TY - GEN
T1 - An Exploration and Validation of Visual Factors in Understanding Classification Rule Sets
AU - Yuan, Jun
AU - Nov, Oded
AU - Bertini, Enrico
N1 - Funding Information:
We thank all the study participants and reviewers for their comments. This work was partially supported by a contract with Capital One and the NSF award number 1928614.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements (rules). Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules. In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding. We then presents a user study exploring their impact. The results show that some design factors have a strong impact on how efficiently readers can process the rules while having minimal impact on accuracy. This work can help practitioners employ more effective solutions when using rules as a communication strategy to understand ML models.
AB - Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements (rules). Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules. In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding. We then presents a user study exploring their impact. The results show that some design factors have a strong impact on how efficiently readers can process the rules while having minimal impact on accuracy. This work can help practitioners employ more effective solutions when using rules as a communication strategy to understand ML models.
KW - Empirical studies in visualization
KW - Ruman-centered computing
KW - Visualization
UR - http://www.scopus.com/inward/record.url?scp=85123798611&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123798611&partnerID=8YFLogxK
U2 - 10.1109/VIS49827.2021.9623303
DO - 10.1109/VIS49827.2021.9623303
M3 - Conference contribution
AN - SCOPUS:85123798611
T3 - Proceedings - 2021 IEEE Visualization Conference - Short Papers, VIS 2021
SP - 6
EP - 10
BT - Proceedings - 2021 IEEE Visualization Conference - Short Papers, VIS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Visualization Conference, VIS 2021
Y2 - 24 October 2021 through 29 October 2021
ER -