solar - learning analytics, the state of the art
DESCRIPTION
On 3 May 2012, the Society for Learning Analytics Research (SoLAR) organised a learning analytics summit. The summit took place in Vancouver, Canada, following the second Learning Ananlytics and Knowledge conference (LAK12). This presentation summarised the state of the art in learning analytics at the time, identifying drivers, challenges, interest groups and future challenges.TRANSCRIPT
Learning Analytics 2012:Review and Future Challenges
Dr Rebecca Ferguson
The Open University, UK
The measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs.
LAK 11 Call for Papers
Learning analytics
Driver 1: Big data
Formal: Blackboard, MoodleInformal: Facebook, OpenLearn
•Interaction data•Personal data•Systems information•Academic information•Social information
Technical challenge
How can we extract value from these big sets of learning-related data?
Driver 2: Online learning
Infographic: http://sloanconsortium.org/sites/default/files/pages/OnlineLearningSurvey-Infographic-1.png
Educational challenge
How can we optimise opportunities for learning?
Driver 3: Political concerns
The goal of creating an interconnected feedback system would be to ensure that key decisions about learning are informed by data and that data are aggregated and made accessible at all levels of the education system for continuous improvement.
US Department of Education, 2010Table: http://www.oecd.org/document/2/0,3746,en_2649_39263238_48634114_1_1_1_1,00.html
Political challenge
How can we substantially improve learning opportunities and educational results at national or international levels?
Three main interest groups
Learners and teachers
Schools and colleges
Governments
Data-driven analytics
Use of web mining techniques•Clustering•Classification•Outlier detection
•Association rule mining•Sequential pattern mining
•Text mining
Effective better learners
The goal:Turn learners into effective better learners
Focus on:data mining and machine learning techniques… to enhance web-based learning environments for the educator to better evaluate the learning process, as well as for the learners to help them in their learning endeavour
Zaïane, 2001
Learning-focused perspectives
Knowledge is constructed through social negotiation
Learning takes place in networks and in communities of practice
Learning can be scaffolded by a more able other Dawson, McWilliam, Tan, 2008
Strategic perspectives – 2007/8
by 2020 the overall portion of the U.S. workforce with a college degree will be lower than it was in 2000
analytics is emerging as a new tool that can address what seem like intractable challenges
analytics has the potential to improve teaching, learning, and student success
EDM and analytics split
• extend geographical focus• make tools easier for educators to use• standardize methods and data across systems• integrate tools within e-learning environments • develop education-specific mining techniques
Disambiguation
Phil Long, George Siemens (2011)
Dividing responsibility
Educational data miningHow can we extract value from these big sets of learning-related data?
Academic (and action) analyticsHow can we substantially improve learning opportunities and educational results at national or international levels?
Learning analyticsHow can we optimise opportunities for learning?
Meeting the challenge
How can we optimise opportunities for learning?
•Maintain focus on this challenge
•Learn from previous work in all three fields
•Integrate experience from different disciplines
•Focus on learners and teachers
Fresh challenges
• Widen range of theory-driven approaches
• Develop methods of presenting analytics clearly
• Adopt standards for the structure and export of data
• Broaden focus from higher education
• Broaden international focus
• Address issues around ethics, privacy and data
• Explore possibilities offered by new data sources