Among the general population, students are especially sensitive to social media and smartphones because of their pervasiveness. Several studies have shown that there is a negative correlation between social media and academic performance since they can lead to behaviors that hurt students' careers, e.g., addictedness. However, these studies either focus on smartphones and social media addictedness or rely on surveys, which only provide approximate estimates. We propose to bridge this gap by i) parametrizing social media usage and academic performance, and ii) combining smartphones and time diaries to keep track of users' activities and their smartphone interaction. We apply our solution on the 72 students participating in the SmartUnitn project, which investigates students' time management and their academic performance. By analyzing the logs of social media apps on students' smartphones while they are studying and attending lessons, and comparing them to students' credits and grades, we can provide a quantitative and qualitative estimate of negative and positive correlations. Our results show the negative impact of social media usage, distinguishing different influence patterns of social media on academic activities and underline the need to take it into account and control the smartphone usage in academic settings.

Context is a fundamental tool humans use for understanding their environment, and it must be modelled in a way that accounts for the complexity faced in the real world. Current context modelling approaches mostly focus on a priori defined environments, while the majority of human life is in open, and hence complex and unpredictable, environments. We propose a context model where the context is organized according to the different dimensions of the user environment. In addition, we propose the notions of endurants and perdurants as a way to describe how humans aggregate their context depending either on space or time, respectively. To ground our modelling approach in the reality of users, we collaborate with sociology experts in an internal university project aiming at understanding how behavioral patterns of university students in their everyday life affect their academic performance. Our contribution is a methodology for developing annotations general enough to account for human life in open domains and to be consistent with both sensor data and sociological approaches.

According to the "human in the loop" paradigm, machine learning algorithms can improve when leveraging on human intelligence, usually in the form of labels or annotation from domain experts. However, in the case of research areas such as ubiquitous computing or lifelong learning, where the annotator is not an expert and is continuously asked for feedback, humans can provide significant fractions of incorrect labels. We propose to address this issue in a series of experiments where students are asked to provide information about their behavior via a dedicated mobile application. Their trustworthiness is tested by employing an architecture where the machine uses all its available knowledge to check the correctness of its own and the user labeling to build a uniform confidence measure for both of them to be used when a contradiction arises. The overarching system runs through a series of modes with progressively higher confidence and features a conflict resolution component to settle the inconsistencies. The results are very promising and show the pervasiveness of annotation mistakes, the extreme diversity of the users' behaviors which provides evidence of the impracticality of a uniform fits-it-all solution, and the substantially improved performance of a skeptical supervised learning strategy.

We present RAMBLE ON, an application integrating a pipeline for frame-based information extraction and an interface to track and display movement trajectories. The code of the extraction pipeline and a navigator are freely available; moreover we display in a demonstrator the outcome of a case study carried out on trajectories of notable persons of the XX Century.

Recent studies have shown that there is a negative correlation between social media and academic performance, since they can lead to behaviours that hurt students' careers, e.g., addictedness. However, these studies either focus on smartphones and social media addictedness per se or rely on sociological surveys, which only provide approximate estimations of the phenomena. We propose to bridge this gap by i) parametrizing social media usage and academic performance and ii) combining smartphones and time diaries to keep track of users' activities and their smartphone interaction. By analyzing the logs of social media apps while studying and attending lessons, and comparing them to students' GPA, we can quantify negative and positive correlations via smartphones.