Files

Scaler_NordiCHI20241.pdf
  • Open Access
  • Adobe PDF
  • 982.86 KB
Download

Details

Authors
Abstract
Forms are one of the most popular and widespread methods of interaction, yet they remain largely improper for adaptation. We argue that forms should be adapted to the user and their context in a controllable way, to minimize the potential negative effects of any adaptation. This can be accomplished with \soft, a novel web environment for designing and deploying forms in which adaptation is initiated by the system and/or the user according to a vector profile, but always under the user's control, using two unsupervised learning methods: (1) A scoring function that ranks the most usable widgets for each data item on the form, balancing the input and preferences of the stakeholders involved in the form (i.e., user, designer, and developer). (2) A widget recommendation that contrasts the user's profile and those of all other users who have used the same form, whether they have modified it before or not. Our experiment with a car booking form shows that, after some interaction sessions (from 1 to 50 depending on the form field) and some user-controlled adaptations (from 3 to 29 depending on the field), the form design converged to a stabilized selection.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Eloi, D., Sahraoui, A. E. A., Vanderdonckt, J., & Luis A. Leiva. (2024). User-controlled Form Adaptation by Unsupervised Learning. Adjunct Proceedings of the 2024 Nordic Conference on Human-Computer Interaction. Published. 2024 Nordic Conference on Human-Computer Interaction, Uppsala, Sweden. https://doi.org/10.1145/3677045.3685431