Introduction to Learning and Knowledge Analytics
An Open Online Course
January 10-February 20, 2011

Technology Enhanced Knowledge Research Institute, Athabasca University

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

This is an open (and free) course offered by the Technology Enhanced Knowledge Research Institute (TEKRI) at Athabasca University. The course is not offered for-credit and is intended for professional development and to raise awareness of the role that analytics can play in education, learning and development, and in evaluating organizational information flows.

Course Description
The growth of data surpasses the ability of organizations or individuals to make sense of it. This concern is particularly pronounced in relation to knowledge, collaboration within an organization, teaching, and learning. Learning institutions and corporations make little use of the data learners "throw off" in the process of accessing learning materials, interacting with educators and peers, and creating new content. In an age where educational institutions are under growing pressure to reduce costs and increase efficiency, analytics promises to be an important lens through which to view and plan for change at course and institutions levels. Corporations likewise face pressure for increased competitiveness and productivity, a challenge that requires important contributions in organizational capacity building from work place and informal learning:
Advances in knowledge modeling and representation, the semantic web, data mining, analytics, and open data form a foundation for new models of knowledge development and analysis. The technical complexity of this nascent field is paralleled by a transition within the full spectrum of learning (education, work place learning, informal learning) to social, networked learning. These technical, pedagogical, and social domains must be brought into dialogue with each other to ensure that interventions and organizational systems serve the needs of all stakeholders. As a multi-disciplinary field, learning analytics requires contributions from learning sciences, computer sciences, statistics,  information sciences, sociology, and psychology.

Learning and Knowledge Analytics 2011 is a conceptual and exploratory introduction to the role of analytics in learning and knowledge development. Most of the topics do not require advanced statistical methods or technical skills. Topics covered during the six-week course will introduce participants to a systemic and integrated view of analytics in the following settings:
The course will also lay a foundation for the upcoming 1st International Learning Analytics and Knowledge Conference held in February, 2011 in Banff, Canada. More information on the conference is available here:

Course Tag
#LAK11 (for Diigo, Twitter, blogs, Delicious)

As an introductory course, faculty, administrators, grad students, learning and development professionals, and organizational leaders will benefit from the topics and concepts covered. While not a prerequisite, participants will find it helpful to have some level of existing familiarity with the Internet, online social networks, and web-based communications - particularly with synchronous and asynchronous technologies for communicating, collaborating and sharing information. As an interactive open course, participants will find that valuable learning occurs, and social connections are formed, through offering contributions, ideas, suggestions in course Moodle  forums, live sessions, or on their blogs.

Course Outcomes
As a result of active participation throughout this course, participants can expect to:
  1. Define learning and knowledge analytics
  2. Map the developments of technologies and practices that influence learning and knowledge analytics as well as developments and trends peripheral to the field.
  3. Evaluate prominent analytics methods and tools and determine appropriate contexts where the methods would be most effective.
  4. Describe how “big data” and data-driven decision making differ from traditional decision making and the potential future implications of this transition.
  5. Design a learning analytics implementation plan at a course level. 
  6. Evaluate the potential impact of the semantic web and linked data on learning resources and curriculum.
  7. Detail various elements organizational leaders need to consider to roll out an integrated knowledge and learning analytics model in an organizational setting.
  8. Describe and evaluate developing trends in learning and knowledge analytics and develop models for their potential impact on teaching, learning, and organizational knowledge.

George Siemens
(TEKRI, Athabasca University)
Jon Dron
(SCIS, Athabasca University)
Dave Cormier
(University of Prince Edward Island)
Sylvia Currie
Tanya Elias
(Athabasca University)

Important Links

Course blog:
Google Group (Daily Email):
Netvibes aggregation:

Technologies Used
Various technologies will be used throughout the course - some for interaction with other participants and others as analytic tools. A partial list of the technologies we will use include:

Moodle: (help resources for managing the forums are available here:
Google Groups:
Vue or CMAP: or
OECD FactBook:
...and numerous other tools as shared by course participants or required based on discussion.

