Educational organisations worldwide are increasingly expected to understand student performance at an individual level so that they can intervene before a student falls behind or is at risk of dropping out prior to concluding their schooling. Legislative accountability requirements in many countries, such as the No Child Left Behind (NCLB) policy in the United States and initiatives implemented in Western Australia such as the School Improvement and Accountability Framework and the Western Australian Monitoring Standards in Education (WAMSE), have further exacerbated this trend. Principals are held accountable for overall performance and teachers for the progress of their students, requiring schools to continuously assess their performance, plan for improvement, and act on these plans in order to further educational outcomes. As such, there is a growing need for improved monitoring of student performance information in concert with data-driven decision making practices which has led to an increased interest in student data and a heightened emphasis on the ways in which schools utilise it (Mandinach, Honey, & Light, 2006; Selwyn, Henderson, & Chao, 2015; Wayman & Stringfield, 2006; Wayman, Stringfield, & Yakimowski, 2004).
Advances in data warehousing, analytics, and visualisation over recent years have provided the foundation for a growing ‘Smart Education Software Market’, allowing schools to focus on the performance of their students through the interpretation of student data (Baker & Yacef, 2009). These systems hold the promise of fast and easy access to student data and histories, the examination of learning tendencies, and the exploration of relationships relevant to student performance. Key areas of application encompass the examination of student attributes, knowledge domains, and the factors impacting learning, as well as the effectiveness of educational support strategies and predictions of future educational attainment (Wayman & Stringfield, 2006).
While the application of educational data mining and related technologies is still in its relative infancy, a number of studies have suggested a positive impact on teaching and student learning outcomes. At the school district level, demographic, achievement, and instructional-process data can be used to make a whole range of decisions to improve student achievement, where resources, professional development and specialist programs can be directed where needed (Armstrong & Anthes, 2001). Similarly, principal and teacher engagement with student data has been identified as central to improving the effectiveness of schools, providing that assessments of student ability are aligned with expectations, are valid and reliable, and sensitive to individual differences (Heritage & Yeagley, 2005). Continued engagement encourages teachers and school staff to utilise data as the standard means to clearly communicate student issues between various stakeholders and data-driven schools tend to use their data to identify problems, plan appropriate strategies, and monitor outcomes in an iterative fashion (Armstrong & Anthes, 2001; Wayman & Stringfield, 2006).
However, despite these promising findings, commercial educational data mining offerings are rarely based on research and there is often limited evaluation of these data tools in practice (Mandinach, Honey, & Light, 2006; Selwyn, Henderson, & Chao, 2015; Vodicka & Vuchic, 2016). The contemporary education landscape cannot be fully comprehended without adequate attention being paid to the accumulation and flow of data, raising the need for detailed inquiry and critique (Selwyn, 2015). To address these issues, vendors need to adopt strategies that integrate collaboration with researchers, teachers, principals, administrators, and district personnel and give due consideration to the ways in which their systems will be utilised in real world contexts in order to guarantee meaningful utility.
This topic is explored in further detail in a paper presented at the 2016 6th International Conference on Education, Research and Innovation (ICERI2016).
Armstrong, J., & Anthes, K. (2001). How data can help. American School Board Journal, 188(11), 38-41.
Baker, R. S., & Yacef, K. (2009). The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining, 1(1), 3-17.
Bense, K., Brooker, M., & Garrett, M. (2016). Improving the monitoring of student performance: The development of an enterprise learning and instructional support (ELIS) platform. In Proceedings of the 6th International Conference on Education, Research, and Innovation (ICERI2016) (pp. 4069-4077).
Heritage, M & Yeagley, R. (2005). Data use and school improvement: Challenges and prospects. Yearbook of the National Society for the Study of Education, 104(2), 320-339.
Mandinach, E. B., Honey, M., & Light, D. (2006). A theoretical framework for data-driven decision making. In Annual meeting of the American Educational Research Association. San Francisco, CA.
Selwyn, N. (2015). Data entry: Towards the critical study of digital data and education. Learning, Media and Technology, 40(1), 64-82.
Selwyn, N., Henderson, M., & Chao, S. H. (2015). Exploring the role of digital data in contemporary schools and schooling—‘200,000 lines in an Excel spreadsheet’. British Educational Research Journal, 41(5), 767-781.
Vodicka, D., & Vuchic, V. (2016). Making Learning Personal for All: The Growing Diversity of Today’s Classroom. Retrieved 19 December, 2016 from http://digitalpromise.org/wp-content/uploads/2016/09/lps-growing_diversity_FINAL-1.pdf
Wayman, J., C., & Stringfield, S. (2006). Technology‐supported involvement of entire faculties in examination of student data for instructional improvement. American Journal of Education, 112(4), 549-571.
Wayman, J., C., Stringfield, S., & Yakimowski, (M). (2004). Software enabling school improvement through analysis of student data (Report No. 67). Retrieved 19 December, 2016 from http://www.waymandatause.com/wp-content/uploads/2013/11/Report67.pdf