The Group Context Framework

Abstract

In this paper, we present the Group Context Framework (GCF), a general-purpose toolkit that allows mobile devices to opportunistically share contextual information. GCF provides a standardized way for developers to request contextual data for their applications. The framework then intelligently groups with other devices to satisfy these requirements. Through two prototypes, we demonstrate how GCF can be used to support a broad range of collaborative and cooperative tasks. We then show how our framework's architecture allows devices to opportunistically detect and collaborate with one another, even when running different applications. Finally, we present two real-world domains that show how GCF's ability to form groups increases users' access to relevant and timely information, and discuss possible incentives and safeguards to context sharing from a user standpoint.

W4-Groups: Modeling the Who, What, When and Where of Group Behavior via Mobility Sensing

“…These cases exemplify the need to detect formed groups across a wide range of scenarios and sensing modalities, similarly motivating the works by de Freitas et al to propose a group context framework that allows devices to form groups autonomously and share context [10,11]. However, this framework offers better support for applications intended to increase the opportunities for serendipitous group formation.…”

“…No one description can capture the nuances of what constitutes a group as the relationship can be on a spectrum of properties from primitive forms, such as sharing a family name to more complex factors, such as the same psychological significance or the skills needed to achieve an agreed-upon goal [19]. Unlike prior work that focuses on opportunistically creating group membership by automatically searching for similar contexts [10], our work begins by modeling groups grounded on the theoretical understanding of small groups. We adopt the definition of group as per McGrath et al, where "a group is an aggregation of two or more people who are to some degree in dynamic interrelation with one another" [44].…”

“…These metrics capture long-term similarities in spatial, temporal, and social scales, collectively forming a robust measure of long-term mobility behavior as follows. between users 𝑖 and 𝑗 represent the aggregation of spatial, temporal, and social similarities: (10) where 𝛼, 𝛽 and 𝛾 represent the weight of the spatial similarity, temporal similarity and social similarity respectively such that 𝛼 + 𝛽 + 𝛾 = 1. This definition allows us to weigh each similarity scale based on the input type.…”

“…While much work focuses on modeling, detection, and understanding group behaviors, these efforts have focused on some but not all of the W4 characteristics in tandem. Prior work assumed that groups are known a priori and have focused on what activities are performed, generally, among students on campus [63] or leverage on gathering data from serendipitous group encounters [10]. We argue that a generalized group detection framework must accomplish two essential criteria: (1) distinguish short-term and long-term group formations based on their underlying purposes, and (2) support multiple data types to accommodate diverse applications that rely on group sensing mechanisms.…”

An approach to pervasive monitoring in dynamic learning contexts : data sensing, communication support and awareness provision

“…Nevertheless, they do not take advantage of the long-range communication infrastructures (e.g., Internet connection, cellular networks, etc.) when they are available [128,61]. This is why, the ideal solution should not only provide autonomy, but also the capability to interact with remote components when they are available.…”