Exploring Issues of User Model Transparency and Proactive Behaviour in an Office Environment Control System

Abstract

It is important that systems that exhibit proactive behaviour do so in a way that does not surprise or frustrate the user. Consequently, it is desirable for such systems to be both personalised and designed in such a way as to enable the user to scrutinise her user model (part of which should hold the rules describing the behaviour of the system). This article describes on-going work to investigate the design of a prototype system that can learn a given user's behaviour in an office environment in order to use the inferred rules to populate a user model and support appropriate proactive behaviour (e.g. turning on the user's fan under appropriate conditions). We explore the tension between user control and proactive services and consider issues related to the design of appropriate transparency with a view to supporting user comprehensibility of system behaviour. To this end, our system enables the user to scrutinise and possibly over-ride the 'IF-THEN' rules held in her user model. The system infers these rules from the context history (effectively a data set generated using a variety of sensors) associated with the user by using a fuzzy-decisiontree-based algorithm that can provide a confidence level for each rule in the user model. The evolution of the system has been guided by feedback from a number of real-life users in a university department. A questionnaire study has yielded supplementary results concerning the extent to which the approach taken meets users' expectations and requirements.

The effects of transparency on trust in and acceptance of a content-based art recommender

“…Dzindolet et al (2003) found that explaining why errors might occur increased trust in automated tools, even when this was not appropriate. Therefore, transparency and task performance can influence each other negatively (see also Cheverst et al 2005). Bilgic and Mooney (2005) note that explanations should not aim just to promote ('sell') a system's recommendations, but that explanations should enable the user to accurately assess recommendation quality.…”

Evaluating Intelligibility Usage and Usefulness in a Context-Aware Application

“…To counter this, context-aware applications should be intelligible (also called transparent, comprehensible, scrutable) by providing explanations of their behavior [1]. Indeed, there have already been several contextaware applications that support some level of intelligibility (e.g., [2,17,18,19,22]). These systems support a limited set of explanations users can ask for: What, Certainty, Inputs, Why, and Why Not.…”

Specification and Verification of Complex Location Events with Panoramic

“…Intelligible Context Models Several papers have established and articulated the need for intelligible models of context [4,6,21]. A few systems have also explored support for intelligible context.…”

“…A few systems have also explored support for intelligible context. Cheverst et al [6] supported users with scrutable decision tree rules and context histories. The PersonisAD [2] framework allowed developers to access supporting evidence for context items.…”