Human interaction discovery in smartphone proximity networks

Abstract

Since humans are fundamentally social beings and interact frequently with others in their daily life, understanding social context is of primary importance in building context-aware applications. In this paper, using smartphone Bluetooth as a proximity sensor to create social networks, we present a probabilistic approach to mine human interaction types in real life. Our analysis is conducted on Bluetooth data continuously sensed with smartphones for over one year from 40 individuals who are professionally or personally related. The results show that the model can automatically discover a variety of social contexts. We objectively validated our model by studying its predictive and retrieval performance.

Using Mobile Phone Sensor Technology for Mental Health Research: Integrated Analysis to Identify Hidden Challenges and Potential Solutions (Preprint)

“…Most of the limited work using smartphone Bluetooth to track social interactions has been performed in closed social networks [9,20,24,25]. In contrast, in the current study sensor data was collected from participants living within Australia who are unlikely to have social connections each other.…”

“…To date, most of the work using smartphone Bluetooth to track social interactions has been performed in closed social networks [9,20,24,25], whereas our approach was to collect Bluetooth connections in a real-world setting. When collecting Bluetooth data in open network settings, it is generally not possible to identify the devices that are detected.…”

F8-3 The Effects of Smartphone Edge Display on EMG Activity of Thumb Muscles in One-handed Interaction

“…They use their smartphones to play games, do social network system (SNS), browse web, and watch videos for interaction with their family, friends, or other peoples (Do & Gatica-Perez, 2013). Smartphone users' finger muscles suffer from musculoskeletal disorders while using the smartphones, because they touch the smartphone thousands of time (Gustafsson et al, 2017).…”

Inferring social activities with mobile sensor networks

“…By analyzing Bluetooth proximity network, a recently proposed instance of topic model, called GroupUs, was able to discover multiple group activities from timestamped social interaction links [11]. While the discovered activity topics were reported to be relatively relevant and can be interpreted by experts, the automatic transformation from discovered activity topics to general semantic meanings (e.g., meeting, chatting, eating) is still missing.…”