CONFLICT SCENARIOS IN SMART HOMES
This is a repository of 102 smart home conflict scenarios, which were designated as conflict by actual human users. In other words, humans consider the scenarios below to be conflicts in a smart home environment. To see how to use this repository, and how the repository was collected, please read the following paper:
Fereshteh Jadidi Miandashti, Mohammad Izadi, Ali Asghar Nazari Shirehjini, and Shervin Shirmohammadi, “An Empirical Approach to Modeling User-System Interaction Conflicts in Smart Homes”, IEEE Trans. on Human-Machine Systems, 2020.
Please note that the scenarios in our repository help identify what is conflict from the users’ perspective. They do not tell us how to handle those conflicts. In other words, the cases below are about conflict detection, not conflict resolution.
This repository can help designers of Smart Homes understand what rules (system behaviors) were perceived by users as conflict, so they can design appropriate conflict detection and conflict resolution modules for their Smart Home system. For example, in one scenario, the user might open the window to let in the fresh air, but the user has forgotten that his pet bird is roaming free in the room and might escape from the window! The system knows the latter fact and closes the window immediately. Our Smart Home users considered this scenario to be a conflict. A designer might come across a scenario similar to this. In this case, the designer can use our repository to (1) understand that his/her scenario, which is very similar to one of the scenarios in our repository, is indeed considered a conflict by smart home users; hence the designer can investigate it subjectively or with some well-known techniques, and (2) design appropriate conflict detection and resolution rules for it in order to increase user satisfaction. Of course, our repository does not contain all possible conflict scenarios in a smart home, but it gives a fairly good starting point.
The scenarios were translated to English by the researchers and the table is not listing duplicate entries.
Each conflict scenario is a sentence in English that can be processed by NLP or can be converted to some features.