A taxonomy of decision support for K-12 teachers in learning analytics designs

Year: 2017

Author: Koh, Elizabeth, Tan, Jennifer

Type of paper: Abstract refereed

In the emerging field of learning analytics (LA), actionable insight from LA designs tends to be a buzzword without clear understandings. Moreover, in K-12 education, where the teacher is a key stakeholder, how can actionable insight from LA systems be implemented to enhance learning for students and teachers? Towards providing greater clarity on this issue, we concretise a taxonomy of decision support for K-12 teachers in LA designs. This taxonomy is illustrated with examples from two prototype LA systems, My Groupwork Buddy (MGB) and the Collaborative Video Annotation and Learning Analytics (CoVAA) Learning Environment. Briefly, MGB is a formative assessment tool for teamwork while CoVAA is a time-point based video annotation system.

Our taxonomy comprises four levels. The base level focuses on descriptive analytics and describes what students' activities on the system are, depicting indicators of student engagement for the teacher. For instance, in MGB, submission data (whether students have completed their teamwork reflection or not), is summarised for the teacher to easily find out who has not participated, and take appropriate action. In CoVAA, teachers are able to download a set of participation data including annotation type, critical lens tag, and comment description, which makes it convenient for them to examine and provide feedback on students' answers.

The next 3 levels - diagnostic, predictive, and prescriptive analytics, provide more decision support for teachers while also involving technical and pedagogical complexity. Diagnostic analytics try to explain why students did what they did. This is analysed after data is collected using techniques such as drill-down tools, correlations, and data mining. For both MGB and CoVAA, this layer of diagnosis is currently done in the back-end using existing statistical techniques by researchers, and shared with the teachers, as data-driven evidence for teachers to take action.

Predictive analytics provide empirical evidence of what students will be engaged in while prescriptive analytics provide recommendations to the student, reducing the immediate intervention required by the teacher. These levels will provide opportunities for teachers to go beyond the common set of responses to probe deeper into student understanding or examine new trends among their students. As such solutions require more time and testing, these analytics are part of the future work planned in the two systems.

Through this taxonomy, we hope to provide a more structured pathway for actionable insight in LA designs and make clearer the role of the teacher. Further implications will be discussed.