TY - CONF T1 - Design of an Active Learning System with Human Correction for Content Analysis T2 - Workshop on Interactive Language Learning, Visualization, and Interfaces, 52nd Annual Meeting of the Association for Computational Linguistics Y1 - 2014 A1 - Jasy Liew Suet Yan A1 - McCracken, Nancy A1 - Kevin Crowston AB - 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. JF - Workshop on Interactive Language Learning, Visualization, and Interfaces, 52nd Annual Meeting of the Association for Computational Linguistics CY - Baltimore, MD ER - TY - CONF T1 - Optimizing Features in Active Machine Learning for Complex Qualitative Content Analysis T2 - Workshop on Language Technologies and Computational Social Science, 52nd Annual Meeting of the Association for Computational Linguistics Y1 - 2014 A1 - Jasy Liew Suet Yan A1 - McCracken, Nancy A1 - Shichun Zhou A1 - Kevin Crowston AB - 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. JF - Workshop on Language Technologies and Computational Social Science, 52nd Annual Meeting of the Association for Computational Linguistics CY - Baltimore, MD ER - TY - CONF T1 - Semi-Automatic Content Analysis of Qualitative Data T2 - iConference Y1 - 2014 A1 - Jasy Liew Suet Yan A1 - McCracken, Nancy A1 - Kevin Crowston JF - iConference CY - Berlin, Germany ER - TY - UNPB T1 - Poster: Socially intelligent computing for coding of qualitative data Y1 - 2012 A1 - Kevin Crowston A1 - McCracken, Nancy PB - Syracuse University School of Information Studies CY - Syracuse, NY ER - TY - Generic T1 - Investigating the Dynamics of FLOSS Development Teams (Poster) Y1 - 2007 A1 - Li, Na A1 - Li, Qing A1 - Kangning Wei A1 - Heckman, Robert A1 - Eseryel, U. Yeliz A1 - Liddy, Elizabeth D. A1 - James Howison A1 - Kevin Crowston A1 - Allen, Eileen E. A1 - Scialdone, Michael J. A1 - Inoue, Keisuke A1 - Harwell, Sarah A1 - Rowe, Steven A1 - McCracken, Nancy A1 - Wiggins, Andrea N1 - SD 2007 poster - Full Adobe PDF 2007 HSD PI's conference poster reporting on the grant project work to date in a full Adobe PDF file. HSD 2007 poster - Small PDF HSD 2007 conference grant progress reporting poster in a smaller PDF file. ER - TY - Generic T1 - Investigating the Dynamics of FLOSS Development Teams (Poster) Y1 - 2006 A1 - Li, Qing A1 - Kangning Wei A1 - Heckman, Robert A1 - Eseryel, U. Yeliz A1 - Liddy, Elizabeth D. A1 - James Howison A1 - Kevin Crowston A1 - Allen, Eileen E. A1 - Inoue, Keisuke A1 - Harwell, Sarah A1 - Rowe, Steven A1 - McCracken, Nancy N1 - Poster describing the current state of the project for the HSD Principal Investigators' conference, 14-15 September 2006, Washington DC. ER -