of recommender systems, explainable AI, and visualization research and propose the first cross-domain design space for explainers of item rankings. In addition, we leverage the descriptive power of the design space to characterize a) existing explainers and b) three main user groups involved in ranking explanation tasks. The generative power of the design space is a means for future designers and developers to create more target-oriented solutions in this only weakly exploited space. |
| title | A Design Space for Explainable Ranking and Ranking Models |
| topic | Machine Learning Information Retrieval |
| url | https://arxiv.org/abs/2205.15305 |