MRES.B.02.08 E-learning: Mining, Analytics and Visualization of Educational Data (MRES.B.02.08)
Maria RANGOUSSI, Katerina ZACHARIADOU
This course module focuses on E-Learning technologies as implemented in modern e-learning platforms that support synchronous and/or asynchronous education events and activities. The core content of the module is Educational Data Mining (EDM) a topic that covers the collection, retrieval, analysis and visualization of educational data produced in digital form. Such data is automatically collected by an e-learning platform (an LMS or a VLE, such as moodle) during the interaction of learners with the platform and the learning content as well as the collaboration of learners who work in teams over a platform. Educational data is subsequently analyzed in order to answer specific research questions that aim to provide feedback to learners, instructors and decision-making parties in Education, in an attempt to improve the learning outcomes as well as the learning experience. The later field is known as Learning Analytics (LA). Data analysis is performed by artificial intelligence / machine learning algorithms, methods and tools. Data visualization is performed using modern relevant tools and visualization environments.
LessThis course module focuses on E-Learning technologies as implemented in modern e-learning platforms that support synchronous and/or asynchronous education events and activities. The core content of the module is Educational Data Mining (EDM) a topic that covers the collection, retrieval, analysis and visualization of educational data produced in digital form. Such data is automatically collected by an e-learning platform (an LMS or a VLE, such as moodle) during the interaction of learners with the platform and the learning content as well as the collaboration of learners who work in teams over a platform. Educational data is subsequently analyzed in order to answer specific research questions that aim to provide feedback to learners, instructors and decision-making parties in Education, in an attempt to improve the learning outcomes as well as the learning experience. The later field is known as Learning Analytics (LA). Data analysis is performed by artificial intelligence / machine le
This course module focuses on E-Learning technologies as implemented in modern e-learning platforms that support synchronous and/or asynchronous education events and activities. The core content of the module is Educational Data Mining (EDM) a topic that covers the collection, retrieval, analysis and visualization of educational data produced in digital form. Such data is automatically collected by an e-learning platform (an LMS or a VLE, such as moodle) during the interaction of learners with the platform and the learning content as well as the collaboration of learners who work in teams over a platform. Educational data is subsequently analyzed in order to answer specific research questions that aim to provide feedback to learners, instructors and decision-making parties in Education, in an attempt to improve the learning outcomes as well as the learning experience. The later field is known as Learning Analytics (LA). Data analysis is performed by artificial intelligence / machine le
Syllabus
Course Objectives/Goals
Upon successful completion of the course, students are expected to be able to:
- Define EDM and LA and differentiate the two terms
- Describe the major types of educational data, their value and the means and processes for data collection
- State the major problems the relevant research seeks to solve and the major research questions that are open to date
- Implement major Machine Learning algorithms (ANN-DNN, SVM, Decision Trees, Bayesian etc.)
- Recognize as such and solve a classification problem using appropriate Machine Learning algorithms and tools
- Recognize as such and solve a prediction problem using appropriate Machine Learning algorithms and tools
- Recognize as such and solve a clustering problem using appropriate Machine Learning algorithms and tools
- Comparatively evaluate major data visualization tools and select the appropriate for the problem at hand
- Use data visualization tools to visualize educational data for the learner and/or the instructor.
Prerequisites/Prior Knowledge
An undergraduate course on Digital Signal Processing and/or Pattern Recognition would be useful.
Assessment Methods
Student evaluation comes from
- An EDM / LA project (50% of the final grade) – individual or teamwork
- A visualization project (50% of the final grade) – individual or teamwork
Bibliography
- Baker, R. S. J.d., & Inventado, P. S. (2014). Educational data mining and learning analytics. In J. A. Larusson & B. White (Eds.), Learning analytics: From research to practice. Berlin, Germany: Springer.
- Baker, R. S. (2015). Big data and education (2nd ed.). New York, NY: Teachers College, Columbia University.
- D'Mello, S. (2017). Emotional learning analytics. In Handbook of learning analytics (p. 115). New York, NY: SOLAR
- Lang, C., Siemens, G., Wise, A., & Gasevic, D. (2017). Handbook of learning analytics. SOLAR, Society for Learning Analytics and Research. New York, NY: SOLAR.
- Leitner, P., Ebner, M., & Ebner, M. (2019). Learning analytics challenges to overcome in higher education institutions. In Utilizing learning analytics to support study success (pp. 91–104). Cham, Switzerland: Springer
- Romero, C., & Ventura, S. (2006). Data mining in E-learning. Southampton, England: Wit-Press
- Romero, C., Ventura, S., Pechenizky, M., & Baker, R. (2010). Handbook of educational data mining. Data Mining and Knowledge Discovery Series. Boca Raton, FL: Editorial Chapman and Hall/CRC Press, Taylor & Francis Group.
Additional info
RESEARCH ARTICLES
- P. Macfadyen and S. Dawson, “Mining LMS data to develop an ‘‘early warning system’’ for educators: A proof of concept,” Computers and Education, vol. 54, no. 2, pp. 588–599, 2010, doi:10.1016/j.compedu.2009.09.008.
