Personal context modelling and annotation

Abstract

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.

Assessing Annotation Consistency in the Wild

“…The time diary used in this work was presented in [10], so we will not go into too much detail on the building process. To summarize, it relied on ATUS, given its potential for activity recognition [2], to obtain an ontology consisting in over 80 candidate labels for three dimensions, each being a question to be asked: activities, locations, and people.…”

“…In this work, we propose the evaluation of the annotation methodology developed in [10], where annotations are built semantically to account for users' understanding of their surroundings and can be deployed in real life scenarios. Thus, users can continuously annotate their experience during their everyday life, providing a detailed and personalized account of their behavior.…”

Mobile Social Media and Academic Performance

“…Time diaries are logs where respondents are asked to detail how they allocated their time in terms of of activities performed, locations visited and people encountered during their day [7]. In this work, we employ a time diary, shown in previous work [5], which asks users three questions: i) "What are you doing? ", i.e., activities like "shopping", ii) "Where are you?…”

“…The project relies on the i-Log mobile application [24,5] to provide the two functionalities needed from smartphones in our approach:…”

“…A dedicated backend infrastructure manages the tasks of synchronizing and storing the streams of data from the smartphones. -Time diaries: i-Log can administer the time diary from [5] as a question composed of three sub-question on activities, locations and social relations of students every 30 minutes. Every triple of questions can be answered within 150 minutes from its notification, with a maximum of 5 questions stacked in queue, otherwise it expires and treated as null.…”