The strength of the work ties

College students often have to team up for class projects, and they select each other based not only on past performance (e.g., grades) but also on whether they have friendship ties (e.g., whether they trust each other). There has not been any study on the relationship between team formation for class projects and social media. To fix that, we ask two group of university students to tell us with whom they wish to work. Afterward, we gathered their online Facebook data and tested the predictors of team formation. We found that self-organized selection of team members does not strongly depend on past grades, but rather on Facebook-derived proxies for tie strength, popularity, extroversion and homophily. These results have important theoretical implications for the team formation literature and practical implications for online educational platforms.

[1]  Krishna P. Gummadi,et al.  You are who you know: inferring user profiles in online social networks , 2010, WSDM '10.

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

[3]  Flavio Figueiredo,et al.  TrendLearner: Early prediction of popularity trends of user generated content , 2014, Inf. Sci..

[4]  S. Myers,et al.  An Initial Examination of College Students' Expressions of Affection Through Facebook , 2011 .

[5]  M. Ashton,et al.  What is the central feature of extraversion? Social attention versus reward sensitivity. , 2002, Journal of personality and social psychology.

[6]  E. David,et al.  Networks, Crowds, and Markets: Reasoning about a Highly Connected World , 2010 .

[7]  Jussara M. Almeida,et al.  Large-scale study of city dynamics and urban social behavior using participatory sensing , 2014, IEEE Wireless Communications.

[8]  Jorge Gonçalves,et al.  Modeling What Friendship Patterns on Facebook Reveal About Personality and Social Capital , 2014, ACM Trans. Comput. Hum. Interact..

[9]  Zhi-Hua Zhou,et al.  Exploratory Under-Sampling for Class-Imbalance Learning , 2006, Sixth International Conference on Data Mining (ICDM'06).

[10]  Li Lin,et al.  Modeling team member characteristics for the formation of a multifunctional team in concurrent engineering , 2004, IEEE Transactions on Engineering Management.

[11]  Yiming Yang,et al.  A Comparative Study on Feature Selection in Text Categorization , 1997, ICML.

[12]  Raymond T. Sparrowe,et al.  Social Networks and the Performance of Individuals and Groups , 2001 .

[13]  A. Portes.  Social Capital: Its Origins and Applications in Modern Sociology , 1998 .

[14]  Cheng Li,et al.  When a friend in Twitter is a friend in life , 2012, WebSci '12.

[15]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[16]  Daniele Quercia,et al.  Working with Friends: Unveiling Working Affinity Features from Facebook Data , 2014, ICWSM.

[17]  J. Moreno.  Who Shall Survive: A New Approach to the Problem of Human Interrelations , 2017 .

[18]  Florian Probst,et al.  Online social networks: A survey of a global phenomenon , 2012 .

[19]  M. McPherson,et al.  Birds of a Feather: Homophily in Social Networks , 2001 .

[20]  Pin Luarn,et al.  Key variables to predict tie strength on social network sites , 2015, Internet Res..

[21]  Kristen E. DiCerbo,et al.  An extensible micro-world for learning in the data networking professions , 2014, Inf. Sci..

[22]  Sancho Salcedo-Sanz,et al.  Team formation based on group technology: a hybrid grouping genetic algorithm approach , 2011, IEEE Engineering Management Review.

[23]  Yiming Yang,et al.  An Evaluation of Statistical Approaches to Text Categorization , 1999, Information Retrieval.

[24]  Juan A. Botía Blaya,et al.  Generation of human computational models with machine learning , 2015, Inf. Sci..

[25]  Esteban Moro,et al.  Social Features of Online Networks: The Strength of Intermediary Ties in Online Social Media , 2011, PloS one.

[26]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[27]  Jason J. Jones,et al.  Social Networks and Labor Markets: How Strong Ties Relate to Job Finding on Facebook’s Social Network , 2017, Journal of Labor Economics.

[28]  Jennifer Neville,et al.  Modeling relationship strength in online social networks , 2010, WWW '10.

[29]  Tanmay Sinha,et al.  Together we stand, Together we fall, Together we win: Dynamic team formation in massive open online courses , 2014, The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014).

[30]  Virgílio A. F. Almeida,et al.  Characterizing user navigation and interactions in online social networks , 2012, Inf. Sci..

[31]  M. Ashton,et al.  What is the central feature of extraversion? Social attention versus reward sensitivity. , 2002, Journal of personality and social psychology.

[32]  Matthew J. Salganik,et al.  Wiki surveys : Open and quantifiable social data collection ∗ , 2012 .

[33]  J. Townsend.  Theoretical analysis of an alphabetic confusion matrix , 1971 .

[34]  G. Labianca,et al.  A Multilevel Model of Group Social Capital , 2006 .

[35]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

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

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

[38]  Zhi-Hua Zhou,et al.  Exploratory Undersampling for Class-Imbalance Learning , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[39]  Derek Ruths,et al.  Geolocation Prediction in Twitter Using Social Networks: A Critical Analysis and Review of Current Practice , 2015, ICWSM.

[40]  Ronald G. Askin,et al.  Forming effective worker teams with multi-functional skill requirements , 2005, Comput. Ind. Eng..

[41]  Fabrício Benevenuto,et al.  Pollution, bad-mouthing, and local marketing: The underground of location-based social networks , 2014, Inf. Sci..

[42]  Antonio Alfredo Ferreira Loureiro,et al.  RECAST: Telling apart social and random relationships in dynamic networks , 2015, Perform. Evaluation.

[43]  Christopher J. Fariss,et al.  Inferring Tie Strength from Online Directed Behavior , 2013, PloS one.

[44]  Stan Matwin,et al.  Addressing the Curse of Imbalanced Training Sets: One-Sided Selection , 1997, ICML.