%0 Journal Article %J Journal of Internet Services and Applications %D 2017 %T Core-periphery communication and the success of free/libre open source software projects %A Kevin Crowston %A Shamshurin, Ivan %K Apache Software Foundation %K communication %K core and periphery %K free/libre open source software (FLOSS) %K inclusive pronouns %K natural language processing %K project success %X We examine the relationship between communications by core and peripheral members and Free/Libre Open Source Software project success. The study uses data from 74 projects in the Apache Software Foundation Incubator. We conceptualize project success in terms of success building a community, as assessed by graduation from the Incubator. We compare successful and unsuccessful projects on volume of communication and on use of inclusive pronouns as an indication of efforts to create intimacy among team members. An innovation of the paper is that use of inclusive pronouns is measured using natural language processing techniques. We also compare the volume and content of communication produced by core (committer) and peripheral members and by those peripheral members who are later elected to be core members. We find that volume of communication is related to project success but use of inclusive pronouns does not distinguish successful projects. Core members exhibit more contribution and use of inclusive pronouns than peripheral members. %B Journal of Internet Services and Applications %V 8 %G eng %U http://rdcu.be/uguP %N 10 %R 10.1186/s13174-017-0061-4 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/170707%20JISA%20final.pdf %0 Conference Paper %B Workshop on Interactive Language Learning, Visualization, and Interfaces, 52nd Annual Meeting of the Association for Computational Linguistics %D 2014 %T Design of an Active Learning System with Human Correction for Content Analysis %A Jasy Liew Suet Yan %A McCracken, Nancy %A Kevin Crowston %X Our research investigation focuses on the role of humans in supplying corrected examples in active learning cycles, an important aspect of deploying active learning in practice. In this paper, we discuss sampling strategies and sampling sizes in setting up an active learning system for human experiments in the task of content analysis, which involves labeling concepts in large volumes of text. The cost of conducting comprehensive human subject studies to experimentally determine the effects of sampling sizes and sampling sizes is high. To reduce those costs, we first applied an active learning simulation approach to test the effect of different sampling strategies and sampling sizes on machine learning (ML) performance in order to select a smaller set of parameters to be evaluated in human subject studies. %B Workshop on Interactive Language Learning, Visualization, and Interfaces, 52nd Annual Meeting of the Association for Computational Linguistics %C Baltimore, MD %8 06/2014 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/ILLWorkshop.ACLFormat.04.28.14.final_.pdf %0 Conference Paper %B Workshop on Language Technologies and Computational Social Science, 52nd Annual Meeting of the Association for Computational Linguistics %D 2014 %T Optimizing Features in Active Machine Learning for Complex Qualitative Content Analysis %A Jasy Liew Suet Yan %A McCracken, Nancy %A Shichun Zhou %A Kevin Crowston %X We propose a semi-automatic approach for content analysis that leverages machine learning (ML) being initially trained on a small set of hand-coded data to perform a first pass in coding, and then have human annotators correct machine annotations in order to produce more examples to retrain the existing model incrementally for better performance. In this “active learning” approach, it is equally important to optimize the creation of the initial ML model given less training data so that the model is able to capture most if not all positive examples, and filter out as many negative examples as possible for human annotators to correct. This paper reports our attempt to optimize the initial ML model through feature exploration in a complex content analysis project that uses a multidimensional coding scheme, and contains codes with sparse positive examples. While different codes respond optimally to different combinations of features, we show that it is possible to create an optimal initial ML model using only a single combination of features for codes with at least 100 positive examples in the gold standard corpus. %B Workshop on Language Technologies and Computational Social Science, 52nd Annual Meeting of the Association for Computational Linguistics %C Baltimore, MD %8 06/2014 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/9_Paper.pdf %0 Conference Paper %B iConference %D 2014 %T Semi-Automatic Content Analysis of Qualitative Data %A Jasy Liew Suet Yan %A McCracken, Nancy %A Kevin Crowston %B iConference %C Berlin, Germany %8 03/2014 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/iConference_Poster_Published.pdf %0 Conference Proceedings %B IFIP Working Group 8.2 Conference: Shaping the Future of ICT Research: Methods and Approaches %D 2012 %T Amazon Mechanical Turk: A research tool for organizations and information systems scholars %A Kevin Crowston %E Anol Bhattacherjee %E Brian Fitzgerald %B IFIP Working Group 8.2 Conference: Shaping the Future of ICT Research: Methods and Approaches %S IFIP AICT %I Springer %C Tampa, FL %V 389 %P 210-221 %8 12/2012 %@ 978-3-642-35141-9 %R 10.1007/978-3-642-35141-9 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/3890210.pdf %0 Unpublished Work %D 2012 %T Poster: Socially intelligent computing for coding of qualitative data %A Kevin Crowston %A McCracken, Nancy %I Syracuse University School of Information Studies %C Syracuse, NY %8 6/2012 %9 Unpublished poster, presented at the SOCS PIs meeting %> https://socqa.syr.edu/sites/crowston.syr.edu/files/SOCQA%20SOCS%20PI%20poster%20small.pdf %0 Journal Article %J International Journal of Social Research Methodology %D 2012 %T Using natural language processing for qualitative data analysis %A Kevin Crowston %A Allen, Eileen E. %A Heckman, Robert %X Social researchers often apply qualitative research methods to study groups and their communications artefacts. The use of computer-mediated communications has dramatically increased the volume of text available, but coding such text requires considerable manual effort. We discuss how systems that process text in human languages (i.e., natural language processing, NLP) might partially automate content analysis by extracting theoretical evidence. We present a case study of the use of NLP for qualitative analysis in which the NLP rules showed good performance on a number of codes. With the current level of performance, use of an NLP system could reduce the amount of text to be examined by a human coder by an order of magnitude or more, potentially increasing the speed of coding by a comparable degree. The paper is significant as it is one of the first to demonstrate the use of high-level NLP techniques for qualitative data analysis. %B International Journal of Social Research Methodology %V 15 %8 2012 %N 6 %& 523-543 %R 10.1080/13645579.2011.625764 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/NLP_for_qualitative_analysis.pdf %0 Journal Article %J Journal of the Association for Information Systems %D 2011 %T Validity issues in the use of social network analysis with digital trace data %A James Howison %A Kevin Crowston %A Wiggins, Andrea %X

There is an exciting natural match between social network analysis methods and the growth of data sources produced by social interactions via information technologies, from online communities to corporate information systems. Information Systems researchers have not been slow to embrace this combination of method and data. Such systems increasingly provide "digital trace data" that provide new research opportunities. Yet digital trace data are substantively different from the survey and interview data for which network analysis measures and interpretations were originally developed. This paper examines ten validity issues associated with the combination of data digital trace data and social network analysis methods, with examples from the IS literature, to provide recommendations for improving the validity of research using this combination.

%B Journal of the Association for Information Systems %V 12 %8 12/2011 %U http://aisel.aisnet.org/jais/vol12/iss12/2/ %N 12 %& Article 2 %R 10.17705/1jais.00282 %> https://socqa.syr.edu/sites/crowston.syr.edu/files/JAIS.RA-JAIS-08-0130-ReferencesFixed.pdf