Inferring Individual Social Capital Automatically via Phone Logs

Social capital is one of the most fundamental concepts in social computing. Individual social capital is often connected with one's happiness levels, well-being, and propensity to cooperate with others. The dominant approach for quantifying individual social capital remains self-reported surveys and generator-methods, which are costly, attention-consuming, and fraught with biases. Given the important role played by mobile phones in mediating human social lives, this study explores the use of phone metadata (call and SMS logs) to automatically infer an individual's social capital. Based on Williams' Social Capital survey as ground truth and ten-week phone data collection for 55 participants, we report that (1) multiple phone-based social features are intrinsically associated with social capital; and (2) analytics algorithms utilizing phone data can achieve high accuracy at automatically inferring an individual's bridging, bonding, and overall social capital scores. Results pave way for studying social capital and its temporal dynamics at an unprecedented scale.

[1]  Eric Gilbert,et al.  Predicting tie strength with social media , 2009, CHI.

[2]  R. Putnam Bowling Alone: America's Declining Social Capital , 1995, The City Reader.

[3]  P. Bühlmann,et al.  The group lasso for logistic regression , 2008 .

[4]  Konrad Paul Kording,et al.  Mobile Phone Sensor Correlates of Depressive Symptom Severity in Daily-Life Behavior: An Exploratory Study , 2015, Journal of medical Internet research.

[5]  K. Cook,et al.  Social Capital: Theory and Research , 2017 .

[6]  K. Cook,et al.  Social Exchange Theory , 1989, Theoretical Sociology.

[7]  Vivek K. Singh,et al.  Predicting Privacy Attitudes Using Phone Metadata , 2016, SBP-BRiMS.

[8]  Dmitri Williams,et al.  On and Off the 'Net: Scales for Social Capital in an Online Era , 2006, J. Comput. Mediat. Commun..

[9]  Qiang Yang,et al.  User demographics prediction based on mobile data , 2013, Pervasive Mob. Comput..

[10]  Erez Shmueli,et al.  openPDS: Protecting the Privacy of Metadata through SafeAnswers , 2014, PloS one.

[11]  Nan Lin,et al.  Access to occupations through social ties , 1986 .

[12]  Angela Kristin VandenBroek,et al.  Superconnected: the Internet, digital media, and techno-social life , 2017 .

[13]  Jim Giles,et al.  Computational social science: Making the links , 2012, Nature.

[14]  C. Stegbauer,et al.  Granovetter (1973): The Strength of Weak Ties , 2018, Schlüsselwerke der Netzwerkforschung.

[15]  Claude S. Fischer,et al.  Bowling Alone: What's the Score? , 2005, Soc. Networks.

[16]  N. Lin Buidling a Network Theory of Social Capital , 1999, Connections.

[17]  Nan Lin,et al.  The Position Generator: Measurement Techniques for Investigations of Social Capital , 2017 .

[18]  Adam A. Lewis,et al.  Multimodal E-Mental Health Treatment for Depression: A Feasibility Trial , 2010, Journal of medical Internet research.

[19]  N. Smelser,et al.  Annual Review of Sociology , 1975 .

[20]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[21]  Alex Pentland,et al.  Using Deep Learning to Predict Demographics from Mobile Phone Metadata , 2015, ArXiv.

[22]  Tom A. B. Snijders,et al.  The Resource Generator: social capital quantification with concrete items , 2005, Soc. Networks.

[23]  Irwin Altman,et al.  Interpersonal Exchange in Isolation , 1965 .

[24]  Alex Pentland,et al.  Predicting Personality Using Novel Mobile Phone-Based Metrics , 2013, SBP.

[25]  Ram Dantu,et al.  Predicting social ties in mobile phone networks , 2010, 2010 IEEE International Conference on Intelligence and Security Informatics.

[26]  J. Coleman,et al.  Social Capital in the Creation of Human Capital , 1988, American Journal of Sociology.

