Plural counterfactual examples have been proposed to explain the prediction of a classifier by offering a user several instances of minimal modifications that may be performed to change the prediction. Yet, such explanations may provide too much information, generating potential confusion for the end-users with no specific knowledge, neither on the machine learning, nor on the application domains. In this paper, we investigate the design of explanation user interfaces for plural counterfactual examples offering comparative analysis features to mitigate this potential confusion and improve the intelligibility of such explanations for non-expert users. We propose an implementation of such an enhanced explanation user interface, illustrating it in a financial scenario related to a loan application. We then present the results of a lab user study conducted with 112 participants to evaluate the effectiveness of having plural examples and of offering comparative analysis principles, both on the objective understanding and satisfaction of such explanations. The results demonstrate the effectiveness of the plural condition, both on objective understanding and satisfaction scores, as compared to having a single counterfactual example. Beside the statistical analysis, we perform a thematic analysis of the participants’ responses to the open-response questions, that also shows encouraging results for the comparative analysis features on the objective understanding.

The increasing usage of complex Machine Learning models for decision-making has raised interest in explainable artificial intelligence (XAI). In this work, we focus on the effects of providing accessible and useful explanations to non-expert users. More specifically, we propose generic XAI design principles for contextualizing and allowing the exploration of explanations based on local feature importance. To evaluate the effectiveness of these principles for improving users’ objective understanding and satisfaction, we conduct a controlled user study with 80 participants using 4 different versions of our XAI system, in the context of an insurance scenario. Our results show that the contextualization principles we propose significantly improve user’s satisfaction and is close to have a significant impact on user’s objective understanding. They also show that the exploration principles we propose improve user’s satisfaction. On the other hand, the interaction of these principles does not appear to bring improvement on both dimensions of users’ understanding.

Multisensory Interaction (M.I.) is a promising research field acting on both perception and cognition. Among benefits, including the "design for all" approach, it is expected to increase humans’ cognitive performance (such as learning and cognitive stimulation) as well as user's experience. To our knowledge, there is no convincing tool allowing researchers to create easily multisensory scenarios, exercises or experimental interaction situations. This paper introduces the PRIM project which aims at designing a new and original tool for designing multisensory interactive interaction situations.

This paper proposes an experimental comparison between human imprecise calculation and fuzzy arithmetic: an empirical study has been conducted to collect real intervals resulting from products and additions with imprecise operands from participants. Fuzzy intervals are elicited from these data and fuzzy arithmetic is applied to the collected imprecise operands. Comparisons show that the fuzzy product and addition differ from the way human beings perform these operations. Moreover, they show that the participants, rather than taking into account the imprecisions in the calculations, realise exact calculation and in the end approximate the exact result.

Imprecise numerical expressions, such as "about 100 meters", are pervasive in natural language. Mobile robotics, Geographic Information Systems, intelligent personal assistants as well as database querying applications are required to automatically and accurately interpret such expressions, called Approximate Numerical Expressions (ANE). The main challenge is to determine their numerical boundaries that sound plausible to users. The aim of this paper is to provide guidelines to interpret ANEs that are independent from the domain and the formal representations. We identified three arithmetical properties and examined their involvement in ANE interpretation as intervals of denoted values. The implicit assumption of symmetry of the intervals was also tested. To do so, 146 participants were asked to provide the intervals corresponding to 24 ANEs in a semantically neutral context. Results suggest that the properties of ANEs we identified are key factors in their interpretation while symmetry is not always maintained. This study contributes towards an understanding of how users process ANEs and its results can be used to improve intelligent interfaces that lead to better users' satisfaction and natural interaction between him/her and the system.

Initial training, which concludes by a driving license, is insufficient because new drivers do not know how to contextualize the learned procedures into effective practices. Our goal is to improve the driver's Situation Awareness, i.e. the way in which the driver perceives events in the environment, and the projection of their status in a close future. More precisely, our concern is the way in which the driver evaluates his own competences. Our aim is to make the driver realize his drawbacks and help him to correct them. For this, first, we model drivers' behavior along two approaches, that is, local and global approaches, in order to have a driver model as exhaustive as possible. Second, we educate the driver, helping him to realize his driving's drawbacks. We present in this paper the results of a specific study on driver classification based on the two approaches.