Trust-based Decision-making for the Adaptation of Public Displays in Changing Social Contexts

Abstract

Public displays may adapt intelligently to the social context, tailoring information on the screen, for example, to the profiles of spectators, their gender or based on their mutual proximity. However, such adaptation decisions should on the one hand match user preferences and on the other maintain the user's trust in the system. A wrong decision can negatively influence the user's acceptance of a system, cause frustration and, as a result, make users abandon the system. In this paper, we propose a trust-based mechanism for automatic decision-making, which is based on Bayesian Networks. We present the process of network construction, initialization with empirical data, and validation. The validation demonstrates that the mechanism generates accurate decisions on adaptation which match user preferences and support user trust.

Trust-based decision-making for smart and adaptive environments

“…They also expressed a high preference for proactive system reactions (4.46 on average) compared to doing nothing (2.47 on average), asking for confirmation on the mobile phone (2.59 on average) or asking for confirmation on the display (3.18 on average). We furthermore found that trust tended to get higher ratings in the live survey (3.91 on average) than in the online survey (3.16 on average), a trend we had already observed in Wißner et al (2014). Apparently the users have more trust in a system that they can actually experience than in a system that is just verbally described to them.…”

“…In contrast to our earlier work Wißner et al (2014) where we focused on the relationship between privacy and user trust, the current work investigates the tension between controllability, transparency and comfort of use. The scenarios were designed in a way that privacy issues were less of a concern (even though they could not be completely excluded).…”

“…With the exception of doing nothing, most system actions got quite high mean values for trust (above 4.0). In our earlier work (Wißner et al 2014), trust ratings for system actions showed greater variations. One reason is that our earlier work also investigated situations that introduced serious risks to privacy, such as viewing personal information or photos on a public display, depending on the system action chosen.…”

“…To mitigate this threat, a variety of mechanisms has been presented to preserve the user's privacy and hide confidential information from others, such as preventing the tracking of tagged consumer items or displaying private information on the user's personal device. In our earlier work (Wißner et al 2014), we presented a trust management system that assesses the users' trust in ubiquitous display environments and decides how and where to present personal information based on location-based context factors, such as other people in the user's immediate neighborhood. While our work did not distinguish between trusted and non-trusted people in the user's physical environment, the approach by Arimura et al (2014) makes use of physical trust relationships between users.…”

CCDEA: Consumer and Cloud – DEA Based Trust Assessment Model for the Adoption of Cloud Services

“…Further, the authors of [8] identified several important parameters in preparing consumers to judge the trustworthiness of cloud service providers. In [9], a system for trust oriented management is presented based on Bayesian networks. This system explained how to intelligently make opinion with respect to public frameworks.…”