Learning Interpretability for Visualizations using Adapted Cox Models through a User Experiment
This work addresses interpretability in visualizations for users, but it is incremental as it builds on existing quality measures and user-based approaches.
The paper tackles the problem of making visualizations more interpretable by modeling user preferences through quality measures, finding that neighborhood conservation measures outperform cluster separability measures and that combining measures improves prediction performance.
In order to be useful, visualizations need to be interpretable. This paper uses a user-based approach to combine and assess quality measures in order to better model user preferences. Results show that cluster separability measures are outperformed by a neighborhood conservation measure, even though the former are usually considered as intuitively representative of user motives. Moreover, combining measures, as opposed to using a single measure, further improves prediction performances.