Course

Unit 1

Unit 1: Educational Data Mining (EDM)
Overview: Introduction to EDM; Fundamentals of EDM; Development of this field over time; Historical and recent technical perspectives in EDM; Technical and data infrastructures in EDM; Diverse set of ML algorithms for mining used in EDM; Some evidence-based key solutions; Major failures that the EDM filed has faced; Open challenges.

Unit 2

Unit 2: Learning Analytics (LA)
Overview: Introduction to LA; Fundamentals of LA; Development of this field over time; Historical and interdisciplinary perspectives in LA; LA solutions, tools, infrastructures, and architectures; Monomodality in LA for more than a decade; Diverse set of ML algorithms for predicting performance across different educational constructs; Integration and adoption challenges of LA in formal education; Open research challenges; Low-cost LA and Global South.

Unit 3

Unit 3: EDM and LA
Overview: Differences in philosophical, social, educational, computational, and psychological stances in EDM and LA; Data processing pipelines; What theories help to build the pipelines in these two fields; ML and AI lenses in the fields; Analysis techniques used in LA and EDM; Limitations and opportunities centered to the required data in these two fields.

Unit 4

Unit 4: Modeling and Interpretation of Educational Data across these two fields
Overview: Latent constructs in measuring educational constructs, especially related to learning and teaching; Identification of constructs and modalities with technical advancements while keeping educational theories and pedagogies in the center; Data preparation, organization, fusion, analysis, and visualization; Sense-making of visualized data with educational stakeholders.

Unit 5

Unit 5: Multimodal Learning Analytics (MMLA)
Overview: Mono-modality versus multimodality in learning; Need of MMLA over LA; Technical advancements that enable the tapping of multiple modalities from a learning situation; Complexities in designing an MMLA situation by involving cross-disciplinary stakeholders like teachers, students, researchers, and syllabus designers; Complexities in designing and following any standard multimodal data processing pipeline; Challenges in the development of MMLA solutions; Integration and adoption issues; Data literacy of educational stakeholders and MMLA.

Prerequisites: A foundational understanding of statistics, proficiency in programming languages such as Python or R, and a basic knowledge of educational theory and practices.

Summary:
This course delves into the interdisciplinary domains of data mining, machine learning, and educational theory to analyze and interpret educational data effectively. Spanning five units, the course begins with exploring Educational Data Mining (EDM), tracing its historical development, technical foundations, and key challenges. Subsequently, it transitions to Learning Analytics (LA), examining its evolution, tools, and integration challenges within formal education systems. The course then explores the intersection of EDM and LA, elucidating their philosophical, social, and computational disparities while highlighting their shared analysis techniques and data processing pipelines. Furthermore, students will gain insights into modelling and interpreting educational data, emphasizing the fusion of technical advancements with educational theories. Finally, the course culminates in Multimodal Learning Analytics (MMLA), addressing the complexities of analyzing multiple modalities in learning environments and the challenges associated with stakeholder involvement, data processing, and integration. Throughout the course, students will use diverse machine learning algorithms, data visualization techniques, and real-world case studies to develop a nuanced understanding of leveraging data for educational insights and decision-making.

Course Objectives:

1. Understand the fundamental principles and historical development of Educational Data Mining (EDM) and Learning Analytics (LA).
2. Explore diverse machine learning algorithms and data processing pipelines utilized in EDM and LA for analyzing educational data.
3. Investigate the interdisciplinary nature of EDM and LA, examining philosophical, social, and computational perspectives.
4. Develop modeling, interpreting, and visualizing educational data skills to derive actionable insights for educational stakeholders.
5. Analyze the challenges and opportunities in implementing Multimodal Learning Analytics (MMLA) solutions in educational settings.

Course Outcomes:

• CO1: Demonstrate proficiency in utilizing machine learning algorithms and data processing techniques for educational data analysis.
• CO2: Critically evaluate EDM and LA solutions’ strengths, limitations, and ethical implications in educational contexts.
• CO3: Apply theoretical frameworks and analytical methods to model and interpret educational data effectively.
• CO4: Communicate insights from educational data analysis to diverse stakeholders through clear and concise visualizations and reports.
• CO5: Develop strategies to address integration and adoption challenges in implementing MMLA solutions, fostering data literacy among educational stakeholders.

Skills:

1. Develop proficiency in statistical analysis, data visualization, and programming, essential for interpreting and communicating insights from educational data.
2. Acquire specialized knowledge in educational theory and practices, enabling the integration of data-driven insights into instructional design and pedagogical decision-making.
3. Cultivate critical thinking and problem-solving skills to address complex challenges in educational data mining, learning analytics, and multimodal learning analytics.
4. Enhance interdisciplinary collaboration and communication skills to effectively engage with diverse stakeholders in implementing data-driven educational interventions, including educators, researchers, and policymakers.
5. Foster a commitment to ethical data practices and a deep understanding of privacy and security considerations when handling sensitive educational data, ensuring responsible use and dissemination of insights derived from data analysis.

