An Adaptive User Interface Based On Personalized Learning

  • Authors:
  • Jiming Liu;Chi Kuen Wong;Ka Keung Hui

  • Affiliations:
  • -;-;-

  • Venue:
  • IEEE Intelligent Systems
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

In human-computer interaction, user interface events and frequencies can be recorded and organized into episodes. By computing episode frequencies and implication relations, we can automatically derive application-specific episode associations and therefore enable an application interface to adaptively provide just-in-time assistance to a user. The authors identify five issues related to designing an adaptive user interface: interaction tracking, episodes identification, user pattern recognition, user intention prediction, and user profile update. In particular, they demonstrate how to identify episodes and associate them with an interface that can act on a user's behalf to interact with an application based on certain recognized plans. To adapt to different users' needs, the interface can personalize its assistance by learning user profiles. For example, by detecting and analyzing users' behavior patterns in using Microsoft Word, the interface can automatically assist users in several Word tasks. The authors' Word interface provides episode associations at two levels: text-level (phrase association) and paragraph-level (formatting automation). They conducted two pilot experiments to evaluate the interface's performance. The suggestions it provided and its ease of use were well received by users, and the interface can to a certain extent increase the productivity of type-setting.