Mirka Saarela

Dr. Mirka Saarela

Academy of Finland Research Fellow
Assistant Professor (tenure track)
Faculty of Information Technology
University of Jyväskylä
Office: Ag C525.3
Tel. +358-40-8055 067
Email: mirka.saarela@jyu.fi

My research lies at the intersection of data mining, education, and machine learning. I am especially interested in explainability and fairness in algorithmic decision-making.

Publications

SAARELA, M. (2024): On the relation of causality- versus correlation-based feature selection on model fairness. Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing (SAC ’24), pp. 56–64.
SAARELA, M. & PODGORELEC V. (2024): Recent Applications of Explainable AI (XAI): A Systematic Literature Review. Applied Sciences. 2024; 14(19):8884.
HAUKALA, J., SAARELA, M., LOBERG, O. & KÄRKKÄINEN, T. (2024): A design for neural network model of continuous reading. Cognitive Systems Research, ISSN 1389-0417, 101284.
AHMADOV, T., KARIMOV, A., DURST, S., SAARELA, M., GERSTELBERGER, W., WAHL, M. F., & KÄRKKÄINEN, T. (2024): A two-phase systematic literature review on the use of serious games for sustainable environmental education. Interactive Learning Environments, 1-22.
KARIMOV, A.; SAARELA, M.; KÄRKKÄINEN, T.(2024): Serious games in science and mathematics education: a scoping umbrella review. International Journal of Serious Games, 11(4).
HEILALA, V., JÄÄSKELÄ, P., SAARELA, M. & KÄRKKÄINEN, T. (2024): Adapting Teaching and Learning in Higher Education Using Explainable Student Agency Analytics. Chapter 2 in Principles and Applications of Adaptive Artificial Intelligence, IGI Global, pp.20-51.
GUNASERKA, S.& SAARELA, M.;(2024): Explainability in Educational Data Mining and Learning Analytics: An Umbrella Review. Proceedings of the 17th International Conference on Educational Data Mining (EDM). International Educational Data Mining Society, pp. 887–892.
KARIMOV, A.; SAARELA, M.; KÄRKKÄINEN, T. & AGHAYEVA, S. (2024): Principals’ use of data analytics in Finnish schools. Proceedings of the 17th International Conference on Educational Data Mining (EDM). International Educational Data Mining Society, pp. 452–457.
KARIMOV, A.; SAARELA, M.; KÄRKKÄINEN, T.(2024): AI-Powered Education Equality: Evidence from Five Countries. E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education. Association for the Advancement of Computing in Education (AACE), pp. 500-505.
KARIMOV, A.; SAARELA, M.; & KÄRKKÄINEN, T.(2024): Ethical Educational Data Processing Differences of Students with Special Needs in Post-Soviet Countries. Proceedings of the 17th International Conference on Educational Data Mining (EDM). International Educational Data Mining Society, pp. 898–902.
KARIMOV, A.; SAARELA, M.; & KÄRKKÄINEN, T. (2024): Understanding teachers’ perspectives on ethical concerns and skills to use AI tools. 14th International Conference on Learning Analytics & Knowledge (LAK24) Companion Proceedings, pp. 230-232.
ZHIDKIKH, D., SAARELA, M., & KÄRKKÄINEN, T. (2023): Measuring self-regulated learning in a junior high school mathematics classroom: Combining aptitude and event measures in digital learning materials.. Journal of Computer Assisted Learning, 39(6), pp. 1834–1851.
KARIMOV, A.; SAARELA, M.; & KÄRKKÄINEN, T.(2023): Clustering to define interview participants for analyzing student feedback: a case of Legends of Learning. 16th International Conference on Educational Data Mining (EDM).
