Educational data mining that supports quality teaching: How to create a culture of data in educational policies

• Published in: IEEE Global Engineering Education Conference pp. 933 - 940
• Main Author: Anon
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.04.2016
• Subjects: Behavioural engagement; Classification; Classrooms; Cognitive ergonomics; Data analysis; Data analytics; Data mining; Education; Emotional engagement; Ergonomics; Instructions observation; Mathematical analysis; Mathematics; Teachers; Teaching; Teaching effectiveness; Training
• ISSN: 2165-9567
• DOI: 10.1109/EDUCON.2016.7474664

Teachers' instructions inside mathematics, sciences, and literacy classrooms, are, recently, subjects of studies that unearth many underpinnings instructions' features. Teachers' educational practices have a huge impact on students' performances. Teaching and learning observation inside classrooms with adequate and adapted tool, for educational analysis and constructive appraisal purposes, has been found relevant. We developed a grid as an observation tool based on grounded standards to measure the on-going educational teaching-learning process. Its validation within classes' visits is processed with a cognitive ergonomics methodology. Within this study, we extract, by data analytics processes, the most relevant observable and measurable practices that affect positively or negatively students' engagement and motivation to learn. Also, data mining techniques, including three classification methods, process quantified acts and behaviors to estimate a global characteristic of teaching effectiveness, the teacher's "ability to change the course of events". Within WEKA environment, and with progressive enhancement of our database, the three classification methods provide rates of correct classified instances that exceed 94%. Educational interpretations of our findings are provided and seem to be rational, according to proficient stakeholders from educational fields.