An Exploration And Validation of Visual Factors in Understanding Classification Rule Sets
This work addresses the need for more effective communication of ML model logic to practitioners, though it is incremental as it builds on existing rule set methods.
The paper tackled the problem of improving the readability and understanding of classification rule sets by exploring visual alternatives to text-based representations, finding that certain visual design factors significantly enhance processing efficiency with minimal impact on accuracy.
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.