KARIMOV, A.; SAARELA, M.; & KÄRKKÄINEN, T.(2023): The impact of online educational platform on students’ motivation and grades: the case of Khan Academy in the under-resourced communities. 16th International Conference on Educational Data Mining (EDM).
SAARELA, M. & GEORGIEVA L.(2022): "Robustness, Stability, and Fidelity of Explanations for a Deep Skin Cancer Classification Model". In Applied Sciences, 12(19), 9545.
HEILALA, V., KELLY, R., SAARELA, M., JÄÄSKELÄ P. & KÄRKKÄINEN, T. (2022): "The Finnish Version of the Affinity for Technology Interaction (ATI) Scale: Psychometric Properties and an Examination of Gender Differences". In International Journal of Human–Computer Interaction, pp. 1-19.
HEILALA, V., JÄÄSKELÄ &, P., SAARELA, M., KUULA, AS., ESKOLA, A., KÄRKKÄINEN, T.(2022): “Sitting at the Stern and Holding the Rudder”: Teachers’ Reflections on Action in Higher Education Based on Student Agency Analytics". In: Digital Teaching and Learning in Higher Education. Palgrave Macmillan, pages 71-91.
SAARELA, M., HEILALA, V., JÄÄSKELÄ, P., RANTAKAULIO, A. & KÄRKKÄINEN, T.(2021): "Explainable Student Agency Analytics". In IEEE Access, Volume 9, pages 137444-137459.
SAARELA, M. & JAUHIAINEN, S. (2021): "Comparison of feature importance measures as explanations for classification models". In Springer Nature Applied Sciences, Volume 3, Issue 2, 272.
TIKKA, S., HAKANEN, J., SAARELA, M. & KARVANEN, J. (2021): "Sima – an Open-source Simulation Framework for Realistic Large-scale Individual-level Data Generation". In International Journal of Microsimulation, Volume 14, Number 3, pages 27-53.
SAARELA, M. & KÄRKKÄINEN, T. (2020): "Can we automate expert-based journal rankings? Analysis of the Finnish publication indicator". In Journal of Informetrics, Volume 14, Issue 2, May 2020, 101008.
HEILALA, V., SAARELA, M., JÄÄSKELÄ, P. & KÄRKKÄINEN, T.(2020): "Course Satisfaction in Engineering Education Through the Lens of Student Agency Analytics". In IEEE Frontiers in Education Conference (FIE), pages 1-9.
HEILALA, V., SAARELA, M., REPONEN, S. & KÄRKKÄINEN, T. (2020): "Let Me Hack It : Teachers’ Perceptions About ‘Making’ in Education". In Advances in Smart Technologies Applications and Case Studies, Lecture Notes in Electrical Engineering. Cham: Springer 684, pages 509-518.
HEILALA, V., JÄÄSKELÄ, P., KÄRKKÄINEN, T. & SAARELA, M.(2020): "Understanding the Study Experiences of Students in Low Agency Profile: Towards a Smart Education Approach". In Advances in Smart Technologies Applications and Case Studies, Lecture Notes in Electrical Engineering. Cham: Springer 684, pages 509-518.
SAARELA, M., RYYNÄNEN, O.-P. & ÄYRÄMÖ, S. (2019): "Predicting Hospital Associated Disability from Imbalanced Data Using Supervised Learning". In Artificial Intelligence in Medicine, Volume 95, pages 88-95.
SAARELA, M., LAHTONEN, J., RUORANEN, M., MÄKELÄINEN, A., ANTIKAINEN, T. & KÄRKKÄINEN, T. (2019): “Automated Profiling of Open-Ended Survey Data on Medical Workplace Learning”. In the International Journal of Emerging Technologies in Learning, Vol 14, No 05, pages 97-107.
AKUSOK, A., SAARELA, M., KÄRKKÄINEN, T., BJÖRK, K.-M. & LENDASSE, A. (2019): "Mislabel Detection of Finnish Publication Ranks". In Proceedings of the 8th International Conference on Extreme Learning Machines (ELM 2017), Springer International Publishing, pages 240-248.
IFENEDO, E., SAARELA, M. & HÄMÄLÄINEN, T. (2019): “Analysing the Nigerian Teacher’s Readiness for Technology Integration”. In the International Journal of Education and Development using Information and Communication Technology, Vol 15, No 03, pages 34-52.
