Data Mining in Education: Techniques and Applications

Data Mining in Education

In this week’s blog post, I am going to discuss educational data mining (EDM) and its various techniques and applications for its use in education. I am going to provide you a discussion that outlines some of the major EDM techniques and applications. I must note there are several lesser known techniques and applications I did not include in this blog post because I do not want to go into the nuances of EDM with you quite yet. Therefore, enjoy reading how we define EDM as well as its various techniques and applications we use within education.slider_4

EDM is an emerging practice within education to organize and manage the massive growth of educational data used in learning institutions.  EDM can be defined as “the application of data mining techniques to use a specific type of dataset that come from educational environments to address important educational decisions” (Romero & Ventura, p. 12. 2013).  Per Romero and Ventura (2013), EDM is concerned with “ developing, researching, and applying computerized methods to detect patterns in large collections of educational data that would otherwise be hard or impossible to analyze due to the enormous volume of data within which they exist” (p. 12). In addition, through the detection of large patterns of data, EDM analyzes data generated by “any type of information systems supporting learning or education in schools, colleges, universities providing traditional and moderns forms and methods of teaching as well as informal learning” (Romero & Ventura, 2013, p. 12).  The goals of EDM involve analyzing unique data sets generated from educational settings “resolve educational research issues as well as improve the quality of managerial decisions” (Bala, 2012 p. 2).

Source: Youtube – What is Educational Data Mining

Educational Data-Mining: Techniques and Applications

Within the field of EDM, there a numerous techniques that allow educators to utilize various applications. There are a variety of different types of data mining (DM) techniques that can be used to manipulate and analyze data, which include association, clustering,  classification, prediction, and decision trees. Their applications include predicting student outcomes, providing information to support educators and educational leaders, detecting student behavior, planning and scheduling, and data visualization.

Source: Youtube – Neil Hefferman and Ryan Baker: Educational Data Mining – Applications and Techniques

Association

The association DM technique is used to estimate the unknown value of a student’s performance and knowledge. Through this technique, it can provide feedback to support educational leaders and teachers in the decision-making process regarding how to improve student learning and enables educational leaders and to take appropriate and proactive action when needed.

Clustering

Within EDM, clustering refers to identifying groups of instances or students that similar in some respect. Thus, this technique measures the distance between similar groups of students to classify them amongst each other. The major applications with clustering in EDM are to group course material or students based on their learning needs and interacting patterns with teachers and students. In addition, clustering can be used to develop curriculum for students within Special Education or for English Language Learners. Lastly, it allows educators to group students based on their learning needs (i.e., Special Education, GATE, Advanced Placement Programs, and English Language Learners).    

Classification

Classification is the process of “finding a set of functions or models that describe and distinguish data into classes, concepts, for the purpose of being able to use the model to predict the class of objects whose class label is unknown (Li, 2007, p. 2). This EDM technique can be used to profile students based on their academic record (i.e., attendance, classroom assessments, and assignment completion) to predict the performance of these students at the end of the semester or a given point in time.

Prediction

The goal of prediction is to “target an attribute or a single aspect of the data from some combination of the aspects of the data (Romero & Ventura, 2013, p. 21). This means a predictor variable is predicted by a set of predictor variables. Prediction takes several forms in EDM through the techniques of classification and regression. The applications of prediction allow educational leaders and teachers predict and forecast student academic or behavior over a given time.

Decision Trees

Decision trees are used in EDM to predict outcomes based on a specific selection of criteria regarding the question being asked the decision-maker (Romero & Ventura, 2013). Like prediction and classification, information like attendance, class test scores, and assignment scores can be used to predict student performance at the end of a semester. Another application of decision trees is scheduling courses for students. Course selection software programs use decision trees to help select student schedules that meet what the student wants to take, times of the course, sections available, and course student capacity.

Conclusion

There are a variety of different techniques and applications within EDM to solve many problems educators face on a daily basis. While this list is comprehensive of the major EDM techniques and applications, there are still many lesser-known techniques and applications that are being used by educators. In addition, as we progress into the future, there are many techniques and applications being developed and fine-tuned. Also, EDM is slowly being transferred to Student Information Software with more user-friendly user interfaces to allow educators to utilize the power of EDM techniques and applications in their daily practice as educators.

Sources

Bala, M. (2012, ). Study of applications of data mining techniques in education. International J Res Sci Technol, 1(1), 1-10.

Li, Y. (2007). Data mining: Concepts, background and methods of integrating uncertainty in data mining. Manuscript in preparation. Retrieved from http://www.ccsc.org/southcentral/E-Journal/2010/Papers/Yihao%20final%20paper%20CCSC%20for%20submission.pdf

Romero , C., & Ventura , S. (2013, ). Data mining in education. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 3(1), 12-27. http://dx.doi.org/https://doi.org/10.1002/widm.1075

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s