Social Network Discovery by Mining Spatio-Temporal Events

Abstract

Knowing patterns of relationship in a social network is very useful for law enforcement agencies to investigate collaborations among criminals, for businesses to exploit relationships to sell products, or for individuals who wish to network with others. After all, it is not just what you know, but also whom you know, that matters. However, finding out who is related to whom on a large scale is a complex problem. Asking every single individual would be impractical, given the huge number of individuals and the changing dynamics of relationships. Recent advancement in technology has allowed more data about activities of individuals to be collected. Such data may be mined to reveal associations between these individuals. Specifically, we focus on data having space and time elements, such as logs of people's movement over various locations or of their Internet activities at various cyber locations. Reasoning that individuals who are frequently found together are likely to be associated with each other, we mine from the data instances where several actors co-occur in space and time, presumably due to an underlying interaction. We call these spatio-temporal co-occurrences events, which we use to establish relationships between pairs of individuals. In this paper, we propose a model for constructing a social network from events, and provide an algorithm that mines these events from the data. Experiments on a real-life data tracking people's accesses to cyber locations have also yielded encouraging results.

Inferring social network structure in ecological systems from spatio-temporal data streams

“…By identifying observation-dense regions in the data stream, which can be seen as gathering events of affiliated individuals, we propose a methodology of drawing links between agents based on their co-participation into those events. Traditional approaches [9][10][11][12] to constructing social networks from spatio-temporal data involve discretizing the observation stream based on some fixed time window Dt and drawing links between individuals when they lie within such 'interaction-radius'. Our method overcomes the practical difficulties of such time-slicing approach in cases when we have no prior knowledge of how big or small the time window size should be, thus having to perform multiple runs across various Dt and select the appropriate one based on some ad hoc quality function.…”

“Hidden” Social Networks in Behavior Change Interventions

“…Criteria for inferring participants social networks were based on timestamps: (1) on the same day; (2) at the same sensor (at three or more co-occurrences); (3) within 30 seconds (signifying cooccurrences of physical activity behavior and to enable social interactions of more than two people to be captured) (see S1). 15,16 Minutes of physical activity were calculated by aggregating the minutes between the timestamp data at each scanned sensor.…”

Finding “interesting” trends in social networks using frequent pattern mining and self organizing maps

“…In a static context, we typically wish to: (i) find patterns that exist across the network, (ii) cluster (group) subsets of the networks, or (iii) build classifiers to categorize nodes and links. In the dynamic context, we wish to identify relationships between the nodes in the network by evaluating the spatio-temporal co-occurrences of events [6]. The latter is thus the focus of the work described in this paper.…”