Time Required
Depending on your familiarity with the concepts of analytics, this course can take between 5-10 hours per week to complete course readings, participate in discussions, complete activities, and attend the live sessions. If you are not able to commit the time required, you can select the level of participation that best meets your needs. Many of the guest presentations, for example, can be treated as stand alone topics. In order to gain a broad understanding of the role of knowledge and learning analytics, sustained participation of the course is warranted.

Weekly Activities
This course has synchronous and asynchronous components. The asynchronous component includes discussion forums (Moodle) and/or blogs/Twitter. The synchronous component involves a weekly guest presenter (generally on Tuesdays) and a Friday follow up informal discussion - both to be held in Elluminate.

Recommended Weekly Activities

 Recommended weekly activities are offered, but participants can engage in the course at any level that their schedule or interests permit.

Getting Started:
  1. Set a few goals: what do you want to gain from the course? How much effort/time are you able/willing to commit? If you’re comfortable do so, please share your goals in the introductory discussion forums.
  2. Download VUE ( or CMAP ( Update your course map on a weekly basis to add new concepts or ideas. Knowledge (or concept) maps can be quite helpful in communicating to others how you see the different elements of the course connecting.
  3. Weekly blogging: reflect on how the discussions of the week can translate into your work setting.
  4. Each week, activities have been planned that will introduce you to different tools and methods for analytics. These activities may seem a bit complex, but the benefit for engaging in them will be a significantly enhanced understanding on analytics approaches.

How does this course work?
This is an open course—no fees are required to join and participate. The course is based on the Massive Open Online Course (MOOC) model that George Siemens and Dave Cormier have run on various topics over the last three years. We heavily emphasize participant contributions and discussions as a means of exploring the diversity of complex subject areas.
Your contributions will make the course a success.

You can contribute in numerous areas: Moodle, live discussions, Twitter, your blog, Second Life, or any other site that interests you. If you feel that we, as course designers, have neglected a particular feature that would help you learn better, then chances are that a few others share your view. And we encourage you to rectify our oversight. As a distributed, open course, we view our actions of pulling together a syllabus and planning weekly topics, readings, and guest presentations as a foundation or learning platform. You are encouraged to build on that platform in whatever way helps you learn and share the most.

Video tutorials introducing the open online course format are detailed here:

Each week will start off with a link to a short summary of the topic, links to relevant readings, and short podcasts/video interviews.

Daily emails will be sent to all course participants summarizing course activity or highlighting important resources or contributions. To receive daily emails, please join If you prefer not to join Google Groups, all postings will be available via RSS and public archive.

Two (sometimes three) live sessions will be held in Elluminate each week. One session will involve a guest speaker addressing an important topic in the course, the second will consist of a weekly discussion with course facilitators.

Netvibes will be used to aggregate blog posts ( Please submit your blog post by emailing me the URL at:

Important Dates

All sessions will be held here in Elluminate:

Week 1: John Fritz: January 11, 1:00 pm, MST
Week 2: Ryan S.J.d. Baker: January 18, 1:00 pm, MST
Week 3: Dragan Gasevic: January 25, 1:00 pm, MST
Week 4: John Whitmer: February 3, 1:00 pm MST
              Dave Snowden: February 4, Time TBD
Week 5: Linda Baer, February 8, Time TBD
Week 6: Simon Buckingham Shum, February 17, 1 pm MST

Course Schedule

Week 1 (Jan 10-16): Introduction to learning and knowledge analytics

Topic Introduction

We produce an enormous quantity of data on a daily basis. Consider the data trails you leave in your daily routine:
We live in digital times. The conversations that used to evaporate around the water cooler are now digitized, waiting for a clever algorithm for analysis. The potential of analytics to increase employee efficiency, match the right people to the right tasks, and to improve access to help resources is tremendous. But significant privacy and ethics concerns exist. Data silos protect individuals from inappropriate use of *our* data. We don’t necessarily want our doctor, insurance provider, or banker to know us fully. Cross-data silo access products are far more accurate representations of who we are (and what our interests are) than we might feel comfortable sharing.

