Abstract

Intelligent Assistants— systems that intelligently help people to address some issue— have been the subject of much AI research. In this talk I will introduce two such systems.

The first assistant focuses on adapting user interfaces to cultural preferences—a task that has been shown to improve a user’s performance, but is oftentimes foregone because of its time-consuming and costly procedure. We introduce our culturally adaptive web application MOCCA , which is able to map information in a cultural user model onto adaptation rules in order to create personalized UIs. We describe how MOCCA achieves its goal and present two empirical studies that MOCCA predicts the user’s desires on an optimal user interface correctly and the generated user interface increases the user’s satisfaction as well as performance when solving a task.

The second assistant helps people in the analysis of datasets. These are often overwhelmed by the large number of operators that are available for pre-proessing, applying a data-mining algorithm, and postprocessing the mining results resulting in a huge design space for possible solutions. Extending notions developed for statistical expert systems we present a prototype Intelligent Discovery Assistant (IDA), which provides users with (i) systematic enumerations of valid DM processes, in order that important, potentially fruitful options are not overlooked, and (ii) effective rankings of these valid processes by different criteria, to facilitate the choice of DM processes to execute.