- Siemens and R. S. Baker, “Learning analytics and educational data mining: Towards communication and collaboration,” In Proc. 2nd International Conference on Learning Analytics and Knowledge (LAK’12), Vancouver, BC, Canada, 2012, pp. 252–254
- Romero and S. Ventura, “Data mining in education,” WIREs Data Mining and Knowledge Discovery, vol. 3, pp. 12-27, 2013, doi: 10.1002/widm.1075.
- Peña-Ayala, “Educational data mining: A survey and a data mining-based analysis of recent works,” Expert Systems with Applications, vol. 41 (4 part 1), pp. 1432-1462, 2014.
- Aldowah, H. Al-Samarraie, and W. M. Fauzy, “Educational data mining and learning analytics for 21st century higher education: A review and synthesis,” Telematics and Informatics, vol. 37, pp. 13-49, 2019.
- H. Bin Roslan and C. J. Chen, “Educational Data Mining for Student Performance Prediction: A Systematic Literature Review (2015-2021),” International Journal of Emerging Technologies in Learning (iJET), vol. 17, no. 5, pp. 147–179, 2022, https://doi.org/10.3991/ijet.v17i05.27685.
- Charitopoulos, M. Rangoussi, and D. Koulouriotis, “On the Use of Soft Computing Methods in Educational Data Mining and Learning Analytics Research: a Review of Years 2010–2018,” International Journal of Artificial Intelligence in Education, vol. 30, no. 3, pp. 371-430, 2020, doi:10.1007/s40593-020-00200-8.
- Roll and R. L. Wylie, “Evolution and revolution in artificial intelligence in education”, International Journal of Artificial Intelligence in Education, vol. 26, no. 2, pp. 582–599, 2016.
- Imran, S. Latif, D. Mehmood, and M. S. Shah, “Student Academic Performance Prediction using Supervised Learning Techniques,” International Journal of Emerging Technologies in Learning (iJET), vol. 14, no. 14, pp. 92–104, 2019, https://doi.org/10.3991/ijet.v14i14.10310.
- Polyzou and G. Karypis, “Feature Extraction for Next-Term Prediction of Poor Student Performance,” IEEE Trans. on Learning Technologies, vol. 12, pp. 237–248, 2019.
- T. Tempelaar, B. Rienties, and B. Giesbers, “In search for the most informative data for feedback generation: Learning analytics in a data-rich context,” Computers in Human Behavior, vol. 47, pp. 157–167, 2015.
- Jokhan, B. Sharma, and S. Singh, “Early warning system as a predictor for student performance in higher education blended courses,” Studies in Higher Education, vol. 44, no. 11, pp. 1900-1911, 2019, doi:10.1080/03075079.2018.1466872.
TOOLS
- RapidMiner: https://rapidminer.com/
- WEKA: https://www.cs.waikato.ac.nz/ml/weka/
- GEPHI: https://gephi.org/
- ProM: https://promtools.org/
- TABLEAU: https://www.tableau.com/
- MATLAB: https://www.mathworks.com/products/matlab.html
WEBSITES
Upon successful completion of the course, students are expected to be able to:
- Define EDM and LA and differentiate the two terms
- Describe the major types of educational data, their value and the means and processes for data collection
- State the major problems the relevant research seeks to solve and the major research questions that are open to date
- Implement major Machine Learning algorithms (ANN-DNN, SVM, Decision Trees, Bayesian etc.)
- Recognize as such and solve a classification problem using appropriate Machine Learning algorithms and tools
- Recognize as such and solve a prediction problem using appropriate Machine Learning algorithms and tools
- Recognize as such and solve a clustering problem using appropriate Machine Learning algorithms and tools
- Comparatively evaluate major data visualization tools and select the appropriate for the problem at hand
- Use data visualization tools to visualize educational data for the learner and/or the instructor.
An undergraduate course on Digital Signal Processing and/or Pattern Recognition would be useful.
Student evaluation comes from
- An EDM / LA project (50% of the final grade) – individual or teamwork
- A visualization project (50% of the final grade) – individual or teamwork
- Baker, R. S. J.d., & Inventado, P. S. (2014). Educational data mining and learning analytics. In J. A. Larusson & B. White (Eds.), Learning analytics: From research to practice. Berlin, Germany: Springer.
- Baker, R. S. (2015). Big data and education (2nd ed.). New York, NY: Teachers College, Columbia University.
- D'Mello, S. (2017). Emotional learning analytics. In Handbook of learning analytics (p. 115). New York, NY: SOLAR
- Lang, C., Siemens, G., Wise, A., & Gasevic, D. (2017). Handbook of learning analytics. SOLAR, Society for Learning Analytics and Research. New York, NY: SOLAR.
