Recent and upcoming research experiments
Our learning analytics research group, under the umbrella of Athabasca University, is conducting different experiments of our learning analytics tools and solutions in collaboration with various institutions around the world. Our experiments promote among others using finer-grained observational data through learning analytics and approximating randomized block designs through matching techniques (e.g., Mahalanobis Distance Matching, Coarsened Exact Matching, Propensity Score Matching), Inverse Probability of Treatment Weighting (IPTW), and Instrumental Variables (IV). The objective is to discover and precisely identify the actual drivers of academic performance for both an individual learner or a group of learners by assessing the cause-effect relationships among education-related variables (i.e., learning and teaching processes). We use a variety of questionnaires and data streams that allow us to categorize each student according to specific variables.
Canada – CNRL – Initiation to VR Study (Upcoming)
· Learning analytics tool: STAGE VR training tool
· Experiment period: June-July 2019
· Participants involved: 12
· Study design: Pilot study
Canada – Athabasca University – COMP308 Study (Upcoming)
· Learning analytics tool: Coding analytics tool used within a Java Programming course
· Experiment period: 2019-2020
· Students involved:
· Tutors involved:
· Study design: Observational study
Canada – Athabasca University – JAV.AU Study
· Learning analytics tool: Coding analytics tool for extracurricular Java programming assignments
· Experiment period: June 2017 to January 2018
· Students involved: 48
· Tutors involved: 19
· Study design: Control/Randomized study
Boulanger, D., Seanosky, J., Guillot, R., Guillot, I., Guillot, C., Fraser, S., Kumar, V., & Kinshuk (2019, accepted). Assessing Learning Analytics Impact on Coding Competence Growth. International Conference on Advanced Learning Technologies (ICALT 2019), July 15-18, Maceió-AL, Brazil.
Guillot, I., Guillot, C., Guillot, R., Seanosky, J., Boulanger, D., Fraser, S.N., Kumar, V., & Kinshuk (2019, accepted). Challenges in recruiting and retaining participants for smart learning environment studies, International Conference on Smart Learning Environments (ICSLE 2019), March 18-20, Denton, USA.
Guillot, R., Seanosky, J., Guillot, I., Boulanger, D., Guillot, C., Kumar, V., & Fraser, S. N. (2018, July). Assessing Learning Analytics Systems Impact by Summative Measures. In 2018 IEEE 18th International Conference on Advanced Learning Technologies (ICALT) (pp. 188-190). IEEE.
Saudi Arabia
· Learning analytics tool: MI-Writer used within an English Course
· Experiment period: Feb 2016 to May 2016
· Students involved: 65
· Teachers involved: 3
· Study design: Observational study
Saudi Arabia
· Learning analytics tool: CODEX used within a Java Programming II course
· Experiment period: January 2016 to April 2016
· Students involved: 80
· Teachers involved: 6
· Study design: Observational study
Note: The CODEX system has been presented at the E-Learning forum in Saudi Arabia hosted by the Deanship of E-Learning and Distance Education 2015.
India – Experiment 2
· Learning analytics tool: MI-Writer used within an English Course
· Experiment period: Feb 2016 to May 2016
· Students involved: 300
· Teachers involved: 6
· Study design: Observational study
India – Experiment 1
· Learning analytics tool: MI-Writer used within an English Course
· Experiment period: Sept. 21, 2015 – End of December 2015
· Students involved: 780
· Teachers involved: 6
· Study design: Observational study