Alberto Castro-Hernández1, Kathleen Swigger1, Fatma Cemile Serce2, and Victor Lopez3
1 Computer Science Department, University of North Texas, USA. (e-mail: albertocastrohernandez@my.unt.edu, kathy@cse.unt.edu).
2 Department of Information Systems Engineering, Atilim University, Turkey. (e-mail: cemileserce@gmail.com).
3 Facultad de Ingeniería de Sistemas Computacionales, Universidad Tecnológica de Panama, Panama. (e-mail: victor.lopez@utp.ac.pa).
Manuscript received on December 29, 2014, ]]>
Accepted for publication on April 27, 2015,
Published on June 15, 2015.
Abstract
This paper describes the use of an automatic classifier to model group potency levels within software development projects. A set of machine learning experiments that looked at different group characteristics and various collaboration measures extracted from a team's communication activities were used to predict overall group potency levels. These textual communication exchanges were collected from three software development projects involving students living in the US, Turkey and Panama. Based on the group potency literature, group-level measures such as skill diversity, cohesion, and collaboration were developed and then collected for each team. A regression analysis was originally performed on the continuous group potency values to test the relationships between the group-level measures and group potency levels. This method, however, proved to be ineffective. As a result, the group potency values were converted into binary labels and the relationships between the group-level measures and group potency were re-analyzed using machine learning classifiers. Results of this new analysis indicated an improvement in the accuracy of the model. Thus, we were able to successfully characterize teams as having either low or high potency levels. Such information can prove useful to both managers and leaders of teams in any setting.
Key words: Software development, group potency, machine learning.
DESCARGAR ARTÍCULO EN FORMATO PDF
ACKNOWLEDGMENTS
]]> The first author thanks Veronica Perez-Rosas for her help in the classifiers' selection for some experiments. Also, he gratefully acknowledges financial support from a CONACYT scholarship and from the Support for Graduate Studies Program of SEP. This material was also based upon work supported by the National Science Foundation under Grant No. 0705638.
REFERENCES
[1] J. D. Herbsleb and D. Moitra, "Global software development," Software, IEEE, vol. 18, no. 2, pp. 16-20, 2001. [ Links ]
[2] P. J. Agerfalk, B. Fitzgerald, H. H. Olsson, and E. O. Conchuir, "Benefits of global software development: the known and unknown," in Making Globally Distributed Software Development a Success Story. Springer, 2008, pp. 1-9. [ Links ]
[3] A. M. Townsend, S. M. DeMarie, and A. R. Hendrickson, "Virtual teams: Technology and the workplace of the future," The Academy of Management Executive, vol. 12, no. 3, pp. 17-29, 1998. [ Links ]
[4] R. P. Biuk-Aghai and S. J. Simoff, "An integrative framework for knowledge extraction in collaborative virtual environments," in Proceedings of the 2001 International ACM SIGGROUP Conference on Supporting Group Work, ser. GROUP'01. New York, NY, USA: ACM, 2001, pp. 61-70. [Online]. Available: http://doi.acm.org/10.1145/500286.500298 [ Links ]
[5] S. A. Munson, K. Kervin, and L. P. Robert Jr, "Monitoring email to indicate project team performance and mutual attraction," in Proceeding of CSCW'14, 17th ACM conference on Computer supported cooperative work & social computing, 2014, pp. 542-549. [ Links ]
[6] G. Chen, C. Wang, and K. Ou, "Using group communication to monitor web-based group learning," Journal of Computer Assisted Learning, vol. 19, no. 4, pp. 401-415, 2003. [ Links ]
[7] P. A. Gloor and Y. Zhao, "Tecflow-a temporal communication flow visualizer for social networks analysis," in CSCW 04 Workshopon Social Networks, 2004. [ Links ]
[8] A. L. Gonzales, J. T. Hancock, and J. W. Pennebaker, "Language style matching as a predictor of social dynamics in small groups," Communication Research, vol. 37, no. 1, pp. 3-19, Feb. 2010. [ Links ]
[9] J. Mathieu, M. T. Maynard, T. Rapp, and L. Gilson, "Team effectiveness 1997-2007: A review of recent advancements and a glimpse into the future," Journal of Management, vol. 34, no. 3, pp. 41 0-476, Jun. 2008. [ Links ]
]]>[10] A. De Jong, K. De Ruyter, and M. Wetzels, "Antecedents and consequences of group potency: A study of self-managing service teams," Management Science, vol. 51, no. 11, pp. 1610-1625, 2005. [ Links ]
[11] A. M. Hardin, M. A. Fuller, and J. S. Valacich, "Measuring group efficacy in virtual teams new questions in an old debate," Small Group Research, vol. 37, no. 1, pp. 65-85, Feb. 2006. [Online]. Available: http://sgr.sagepub.com/content/37/1/65 [ Links ]