- Leitner, P., Ebner, M., & Ebner, M. (2019). Learning analytics challenges to overcome in higher education institutions. In Utilizing learning analytics to support study success (pp. 91–104). Cham, Switzerland: Springer
- Romero, C., & Ventura, S. (2006). Data mining in E-learning. Southampton, England: Wit-Press
- Romero, C., Ventura, S., Pechenizky, M., & Baker, R. (2010). Handbook of educational data mining. Data Mining and Knowledge Discovery Series. Boca Raton, FL: Editorial Chapman and Hall/CRC Press, Taylor & Francis Group.
RESEARCH ARTICLES
- P. Macfadyen and S. Dawson, “Mining LMS data to develop an ‘‘early warning system’’ for educators: A proof of concept,” Computers and Education, vol. 54, no. 2, pp. 588–599, 2010, doi:10.1016/j.compedu.2009.09.008.
- Siemens and R. S. Baker, “Learning analytics and educational data mining: Towards communication and collaboration,” In Proc. 2nd International Conference on Learning Analytics and Knowledge (LAK’12), Vancouver, BC, Canada, 2012, pp. 252–254
- Romero and S. Ventura, “Data mining in education,” WIREs Data Mining and Knowledge Discovery, vol. 3, pp. 12-27, 2013, doi: 10.1002/widm.1075.
- Peña-Ayala, “Educational data mining: A survey and a data mining-based analysis of recent works,” Expert Systems with Applications, vol. 41 (4 part 1), pp. 1432-1462, 2014.
- Aldowah, H. Al-Samarraie, and W. M. Fauzy, “Educational data mining and learning analytics for 21st century higher education: A review and synthesis,” Telematics and Informatics, vol. 37, pp. 13-49, 2019.
- H. Bin Roslan and C. J. Chen, “Educational Data Mining for Student Performance Prediction: A Systematic Literature Review (2015-2021),” International Journal of Emerging Technologies in Learning (iJET), vol. 17, no. 5, pp. 147–179, 2022, https://doi.org/10.3991/ijet.v17i05.27685.
- Charitopoulos, M. Rangoussi, and D. Koulouriotis, “On the Use of Soft Computing Methods in Educational Data Mining and Learning Analytics Research: a Review of Years 2010–2018,” International Journal of Artificial Intelligence in Education, vol. 30, no. 3, pp. 371-430, 2020, doi:10.1007/s40593-020-00200-8.
- Roll and R. L. Wylie, “Evolution and revolution in artificial intelligence in education”, International Journal of Artificial Intelligence in Education, vol. 26, no. 2, pp. 582–599, 2016.
- Imran, S. Latif, D. Mehmood, and M. S. Shah, “Student Academic Performance Prediction using Supervised Learning Techniques,” International Journal of Emerging Technologies in Learning (iJET), vol. 14, no. 14, pp. 92–104, 2019, https://doi.org/10.3991/ijet.v14i14.10310.
- Polyzou and G. Karypis, “Feature Extraction for Next-Term Prediction of Poor Student Performance,” IEEE Trans. on Learning Technologies, vol. 12, pp. 237–248, 2019.
- T. Tempelaar, B. Rienties, and B. Giesbers, “In search for the most informative data for feedback generation: Learning analytics in a data-rich context,” Computers in Human Behavior, vol. 47, pp. 157–167, 2015.
- Jokhan, B. Sharma, and S. Singh, “Early warning system as a predictor for student performance in higher education blended courses,” Studies in Higher Education, vol. 44, no. 11, pp. 1900-1911, 2019, doi:10.1080/03075079.2018.1466872.
TOOLS
- RapidMiner: https://rapidminer.com/
- WEKA: https://www.cs.waikato.ac.nz/ml/weka/
- GEPHI: https://gephi.org/
- ProM: https://promtools.org/
- TABLEAU: https://www.tableau.com/
- MATLAB: https://www.mathworks.com/products/matlab.html
WEBSITES
Students can find sample evaluation material for this course module under the "DOCUMENTS" in the left frame menu.
The concepts of Big Data and Data Mining are defined and exemplified in this Unit. The same concepts are narrowed down to the field of Education and their role and contribution in education-related research are examined.
Educational Data Mining (EDM) and Learning Analytics (LA) are often used as synonyms in current research. This Unit juxtaposes their aims, uses, methodologies and inner mechanisms / algorithms in order to shed light to their common as well as to their differentiating features.
Current education-related research employs modern EDM and/or LA methods and tools to get answers to a spectrum of research questions pertaining to practically all aspects of education and the respective stakeholders. An overview along with an attempt to discern open issues is offered in this Unit.
This Unit presents a rough classification of education-related problems addressed by EDM and relates each class of problems to the major / most popular Machine Learning methods and tools employed to address them.
Classification, Prediction and Clustering represent three major classes of methods that scientists frequently employ to address problems across practically any discipline, Education being no exception. Worked examples and case studies from the field of Education are presented in this Unit for each of these tasks.
Data volume as well as data dimensionality having dramatically increased in the era of Bid Data, the role of visualization methods and tools has emerged as critical to the researcher. This Unit presents the current trend that shifts from the more traditional, descriptive data visualization methods and tools to the more dynamic paradigm of visual analytics.
Calendar
Announcements
- - There are no announcements -
