Technology is advancing to a point where data is being gathered automatically. Smartphones track users and coordinate that information with applications to recommend stores, local attractions, etc. (Ysai et al., 2009). Along with consumer devices, higher education has begun tracking data (Goldstein, 2005; Yanosky, 2009). Systems such as Blackboard are now able to track students within the system (Blackboard Inc., n.d.). This presentation will examine data mining at the Open High School of Utah (OHSU).
Purpose of this Session
This session is intended for K-12 educators, instructional technologists (both K-12 and higher education) and education policy makers. The purpose of the session to inform participants about the benefits and challenges of data mining in K-12 distance education. Specifically, this presentation will show the results of data mining at the Open High School of Utah (OHSU). Participants will see the methods behind data mining as well as its results. Data visualization will also be discussed.
Objectives of the Session
In this session we will provide background on data mining, student attrition and related literature. Methods of data mining will be discussed. Visualizations of the data will be presented and explained. Lastly, conclusions will be drawn based on the data and areas of future research outlined. Time will be allotted for questions and comments.
This presentation will show that even basic data mining with common software can create useful findings. Participants will be shown tips, including how to avoid common pitfalls in data mining. The limitations of data mining will also be shown.
Technology is advancing to a point where data is being gathered automatically. Smartphones, like the iPhone, track users and coordinate that information with applications to recommend stores, local attractions, etc. (Tsai et al., 2009). Even mundane devices are being programmed to ‘tweet’ information as they are being used (Hanlon, 2009). Along with consumer devices, higher education has begun tracking data (Goldstein, 2005; Yanosky, 2009). Learning Management Systems such as Blackboard are now able to track student behavior within the system (Blackboard Inc., n.d.). As this information is being gathered the practice of data mining becomes increasingly relevant.
Still, research regarding data mining in distance education is only beginning to emerge. Much of the attention regarding data mining has been towards adaptive or recommender systems. However, researchers have explored using data mining to monitor and detect patterns in student attrition (Macfayden & Dawson, 2010).
Although this research is beginning to inform higher education, research into data mining at K-12 institutions lags behind. Our research is meant to close that gap and hopefully the beginning of data-driven decision making in K-12 education.
Goldstein, P. J. (2005, December). Academic Analytics: The Uses of Management Information and Technology in Higher Education. EDUCAUSE Center for Applied Research. Retrieved from http://net.educause.edu/ir/library/pdf/ECM/ECM0508.pdf
Hanlon, T. (2009). Six weird and wonderful things people have built with Twitter. Gizmag. Retrieved February 4, 2010 from http://www.gizmag.com/6-weird-and-wonderful-things-people-have-built-with-twitter/11196/
Macfadyen, L. P., & Dawson, S. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & Education, 54(2), 588-599. doi:10.1016/j.compedu.2009.09.008
Tsai, J. Y., Kelley, P., Drielsma, P., Cranor, L. F., Hong, J., & Sadeh, N. (2009). Who’s viewed you?: the impact of feedback in a mobile location-sharing application. In Proceedings of the 27th international conference on Human factors in computing systems (pp. 2003-2012). Boston, MA, USA: ACM. doi:10.1145/1518701.1519005
Yanosky, R. (2009). Institutional Data Management in Higher Education. EDUCAUSE Center for Applied Research. Retrieved February 2, 2010 from http://net.educause.edu/ir/library/pdf/ECM/ECM0908.pdf