KÄRKKÄINEN, T., JUUTINEN, S., SAARELA, M. & NISSINEN, K. (2018): "Lokidatan käyttö oppilaiden profiloimisessa – sovellus matematiikan PISA-aineistoon". In PISA pintaa syvemmältä: PISA 2015 Suomen pääraportti (PISA National Reports), pages 259-289.
GAVRIUSHENKO, SAARELA, M. & KÄRKKÄINEN, T. (2018): "Towards Evidence-Based Academic Advising Using Learning Analytics". In Communications in Computer and Information Science book series (CCIS, volume 865), Springer International Publishing, pages 44-65.
SEIDEL, N. & SAARELA, M. (2018): "Course of Study Analytics in Distance Learning". To appear in CEUR workshop proceedings.
SAARELA, M. & KÄRKKÄINEN, T. (2017): "Knowledge Discovery from the Programme for International Student Assessment". Book Chapter in Learning Analytics: Fundaments, Applications, and Trends, Springer International Publishing, pages 229 - 267.
SAARELA, M., HÄMÄLÄINEN, J. & KÄRKKÄINEN, T. (2017): "Feature Ranking of Large, Robust, and Weighted Clustering Result". In Proceedings of the 21th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017), Springer International Publishing, pages 96 - 109.
SAARELA, M., RYYNÄNEN, O.-P. & ÄYRÄMÖ, S. (2017): "Predicting hospital associated disability using supervised learning". In Raportti esittelee Value from Public Health Data with Cognitive Computing -projektin osatutkimusten tuloksia, pages 73-83 (D-2).
SAARELA, M. (2017): "Automatic Knowledge Discovery from Sparse and Large-Scale Educational Data. Case Finland". Dissertation. Jyväskylä studies in computing 262.
GAVRIUSHENKO, SAARELA, M. & KÄRKKÄINEN, T. (2017): "Supporting Institutional Awareness and Academic Advising Using Clustered Study Profiles". In Proceedings of the 9th International Conference on Computer Supported Education (CSEDU 2017), pages 35-46.
SAARELA, M., KÄRKKÄINEN, T., LEHTONEN, T., & ROSSI, T. (2016): "Expert-based versus citation-based ranking of scholarly and scientific publication channels". Journal of Informetrics, Vol. 10.3, pages 693 - 718.
SAARELA, M., YENER, B., ZAKI, M, & KÄRKKÄINEN, T. (2016): "Predicting Math Performance from Raw Large-Scale Educational Assessments Data : A Machine Learning Approach". Workshop on Machine Learning for Digital Education and Assessment Systems of the 33rd International Conference on Machine Learning (ICML 2016).
SAARELA, M., & KÄRKKÄINEN, T. (2015): "Analysing Student Performance using Sparse Data of Core Bachelor Courses". Journal of Educational Data Mining, Vol. 7.1, pages 3 − 32.
SAARELA, M., & KÄRKKÄINEN, T. (2015): "Weighted Clustering of Sparse Educational Data". In Proceedings of The 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2015), pages 337 − 342.
KÄRKKÄINEN, T., & SAARELA, M. (2015): "Robust Principal Component Analysis of Data with Missing Values". In Proceedings of The 11th International Conference on Machine Learning and Data Mining (MLDM 2015), Springer International Publishing, pages 140 − 154.
SAARELA, M., & KÄRKKÄINEN, T. (2015): "Do Country Stereotypes exist in Educational Data? A Clustering Approach for Large, Sparse, and Weighted Data". In Proceedings of The 8th International Conference on Educational Data Mining (EDM 2015), pages 156 − 163.
SAARELA, M., & KÄRKKÄINEN, T. (2014): "Discovering Gender-Specific Knowledge from Finnish Basic Education using PISA Scale Indices". In Proceedings of The 7th International Conference on Educational Data Mining (EDM 2014), pages 60 − 68.