Towards a partnership of teachers and intelligent learning technology: A systematic literature review of model‐based learning analytics.

TEACHING methods; COMPUTER assisted instruction; SYSTEMATIC reviews; LEARNING strategies; COMPARATIVE studies; INTERPROFESSIONAL relations; TEACHERS; STUDENTS; DECISION making; EDUCATIONAL technology; INTELLECT; DESCRIPTIVE statistics; RESEARCH funding

Background: With increased use of artificial intelligence in the classroom, there is now a need to better understand the complementarity of intelligent learning technology and teachers to produce effective instruction. Objective: The paper reviews the current research on intelligent learning technology designed to make models of student learning and instruction transparent to teachers, an area we call model‐based learning analytics. We intended to gain an insight into the coupling between the knowledge models that underpin the intelligent system and the knowledge used by teachers in their classroom decision making. Methods: Using a systematic literature review methodology, we first identified 42 papers, mainly from the domain of intelligent tutoring systems and learning analytics dashboards that conformed to our selection criteria. We then qualitatively analysed the context in which the systems were applied, models they used and benefits reported for teachers and learners. Results and Conclusions: A majority of papers used either domain or learner models, suggesting that instructional decisions are mostly left to teachers. Compared to previous reviews, our set of papers appeared to have a stronger focus on providing teachers with theory‐driven insights and instructional decisions. This suggests that model‐based learning analytics can address some of the shortcomings of the field, like meaningfulness and actionability of learning analytics tools. However, impact in the classroom still needs further research, as in half of the cases the reported benefits were not backed with evidence. Future research should focus on the dynamic interaction between teachers and technology and how learning analytics has an impact on learning and decision making by teachers and students. We offer a taxonomy of knowledge models that can serve as a starting point for designing such interaction. Lay Description: What is currently known: Current learning analytics solutions are often not perceived helpful by teachers What this paper adds: Model‐based learning analytics seeks to make these systems more transparent and actionableOur review shows there is good potential that systems designed in this way would have greater impact on classroom teaching Implications for practitioners: Pedagogical‐psychological models should be an integral part of intelligent learning systems designsWe offer a taxonomy of such models and current good practices of their use as a starting point [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Assisted Learning is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)