MOOCs & Learning Analytics
Download as PPTX, PDF2 likes516 views
This document discusses MOOCs and learning analytics. It provides an overview of MOOCs, including their characteristics and growth. It also discusses learning analytics, defining it as measuring data about learners and contexts to optimize learning. Various learning analytics methods and applications are outlined, including at the EDSA and OU. The OU's Analyse tool for early identification of at-risk students using machine learning is also summarized.
MOOCs & Learning Analytics
- 1. MOOCs & Learning Analytics John Domingue & Alexander Mikroyannidis Knowledge Media Institute The Open University, UK
- 3. A revolution in education
- 4. Characteristics of MOOCs • Focus is on social media and peer support / assessment • Heavy use of multimedia and online educational tools • Large numbers of registered learners, especially in MOOCs offered by renowned universities • Low completion rates • Certificates are awarded on completion of a MOOC based on certain criteria, some of which are free of charge and others that incur a fee and may require identity verification.
- 5. PAGE ‹#› Over 1,800,000 FutureLearn sign-ups Over 2,200,000 course sign-ups PROGRESS SINCE LAUNCH In just over a year, FutureLearn has built a large userbase
- 7. Open Educational Resources Open Educational Resources can be described as: “teaching, learning and research resources that reside in the public domain or have been released under an intellectual property license that permits their free use or repurposing by others depending on which Creative Commons license is used” (Atkins et al., 2007)
- 8. iTunes U
- 9. OU iTunes U Stats • Open University on iTunes U was launched on 3rd June 2008 • Now 58 iTunes U Courses • 68,138,000 downloads • Over 9,015,700 visitors downloaded files • Currently averaging 87,500 downloads a week • 449 collections containing 3,485 tracks (1,638 audio, 1,847 video) • 423 OpenLearn study units as eBooks (ePub), representing over 5,000 hours of study • Currently delivering an average of 0.3 TB of data a week
- 10. EDSA MOOC: Process Mining • The EDSA MOOC “Process Mining: Data science in Action” explains the key analysis techniques in process mining. The course provides easy-to-use software, real-life data sets, and practical skills to directly apply the theory in a variety of application domains. • Available on Coursera: https://www.coursera.org/course/procmin • Over 42,000 registered students on its first run
- 11. Planned EDSA courses the Data Science community. Table 3: EDSA Core Curriculum Schedule Topic Schedule Foundations of Data Science M6 Foundations of Big Data M6 Big Data Architecture M6 Distributed Computing M6 Machine Learning, Data Mining and Basic Analytics M6 Process Mining M6 Statistical / Mathematical Foundations M18 D2.1 Data Science Curricula 1 Page 11 of 37 Data Management and Curation M18 Big Data Analytics M18 Data Visualisation M18 Finding Stories in Open Data M18 Programming / Computational Thinking (R and Python) M30 Stream Processing M30 Visual Analytics M30 Data Exploitation including data markets and licensing M30
- 12. Part II: Learning Analytics
- 13. What is Learning Analytics? “The measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs” (1st International Conference on Learning Analytics and Knowledge – LAK 2011 https://tekri.athabascau.ca/analytics/). A “bricolage field, incorporating methods and techniques from a broad range of feeder fields: social network analysis (SNA), machine learning, statistics, intelligent tutors, learning sciences, and others” (Siemens 2014).
- 14. Methods Content analysis – particularly of resources which students create, such as essays. Discourse Analytics – aims to capture meaningful data on student interactions, e.g. by exploring the properties of the language used. Social Learning Analytics (Buckingham Shum et al. 2012b) – aimed at exploring the role of social interactions in learning, the importance of learning networks, discourse used for sensemaking, etc. Disposition Analytics (Brown 2012; Buckingham Shum et al. 2012a) – seeks to capture data regarding student's dispositions to their own learning, and the relationship of these to their learning. For example, “curious” learners may be more inclined to ask questions.
- 15. Applications (Powell & MacNeill 2012) • Individual learners using analytics to reflect on their achievements and patterns of behavior in relation to their peers. • Identification of students who may require extra support and attention. • Helping teachers and support staff to plan supporting interventions with individuals and groups. • Enabling functional groups, such as course teams, to improve current courses or develop new curriculum offerings. • Providing information to help institutional administrators to take decisions on matters such as marketing and recruitment or efficiency and effectiveness measures.
- 16. EDSA approach • With Learning Analytics it will be possible to obtain valuable information about how the students interact with the EDSA courseware, in addition to their own judgments provided via questionnaires. • Our approach is based on tracking learner activities, which consist of interactions between a subject (learner), an object (learning activity) and is bounded with a verb (action performed). • We use the Tin Can API (xAPI) for expressing learner activities and the Learning Locker for storing and visualising them.
- 17. OU Analyse • Using machine-learning based methods for early identification of students at risk of failing. • The overall objective is to significantly improve the retention of OU students. • Approach: – Demographic and VLE (Moodle) data – Four predictive models
- 18. OU Analyse demo http://analyse.kmi.open.ac.uk
- 19. Example: video lecture micro activity
- 20. References • Atkins, D. E., Brown, J. S. & Hammond, A. L. (2007) A Review of the Open Educational Resources (OER) Movement: Achievements, Challenges, and New Opportunities. The William and Flora Hewlett Foundation. • Brown, M., (2012). Learning Analytics: Moving from Concept to Practice. EDUCAUSE Learning Initiative Briefing. http://www.educause.edu/library/resources/learning-analytics- moving-concept-practice • Buckingham Shum, S. and Deakin Crick, R. (2012a). Learning Dispositions and Transferable Competencies: Pedagogy, Modelling and Learning Analytics. Proceedings of the 2nd International Conference on Learning Analytics & Knowledge, Vancouver, 29 Apr-2 May 2012. ACM: New York. pp.92-101. Retrieved from: http://oro.open.ac.uk/32823 • Buckingham Shum, S. and Ferguson, R. (2012b). Social Learning Analytics. Educational Technology & Society Special Issue on Learning & Knowledge Analytics, Eds. G. Siemens & D. Gašević, 15, 3,, 3-26. Retrieved from: http://oro.open.ac.uk/34092 • Powell, S., & MacNeill, S. (2012). Institutional readiness for analytics. Cetis Analytics Series, 1(8). Retrieved from http://publications.cetis.ac.uk/2012/527 • Siemens, G. (2014). Supporting and Promoting Learning Analytics Research. Inaugural Issue of the Journal of Learning Analytics. Journal of Learning Analytics 1(1), 1–2. • Swan, M. (2013). The quantified self: Fundamental disruption in big data science and biological discovery. Big Data, 1(2), 85-99.
Editor's Notes
- #4: MOOCs have led to widespread publicity and also strategic dialogue in the education sector. Exactly where this revolution will lead is not yet known but some radical predictions have been made including the end of the need for university campuses, while milder future outlooks are discussing ‘blended learning’ (combination of traditional lectures with new digital interactive activities).