An Empirical Approach to Modeling User-System Interaction Conflicts in Smart Homes

Conflict is one of the important factors affecting user satisfaction and trust in smart environments, yet conflict modeling in mixed initiative smart environments has not been sufficiently explored. Most of the existing literature on conflict in smart homes are centered on conflicts between users. Although research has shown that about 75% of conflicts are between users and system [1], only a few studies have considered user-system conflicts in smart homes. The aim of this article is to empirically propose both a definition and a run-time detection method for conflicts between users and smart home systems. Our empirical study is based on conflict sample scenarios collected from 163 users. Using clustering on these scenarios, we form an empirical definition of user-system conflict in smart homes. We also propose two functions that characterize each class of the collected scenarios, and we detect conflicts from this characterization. Our conflict detection model could help users achieve a more satisfactory experience in smart homes. Moreover, the model can offer benefits for system developers to design and deploy more reliable smart homes.

I. Introduction

Ambient Intelligence (AmI) is a domain in which devices, tools, and the environment are networked in a way that they can interact with each other and perform actions based on users’ needs. “In an AmI world, massively distributed devices operate collectively while embedded in the environment using information and intelligence that is hidden in the interconnection network” [2]. The aim of this domain is to provide a proactive environment that is aware of the users’ presence, as well as their personal, emotional, and locational characteristics, and is able to respond to users’ needs properly [3].