[27]  Akane Sano,et al.  Recognizing academic performance, sleep quality, stress level, and mental health using personality traits, wearable sensors and mobile phones , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[28]  Cliff Lampe,et al.  Cultivating Social Resources on Social Network Sites: Facebook Relationship Maintenance Behaviors and Their Role in Social Capital Processes , 2014, J. Comput. Mediat. Commun..

[29]  Kimmo Kaski,et al.  Reciprocity of mobile phone calls , 2010, 1002.0763.

[30]  Michael A Babyak,et al.  What You See May Not Be What You Get: A Brief, Nontechnical Introduction to Overfitting in Regression-Type Models , 2004, Psychosomatic medicine.

[31]  P. Adler,et al.  Social Capital: Prospects for a New Concept , 2002 .

[32]  William W. S. Wei Time Series Analysis , 2013 .

[33]  Alex Pentland,et al.  Predicting Spending Behavior Using Socio-mobile Features , 2013, 2013 International Conference on Social Computing.

[34]  Claude S. Fischer,et al.  A Procedure for Surveying Personal Networks , 1978 .

[35]  Zhihai Rong,et al.  Orderliness predicts academic performance: behavioural analysis on campus lifestyle , 2017, Journal of The Royal Society Interface.

[36]  John Zimmerman,et al.  "You Never Call, You Never Write": Call and SMS Logs Do Not Always Indicate Tie Strength , 2015, CSCW.

[37]  Y. Connie Yuan,et al.  Homophily of Network Ties and Bonding and Bridging Social Capital in Computer-Mediated Distributed Teams , 2006, J. Comput. Mediat. Commun..

[38]  Alex Pentland,et al.  Social fMRI: Investigating and shaping social mechanisms in the real world , 2011, Pervasive Mob. Comput..

[39]  Burcin Bozkaya,et al.  Money Walks: Implicit Mobility Behavior and Financial Well-Being , 2015, PloS one.

[40]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[41]  Vivek K. Singh,et al.  Cooperative phoneotypes: exploring phone-based behavioral markers of cooperation , 2016, UbiComp.

[42]  Wen-Lung Shiau,et al.  Factors affecting online group buying intention and satisfaction: A social exchange theory perspective , 2012, Comput. Hum. Behav..

[43]  B. Wellman,et al.  Different Strokes from Different Folks: Community Ties and Social Support , 1990, American Journal of Sociology.

[44]  Jaemin Jung,et al.  From Access to Utilization , 2013 .

[45]  John Zimmerman,et al.  Mining smartphone data to classify life-facets of social relationships , 2013, CSCW.

[46]  T. Harpham,et al.  Measuring social capital within health surveys: key issues. , 2002, Health policy and planning.

[47]  Russell Beale,et al.  Supporting social interaction with smart phones , 2005, IEEE Pervasive Computing.

[48]  Alex Pentland,et al.  Reality mining: sensing complex social systems , 2006, Personal and Ubiquitous Computing.

[50]  J. Richardson Handbook of Theory and Research for the Sociology of Education , 1986 .

[51]  Gabriel Cadamuro,et al.  Predicting poverty and wealth from mobile phone metadata , 2015, Science.

[52]  Robert E. Kraut,et al.  Social capital on facebook: differentiating uses and users , 2011, CHI.

[53]  Cliff Lampe,et al.  The Benefits of Facebook "Friends: " Social Capital and College Students' Use of Online Social Network Sites , 2007, J. Comput. Mediat. Commun..

[54]  Tanzeem Choudhury,et al.  Towards circadian computing: "early to bed and early to rise" makes some of us unhealthy and sleep deprived , 2014, UbiComp.

[55]  J. Burgon Making the links. , 2002, Nursing standard (Royal College of Nursing (Great Britain) : 1987).

[56]  P. Bourdieu Forms of Capital , 2002 .

[57]  Sehee Han,et al.  Does social networking service usage mediate the association between smartphone usage and social capital? , 2013, New Media Soc..

[58]  Mark S. Granovetter The Strength of Weak Ties , 1973, American Journal of Sociology.