[12] A. E. Akgun, H. Keskin, J. Byrne, and S. Z. Imamoglu, "Antecedents and consequences of team potency in software development projects," Information & Management, vol. 44, no. 7, pp. 646-656, 2007. [ Links ]
[13] S. M. Gully, K. A. Incalcaterra, A. Joshi, and J. M. Beaubien, "A metaanalysis of team-efficacy, potency, and performance: interdependence and level of analysis as moderators of observed relationships," Journal of Applied Psychology, vol. 87, no. 5, p. 819, 2002. [ Links ]
[14] R. A. Guzzo, P. R. Yost, R. J. Campbell, and G. P. Shea, "Potency in groups: Articulating a construct," British Journal ofSocial Psychology, vol. 32, no. 1, pp. 87-106, 1993. [ Links ]
[15] N. Sivasubramaniam, W. D. Murry, B. J. Avolio, and D. I. Jung, "A longitudinal model of the effects of team leadership and group potency on group performance," Group & Organization Management, vol. 27, no. 1, pp. 66-96, Mar. 2002. [Online]. Available: http://gom.sagepub.com/content/27/1/66 [ Links ]
[16] S. W. Lester, B. M. Meglino, and M. A. Korsgaard, "The antecedents and consequences of group potency: A longitudinal investigation of newly formed work groups," Academy ofManagement Journal, pp. 352-368, 2002. [Online]. Available: http://www.jstor.org/stable/10.2307/3069351 [ Links ]
[17] A. D. Stajkovic, D. Lee, and A. J. Nyberg, "Collective efficacy, group potency, and group performance: meta-analyses of their relationships, and test of a mediation model," Journal of Applied Psychology, vol. 94, no. 3, p. 814, 2009. [ Links ]
[18] D. M. Paskevich, L. R. Brawley, K. D. Dorsch, and W. Neil, "Relationship between collective efficacy and team cohesion: Conceptual and measurement issues," Group Dynamics: Theory, Research, and Practice, vol. 3, no. 3, pp. 210-222, 1999. [ Links ]
[19] T. Ogwang, "A convenient method of computing the gini index and its standard error," Oxford Bulletin of Economics and Statistics, vol. 62, no. 1, pp. 123-129, 2000. [ Links ]
[20] S. M. Gully, D. J. Devine, and D. J. Whitney, "A meta-analysis of cohesion and performance effects of level of analysis and task interdependence," Small Group Research, vol. 26, no. 4, pp. 497-520, 1995. http://dx.doi.org/10.17562/PB-51-8 [ Links ]
[21] V. L. Schwanda, K. Barron, J. Lien, G. Schroeder, A. Vernon, and J. T. Hancock, "Temporal patterns of cohesiveness in virtual groups," in Proceedings ofthe ACM 2011 Conference on Computer Supported Cooperative Work, ser. CSCW'11. New York, NY, USA: ACM, 2011, pp. 709-712. [ Links ]
]]>[22] Y. R. Tausczik and J. W. Pennebaker, "Improving teamwork using real-time language feedback," in Proceedings of Human Factors in Computing Systems (CHI), 2013, pp. 459-468. [ Links ]
[23] F. C. Serce, K. Swigger, F. N. Alpaslan, R. Brazile, G. Dafoulas, and V. Lopez, "Online collaboration: Collaborative behavior patterns and factors affecting globally distributed team performance," Computers in Human Behavior, vol. 27, no. 1, pp. 490-503, Jan. 2011. [ Links ]
[24] J. W. Pennebaker, C. K. Chung, M. Ireland, A. Gonzales, and R. J. Booth, "The development and psychometric properties of LIWC2007," Austin, TX, LIWC. Net, 2007. [ Links ]
[25] R. R. Hirschfeld, M. S. Cole, J. B. Bernerth, and T. E. Rizzuto, "Voluntary survey completion among team members: Implications of noncompliance and missing data for multilevel research," Journal of Applied Psychology, vol. 98, no. 3, pp. 454-468, 2013. [ Links ]
[26] D. A. Newman and H.-P. Sin, "How do missing data bias estimates of within-group agreement? Sensitivity of SD WG, CVWG, rWG(J), rWG(J)* , and ICC to systematic nonresponse," Organizational Research Methods, vol. 12, no. 1, pp. 113-147, Jan. 2009. [ Links ]
]]>[27] D. A. Newman, C. Lance, and R. Vandenberg, "Missing data techniques and low response rates," Statistical and methodological myths and urban legends, pp. 7-36, 2009. [ Links ]
[28] M. K. Lindell, C. J. Brandt, and D. J. Whitney, "A revised index of interrater agreement for multi-item ratings of a single target," Applied Psychological Measurement, vol. 23, no. 2, pp. 127-135, Jun. 1999. [Online]. Available: http://apm.sagepub.com/content/23/2/127 [ Links ]
[29] A. J. Smola and B. Schoelkopf, "A tutorial on support vector regression," 1998, NeuroCOLT2 Technical Report NC2-TR-1998-030. [ Links ]
[30] H. D. Young, Statistical treatment of experimental data. McGraw-Hill, 1962. [ Links ]
[31] I. Brooks and K. Swigger, "Using sentiment analysis to measure the effects of leaders in global software development," in International Conference on Collaboration Technologies and Systems (CTS), 2012, pp. 517-524. [ Links ]
[32] J. Pennebaker, The Secret Life of Pronouns: What Our Words Say About Us. Bloomsbury USA, 2013. [ Links ]
[33] Y. R. Tausczik and J. W. Pennebaker, "The psychological meaning of words: LIWC and computerized text analysis methods," Journal of language and social psychology, vol. 29, no. 1, pp. 24-54, 2010. [ Links ]
]]>