Microgenetic Learning Analytics Methods: Hands-on Sequence Analysis Workshop Report

Authors

  • Ani Aghababyan
  • Taylor Martin O'Reilly Media
  • Phillip Janisiewicz Agile Dynamics
  • Kevin Close Utah State University

DOI:

https://doi.org/10.18608/jla.2016.33.6

Keywords:

Microgenetic analysis, R, RStudio, learning analytics, data mining, hierarchical clustering, sequential pattern mining

Abstract

Learning analytics is an emerging discipline and, as such, it benefits from new tools and methodological approaches.  This work reviews and summarizes our workshop on microgenetic data analysis techniques using R, held at the 2nd annual Learning Analytics Summer Institute in Cambridge, Massachusetts on June 30th, 2014. Specifically, this paper introduces educational researchers to our experience using data analysis techniques with the RStudio development environment to analyze temporal records of 52 elementary students’ affective and behavioral responses to a digital learning environment. In the RStudio development environment, we used methods such as hierarchical clustering and sequential pattern mining. We also used RStudio to create effective data visualizations of our complex data. The scope of the workshop, and this paper, assumes little prior knowledge of the R programming language, and thus covers everything from data import and cleanup to advanced microgenetic analysis techniques. Additionally, readers will be introduced to software setup, R data types, and visualizations. This paper not only adds to the toolbox for learning analytics researchers (particularly when analyzing time series data), but also shares our experience interpreting a unique and complex dataset.

Author Biographies

Taylor Martin, O'Reilly Media

Taylor Martin - It is a common belief that doing promotes learning in complex domains like mathematics and science, but there is little research that establishes the validity of this claim. Dr. Martin examines how people learn from doing, or active participation, both physical and social. Currently, is examining how mobile and social learning environments (online and in person) influence content learning in mathematics, engineering and computational thinking using learning analytics methods to understand learning processes at a fine-grained level. Dr. Martin is Director of the Active Learning Lab at Utah State University. She is currently serving as a Program Director on rotation at the National Science Foundation. There she works on several programs and focuses on a variety of efforts across the foundation to understand how Big Data is impacting research in Education and across the STEM disciplines.

Phillip Janisiewicz, Agile Dynamics

Phillip Janisiewicz is a Data Scientist for the Active Learning Lab in the Department of Instructional Technology and Learning Sciences at Utah State University conducting research in data management and data modeling. Phil works as part of the Active Learning Lab Research and Development team to investigate and implement new models and techniques for predicting student learning and behavior and inferring the relevance and impact of recommendations and personalized content, using a rich corpus of student data. This is a strategic role where he is responsible for identifying new analysis methods and pursuing the execution of projects with a high level of autonomy. Phil has been involved in designing and developing databases, web-based applications, analysis methods, and data visualization techniques. Some of his projects have included data collection across multiple states and by multiple research organizations. He has designed and implemented security and quality assurance measures to meet the highest regulations for data management.

Kevin Close, Utah State University

Kevin Close is a Ph.D. student in instructional design and learning sciences at Utah State University. Before coming to Utah State, he received his BA in religion from Carleton College in Northfield, Minnesota and spent five years teaching English, Math, American History, and Chinese Language. His research interests include using data mining techniques to improve K-12 classroom environments by improving stealth assessment techniques.

References

Abbott, A. & Tsay, A. (2000) Sequence Analysis and Optimal Matching Methods in Sociology: Review and Prospect Sociological Methods & Research, Vol. 29, 3-33.

Berland, M., Martin, T., Benton, T., Petrick Smith, C., & Davis, D. (2013). Using Learning Analytics to Understand the Learning Pathways of Novice Programmers. Journal of the Learning Sciences, 22(4), 564–599.

Blöte, A. W., Resing, W., Mazer, P., & Van Noort, D. A. (1999). Young children's organizational strategies on a same–different task: A microgenetic study and a training study. Journal of Experimental Child Psychology, 74(1), 21-43.

Buchta, C., Hahsler, M., Buchta, M. C., & Matrix, I. (2007). The arulesSequences Package.

Fazio, L. K., & Siegler, R. S. (2013). Microgenetic learning analysis: A distinction without a difference. Human Development, 56(1), 52-58.

Flavell, J. H., & Draguns, J. (1957). A microgenetic approach to perception and thought. Psychological Bulletin, 54(3), 197.

Gabadinho, A., Ritschard, G., Müller, N. S., Studer, M. (2011). Analyzing and Visualizing State Sequences in R with TraMineR. Journal of Statistical Software, 40(4), 1-37. URL http://www.jstatsoft.org/v40/i04/.

Granott, N. (1998). A paradigm shift in the study of development: Essay review of Emerging Minds by RS Siegler. Human Development, 41(5-6), 360-365.

Kuhn, D., Goh, W., Iordanou, K., & Shaenfield, D. (2008). Arguing on the Computer: A Microgenetic Study of Developing Argument Skills in a Computer‐Supported Environment. Child Development, 79(5), 1310-1328.

Maechler, M., Rousseeuw, P., Struyf, A., Hubert, M., Hornik, K.(2015). cluster: Cluster Analysis Basics and Extensions. R package version 2.0.3.

Neuwirth, E., & Neuwirth, M. E. (2007). The RColorBrewer Package.

Opfer, J. E., & Thompson, C. A. (2008). The trouble with transfer: Insights from microgenetic changes in the representation of numerical magnitude. Child Development, 79(3), 788-804.

Schlagmüller, M., & Schneider, W. (2002). The development of organizational strategies in children: Evidence from a microgenetic longitudinal study. Journal of Experimental Child Psychology, 81(3), 298-319.

Siegler, R.S. and Jenkins, E. (1989) How Children Discover New Strategies. Hillsdale, N.J.: Erlbaum

Siegler, R. S., Thompson, C. A., & Schneider, M. (2011). An integrated theory of whole number and fractions development. Cognitive psychology, 62(4), 273-296.

Tunteler, E., Pronk, C. M., & Resing, W. (2008). Inter-and intra-individual variability in the process of change in the use of analogical strategies to solve geometric tasks in children: A microgenetic analysis. Learning and Individual Differences, 18(1), 44-60.

Ward, J. H., Jr. (1963), "Hierarchical Grouping to Optimize an Objective Function", Journal of the American Statistical Association, 58, 236–244.

Zaki., M. J. (2001). SPADE: An Efficient Algorithm for Mining Frequent Sequences. Machine

Learning Journal, 42, 31–60

Downloads

Published

2016-12-19

How to Cite

Aghababyan, A., Martin, T., Janisiewicz, P., & Close, K. (2016). Microgenetic Learning Analytics Methods: Hands-on Sequence Analysis Workshop Report. Journal of Learning Analytics, 3(3), 96-114. https://doi.org/10.18608/jla.2016.33.6

Issue

Vol. 3 No. 3 (2016): Learning Analytics Tutorials

Section

Special section: Tutorials in learning analytics (LASI and LAK 2014)

License

TEST