Course Outcomes (CO) – Program Outcomes (PO) Mappings

1. Peña-Ayala, A. (2014). Educational data mining. Studies in Computational Intelligence, 524.
2. Larusson, J. A., & White, B. (Eds.). (2014). Learning analytics: From research to practice (Vol. 13). Springer.
3. Romero, C., Ventura, S., Pechenizkiy, M., & Baker, R. S. (Eds.). (2010). Handbook of educational data mining. CRC press.
4. Rodriguez, C. O. (2013). Two distinct course formats in the delivery of connectivist MOOCs. Turkish Online Journal of Distance Education, 14(2), 66-80.
5. ElAtia, S., Ipperciel, D., & Zaïane, O. R. (Eds.). (2016). Data mining and learning analytics: Applications in educational research. John Wiley & Sons.
6. Lester, J., Klein, C., Johri, A., & Rangwala, H. (Eds.). (2018). Learning analytics in higher education: Current innovations, future potential, and practical applications. Routledge.
7. Romero, C., & Ventura, S. (2010). Educational data mining: a review of the state of the art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (applications and reviews), 40(6),
   601-618.
8. Krumm, A., Means, B., & Bienkowski, M. (2018). Learning analytics goes to school: A collaborative approach to improving education. Routledge.
9. Siemens, G., & Baker, R. S. D. (2012, April). Learning analytics and educational data mining: towards communication and collaboration. In Proceedings of the 2nd international conference on learning analytics and knowledge (pp. 252-254).
10. Daniel, B. K. (Ed.). (2016). Big data and learning analytics in higher education: current theory and practice. Springer.
11. Oviatt, S., Schuller, B., Cohen, P., Sonntag, D., & Potamianos, G. (2017). The handbook of multimodal-multisensor interfaces, volume 1: Foundations, user modeling, and common modality combinations. Morgan & Claypool.
12. Shankar, S.K., Ruiz-Calleja, A., Prieto, L.P., Rodríguez-Triana, M.J., Chejara, P., & Tripathi, S. (2023), CIMLA: A Modular and Modifiable Data Preparation, Organization, and Fusion Infrastructure to Partially Support the Development of Context-aware MMLA Solutions. JUCS – Journal of Universal Computer Science 29(3): 265-297. https://doi.org/10.3897/jucs.84558
13. Shankar, S. K., Prieto, L. P., Rodríguez-Triana, M. J., & Ruiz-Calleja, A. (2018, July). A review of multimodal learning analytics architectures. In IEEE 18th International Conference on Advanced Learning Technologies (ICALT 2018). IEEE, (pp. 212-214). https://doi.org/10.1109/ICALT.2018.00057

1. de Baker, R. S. J., & Inventado, P. S. (2014). Chapter X: Educational Data Mining and Learning Analytics. Comput. Sci, 7, 1-16.
2. Ferguson, R. (2012). Learning analytics: drivers, developments and challenges. International Journal of Technology Enhanced Learning, 4(5-6), 304-317.
3. Siemens, G., & Gasevic, D. (2012). Guest editorial-learning and knowledge analytics. Journal of Educational Technology & Society, 15(3), 1-2.
4. Romero, C., & Ventura, S. (2010). Educational data mining: a review of the state of the art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (applications and reviews), 40(6),
   601-618.
5. Macfadyen, L. P., & Dawson, S. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & education, 54(2), 588-599.
6. Ellis, R. A., Han, F., & Pardo, A. (2017). Improving learning analytics–Combining observational and self-report data on student learning. Journal of Educational Technology & Society, 20(3), 158-169.
7. Elmoazen, R., Saqr, M., Tedre, M., & Hirsto, L. (2022). A systematic literature review of empirical research on epistemic network analysis in education. IEEE Access, 10, 17330-17348.
8. Lynch, R., & Dembo, M. (2004). The relationship between self-regulation and online learning in a blended learning context. International Review of Research in Open and Distributed Learning, 5(2), 1-16.
9. Slade, S., & Prinsloo, P. (2013). Learning analytics: Ethical issues and dilemmas. American Behavioral Scientist, 57(10), 1510-1529.
10. Chejara, P., Prieto, L. P., Rodríguez-Triana, M. J., Ruiz-Calleja, A., Kasepalu, R., & Shankar, S.K. (2023, March). How to Build More Generalizable Models for Collaboration Quality? Lessons Learned from Exploring Multi-Context Audio-Log Datasets using Multimodal Learning Analytics. In LAK23: 13th International Learning Analytics and Knowledge Conference (LAK2023). ACM, USA, 111–121. https://doi.org/10.1145/3576050.3576144

Evaluation Pattern:

*CA – Can be Quizzes, Assignment, Projects, and Reports, and Seminar