LASER is a research project funded by the French National Research Agency (ANR) which main objective is to investigate how to better understand and support students’ self-regulated learning (SRL) strategies in Blended Learning (BL) using Learning Analytics (LA) solutions and techniques. LASER will follow a designed-based research approach, combining data and process mining techniques with theoretical models from the educational sciences in BL through testbeds and experiments. This project contributes with novel empirical data on the strategies developed by students in BL scenarios, as well as new theoretically grounded analytical techniques that will advance the LA and Educational Sciences international research domains. LASER will also contribute in the operationalization of the national Higher Education strategy for facing the COVID-19 pandemic and the transformations of the DUTs by providing case studies on how to deploy models of education at a large scale.


Studies point out that self-regulation is a crucial higher-order skill required to adapt to the constantly changing professional environments of the 21st century (Ehlers, et al., 2019). Self-regulated learners use cognitive, metacognitive and resource management strategies to plan, manage and control their learning process to achieve their goals and persevere until they succeed (Panadero, 2017). Nowadays, Higher Education Institutions (HEIs) are especially interested in fostering students’ SRL skills because of the transformation towards a more flexible and dynamic models of learning and instruction (Engels et al., 2007). This transformation has become especially important in the past years due to the growing number of students in Higher Education; and, currently due to the social unexpected events derived from the COVID-19 pandemic.

To address this transformation, most of institutions follow two approaches. Firstly, moving from traditional to Blended Learning (BL) practices. BL is a pedagogical approach that combines activities taking place in different learning modes, traditional face-to-face (f2f) with online activities (Graham, 2016), which most popular form has been the Flipped Classroom (FC) (Taotao et al., 2017). BL has been proven a pedagogical approach with positive learning effects (Graham, 2016) and also one of the most effective methods for supporting students’ SRL skills (Broadbent, 2017) and informing science education (Stockwell et al., 2015). Secondly, by promoting Learning Analytics (LA) solutions. LA studies how to understand and optimize learning and learning environments using advanced big data analysis techniques (Viberg et al., 2018). Researchers in this domain study how to use advanced data analysis techniques for analyzing the trace data collected by HEIs Learning Management Systems (LMS) about students’ interactions with the course content (Jovanovic et al., 2017; Jovanovic et al., 2019; Wang, 2017).

Lots of works have been conducted in LA focusing on studying and supporting SRL, but they are still limited in its scope. First, most of the experiments have been conducted in online courses or BL courses designed as a flipped classroom, so other types of BL are underrepresented. Second, various studies analyze self-reported data to understand SRL (Boradbent & Fuller-Tyszkewicz, 2018; Broadbent, 2017), some use trace data to see how it manifests (Jovanovic et al., 2017; Jovanovic et al., 2019; Wang, 2017), but few combine these data sources (Bannert et al., 2019; Cicchinelli et al., 2018) and none use qualitative methods for understanding what happens during the face-to-face classroom sessions. So, current results provide a limited picture of how SRL occurs, offering a biased perspective and misleading on how SRL manifest across the different learning modes. Therefore, very little is known about which students’ self-regulatory strategies relate with academic performance in BL scenarios in Higher Education, and therefore, about how LA tools should support them.

Research objectives

  • Objective 1. To Propose an Analytical Framework composes by instruments and measures combining self-reported and trace data sources to understand: (1) how SRL manifest in BL across time and learning modes (online and face-to-face), and (2) their relationship with learners’ characteristics and performance.
  • Objective 2. To design a LA dashboard-based solution for teachers and students for supporting SRL in BL.
  • Objective 3. To evaluate the impact of the LA solutions in students’ learning strategies and teachers’ decision making in BL scenarios.


  • Bannert, M., Reimann, P., & Sonnenberg, C. “Process mining techniques for analysing patterns and strategies in students’ self-regulated learning.” Metacognition and learning 9.2 (2014): 161-185.
  • Broadbent, J. (2017). Comparing online and blended learner’s self-regulated learning strategies and academic performance. IHE, 33, 24-32.
  • Broadbent, J., & Fuller-Tyszkiewicz, M. (2018). Profiles in self-regulated learning and their correlates for online and blended learning students.Educational Technology Research and Development, 66(6), 1435-1455.
  • Cicchinelli, A., et al. (2018). Finding traces of self-regulated learning in activity streams. In ACM Proc. of LAK, 191-200, ACM.
  • Ehlers, Ulf. Et al (2019). Future Skills – The Future of Learning and Higher education. Results of the International Future Skills Delphi Survey. Karlsruhe
  • Graham CR. (2016) Blended learning systems. Definition, current trends, and future directions. Handbook of blended learning: Global perspectives, local designs. 3–21.
  • Jovanović, J., et al. (2017). Learning analytics to unveil learning strategies in a flipped classroom. The Internet and Higher Education 33(4): 74-85.
  • Jovanovic, J., et al. (2019). Predictive power of regularity of pre-class activities in a flipped classroom. Computers & Education 134 (2019): 156-168.
  • Panadero, et al. (2016) Third wave of measurement in the self-regulated learning field: when measurement and intervention come hand in hand, Scandinavian Journal of Educational Research, 60:6, 723-735
  • Engels, N. et al (2007). “Development and validation of the self-regulated learning inventory for teachers.” Perspectives in Education 25.4: 29-47.
  • Stockwell, B. R. et al (2015). Blended learning improves science education. Cell, 162(5), 933-936.
  • Taotao, L. et al . (2017) Use of the flipped classroom instructional model in higher education: instructors’ perspectives. Journal of computing in higher education 29(2): 179-200.
  • Viberg, O., et al. (2018). The current landscape of learning analytics in HE. CHB, 89, 98-110.
  • Wang FH. (2017) An exploration of online behaviour engagement and achievement in flipped classroom supported by learning management system. Computers & Education. 114:79-91.