Social networks from smartphone sensors : construction and prediction issues

• Main Author: Subramanian, Varun.
• Other Authors: School of Computer Engineering
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering::Computer applications::Social and behavioral sciences
• Online Access: http://hdl.handle.net/10356/51968
• Institution: Nanyang Technological University

In this project we investigate how social networks can be derived from various partially anonymized sensor data from a mobile device. In addition we investigate whether the social network derived from one sensor can be predicted from other social networks. My main contributions to this project are as follows. Firstly a general methodology is developed to construct a social network similarity graph based on either direct or indirect user relationship derived from the sensor data logs available from the mobile devices. Secondly an approach is developed to predict the social network similarity graph derived from data logs for a particular sensor type, using the features extracted from a composition of social networks derived from data logs for other sensor types. Experiments are performed on the Nokia Mobile Data Challenge (MDC) dataset to show the feasibility of the developed approaches.