This PhD research project investigates the privacy and data protection issues surrounding learning analytics in higher education. In three studies, the project will examine the state-of-the-art of both issues in terms of what is already known as well as investigate the expectations of different human stakeholders in the overall learning analytics ecosystem.
Grounded in the results from the state of-the-art and the stakeholder expectations, a toolbox that aims at informing the learning analytics stakeholders on the identified privacy and data protection issues will be developed. The toolbox will communicate a bigger picture of what, how, and why learning data are collected and analysed throughout the learning analytics processes.
As data reporting (i.e., the stage of closing loops of learning analytics processes) is an essential phase in the learning analytics ecosystem, a privacy risk aware approach will be proposed to quantify data privacy and protection aspects in learning analytics and make data reporting recommendations based on users' privacy preferences. The impact of this PhD project will increase transparency and thus improve trust of learning analytics in higher education.
Liu, Q., Khalil, M., Shakya, R. and Jovanovic, J. (2025). " Advancing privacy in learning analytics using differential privacy," In: LAK25: 15th International Learning Analytics and Knowledge Conference. DOI: https://doi.org/10.1145/3706468.3706493 [29% acceptance rate] [accepted]
Liu, Q., Deho, O., Vadiee, F., Khalil, M., Joksimovic S., and Siemens, G. (2025). "Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms," In: LAK25: 15th International Learning Analytics and Knowledge Conference. DOI: https://doi.org/10.1145/3706468.3706546 [29% acceptance rate] [accepted]
Liu, Q., Khalil, M., Shakya, R. and Jovanovic, J. (2025). Ensuring privacy through synthetic data generation in education, British Journal of Educational Technology (Special Issue: AI for Data Generation in Education: Towards Learning and Teaching Support at Scale), [under review] [IF=6.7] https://bera-journals.onlinelibrary.wiley.com/doi/10.1111/bjet.13576
Khalil, M., Shakya, R., Liu, Q., & Ebner, M. (2024). How to plan and manage a blended learning course module using generative artificial intelligence? In Case Studies on Blended Learning in Higher Education (pp. 53–72). Springer. DOI: https://doi.org/10.1007/978-981-97-9388-4_4
Liu, Q., and Khalil, M. (2024). Explainable AI in Learning Analytics: Improving Predictive Models and Advancing Transparency and Trust. In: 2024 IEEE Global Engineering Education Conference (EDUCON), pp. 1–7. DOI: https://ieeexplore.ieee.org/document/10578733
Liu, Q., Khalil, M., Shakya, R. and Jovanovic, J. (2024). Scaling While Privacy Preserving: a Comprehensive Synthetic Tabular Data Generation and Evaluation in Learning Analytics. In: LAK24: 14th International Learning Analytics and Knowledge Conference. DOI: https://doi.org/10.1145/3636555.3636921 [30% acceptance rate]
Javier, Khalil, M., Jesús Domingo Segovia and Liu, Q. (2024). Learning analytics for enhanced professional capital development: a systematic review. Frontiers in Psychology, 15. DOI: https://doi.org/10.3389/fpsyg.2024.1302658.
Liu, Q., & Khalil, M. (2023). Understanding privacy and data protection issues in learning analytics using a systematic review. British Journal of Educational Technology, 54, 1715–1747. DOI: https://doi.org/10.1111/bjet.13388 [IF=6.7]
Tutorials, Workshops and Posters [peer-reviewed]
Liu, Q. & Khalil, M. (2023, June). Exploring the Generation of Synthetic Educational Tabular Data using LLMs [Workshop paper]. In 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'24), AI for Education (AI4EDU): Advancing Personalized Education with LLM and Adaptive Learning Workshop, Barcelona, Spain.
Liu, Q., Shakya, R Khalil, M. (2023, June). Differential Privacy for Enhanced Privacy in Educational Data Science [Poster presentation]. Norwegian Artificial Intelligence Research Consortium Annual Conference, Kristiansand, Norway.
Liu, Q. (2023, March). Privacy and Data Protection for a Trustworthy Learning Analytics in Higher Education [Poster presentation]. The 14th International Learning Analytics and Knowledge Conference, Kyoto, Japan. [best poster award]
Liu, Q., & Khalil, M. (2023, May). A detail survey of identified privacy and data protection issues for learning analytics [Poster presentation]. Nordic Learning Analytics Summer Institute, Oulu, Finland.
Liu, Q., & Khalil, M. (2023, May). Neuroscience Inspired Artificial Working Memory [Poster presentation]. Norwegian Artificial Intelligence Research Consortium Annual Conference, Tromsø, Norway.
Liu, Q., Mestre, A & Khalil, M. (2023, March 13-17). Perspectives of Multimodal Data Sharing and Privacy in VR Learning Rooms [Poster presentation]. The 13th International Learning Analytics and Knowledge Conference, Arlington, Texas, USA. [best poster award]
