Research has proven that stress reduces quality of life and causes many diseases. For this reason, several researchers devised stress detection systems based on physiological parameters. However, these systems require that obtrusive sensors are continuously carried by the user. In our paper, we propose an alternative approach providing evidence that daily stress can be reliably recognized based on behavioral metrics, derived from the user's mobile phone activity and from additional indicators, such as the weather conditions (data pertaining to transitory properties of the environment) and the personality traits (data concerning permanent dispositions of individuals). Our multifactorial statistical model, which is person-independent, obtains the accuracy score of 72.28% for a 2-class daily stress recognition problem. The model is efficient to implement for most of multimedia applications due to highly reduced lowdimensional feature space (32d). Moreover, we identify and discuss the indicators which have strong predictive power.

No abstract

The Workshop on Computational Personality Recognition aims to define the state-of-the-art in the field and to provide tools for future standard evaluations in personality recognition tasks. In the WCPR14 we released two different datasets: one of Youtube Vlogs and one of Mobile Phone interactions. We structured the workshop in two tracks: an open shared task, where participants can do any kind of experiment, and a competition. We also distinguished two tasks: A) personality recognition from multimedia data, and B) personality recognition from text only. In this paper we discuss the results of the workshop. Categories and Subject Descriptors

Abstract. The paper presents an empirical model of acceptance of mobile phones by elderly people. It is based on an extension of the widely used TAMTechnology Acceptance Model and aims specifically at investigating the relationship among intrinsic and extrinsic motivations to use. The data consists of 740 questionnaires from people over 65 years old. The validated model shows that intrinsic motivations play an important role albeit always mediated by utilitarian motives. Similarly, it emerges a strong influence of the reference social group (children and relatives) in increasing the utilitarian values of the use of mobile phones. These findings suggest that mobile phone usage by elderly might not be, after all, too much different, from a motivational point of view, from that of younger or adult people.

In this paper, we discuss a machine learning approach to automatically detect functional roles played by participants in a face to face interaction. We shortly introduce the coding scheme we used to classify the roles of the group members and the corpus we collected to assess the coding scheme reliability as well as to train statistical systems for automatic recognition of roles. We then discuss a machine learning approach based on multi-class SVM to automatically detect such roles by employing simple features of the visual and acoustical scene. The effectiveness of the classification is better than the chosen baselines and although the results are not yet good enough for a real application, they demonstrate the feasibility of the task of detecting group functional roles in face to face interactions.

In this paper, an influence model is used to recognize functional roles played during meetings. Previous works on the same corpus demonstrated a high recognition accuracy using SVMs with RBF kernels. In this paper, we discuss the problems of that approach, mainly over-fitting, the curse of dimensionality and the inability to generalize to different group configurations. We present results obtained with an influence modeling method that avoid these problems and ensures both greater robustness and generalization capability.

Tabletop interfaces are a novel class of technologies that are particularly suited to support co‐located collaboration. The Collaborative Puzzle Game (CPG) is a tabletop interactive activity developed for fostering collaboration skills in children with Autism Spectrum Disorders (ASD). The CPG features an interaction rule called Enforced Collaboration (EC); in order to be moved, puzzle pieces must be touched and dragged simultaneously by the two players. Two studies were conducted to test the effect of EC on collaboration. In Study I, 70 typically developing boys were tested in pairs to characterise the way they respond to EC; in Study II, 16 boys with ASD were tested in pairs. Results suggest that EC has a generally positive effect on collaboration and is associated with more complex interactions. For children with ASD, the EC interaction rule was effective in triggering behaviours associated with co‐ordination of the task and negotiation.

This study evaluated the effectiveness of a three-week intervention in which a co-located cooperation enforcing interface, called StoryTable, was used to facilitate collaboration and positive social interaction for six children, aged 8-10 years, with Autistic Spectrum Disorder (ASD). Intervention focused on exposing pairs of children to an enforced collaboration paradigm while they narrated a story. Pre-and post intervention tasks included a "low technology" version of the story telling device and a non story-telling play situation using a free construction game. The outcome measure was a structured observation scale of social interaction. Results demonstrated progress in three areas of social behaviors. First, the participants were more likely to initiate positive social interaction with peers after the intervention. Second, the level of shared play of the children increased from the pre-test to the post test and they all increased the level of collaboration following the intervention. Third, the children with ASD demonstrated lower frequencies of autistic behaviors while using the StoryTable in comparison to the free construction game activity. The implications of these findings are discussed in terms of the effectiveness of this intervention for higher functioning children with ASD.