When applied to learning - corporate, higher education, K-12 - analytics raise similar concerns about the interplay between the value between transparent data silos and privacy and ethics. This course will explore learning and knowledge analytics, including analytics methods and models, systemic application, potential data sources, the “soft/human/non-quantifiable” aspect of learning, as well as privacy and ethical considerations in deploying analytics.

In week one, we will focus mainly on building some familiarity with the concepts (and language) of learning and knowledge analytics. We define learning analytics as: “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” (Learning Analytics 2011 Conference site:

Readings & Resources
Why now?
Technologies used this week
Blogs (if you decide to blog in addition to Moodle forum participation)
VUE (if you decide to use it to create your concept map)

Guest Speaker
John Fritz:
Time: January 11, 1 pm Mountain Time...see time zone conversions
Location: Elluminate -

Related articles for additional reading
Amy Sliva, V.S. Subrahmanian, Vanina Martinez and Gerardo I. Simari, The SOMA Terror Organization Portal (STOP): social network and analytic tools for the real-time analysis of terror groups
Romero, C., & Ventura, S. (2007). Educational data mining: A survey from 1995 to 2005. [Article]. Expert Systems with Applications, 33(1), 135-146.

Participate in forums for Week 1:
Create a Hunch Account: . Go through the process of personalizing your account (i.e. answer the Hunch questions).
Start searching/playing
What are your reactions? How can this model be used for teaching/learning?
Share your views in the Moodle discussion forum for

Week 2 (Jan 17-23): Rise of “Big Data” and Data Scientists

Topic Introduction

Data and data analysis is changing business, health care, society, and education, largely necessitated by growth in abundance of data. As data mining and analytics develop in technique and application, their influence on decision makers will increased. "Big data" is challenging long-established methods within science.
Data scientists (though some argue it's not a useful term - see Quora readings this week) have enormous control over how we experience data and what is known about us by businesses and governments. How does big data impact education? What roles do data scientists and practitioners play in corporates, K-12 schools, and higher education? We'll tackle these topics in greater detail this week.

Readings & Resources

New technologies used this week
Diigo/Delicious: tag resources with LAK11
Share your Twitter ID in the moodle discussion forum ( so you can connect with others in LAK11 who are also on Twitter.

Guest Speaker
Ryan S. J.D. Baker:
Time: January 18, 1 pm Mountain Time...see time zone conversions
Location: Elluminate -

Additional Resources

IBM Smarter Planet:
Data Blogs:
And meta-list on Quora:
Data Science (scientist) resources
Taxonomy of Data Science:
Data Science Venn Diagram:

Participate in forums for Week 2:
Download SNAPP:
Run SNAPP on moodle forums
In the discussion forum for the week (or on your blog) detail the value of this tool for educators.
What is the benefit of SNAPP?
What additional functionality is required?
If you're using VUE or CMAP to develop your concept map, add new concepts from this week and detail connections to previous concepts.

Week 3 (Jan 24-30): Semantic Web, Linked Data, & Intelligent Curriculum

Topic Introduction:

As the semantic web develops and knowledge is mapped, it can be linked to existing analysis models in order to provide personalized and adaptive content for learners. Personalized and adaptive learning has been a dream of educators for decades. Developments with linked data offer new promise in realizing a scalable system of learning. Through readings, videos, and discussions this week, we will clarify frequently misunderstood terms: semantic web, linked data, and the semantic web.

Readings & Resources:

New technologies used this week:

Guest Speaker:
Dragan Gasevic:
Time: January 25, 1 pm Mountain Time...see time zone conversions
Location: Elluminate -

Kimberly Arnold, Purdue Signals project
Time: January 26, 1:30 pm Mountain Time...see time zone conversions (please note the changed time)
Location: Elluminate -

Additional readings/resources:
The Joy of Stats (Hans Rosling)
Play around with Freebase:

Participate in forums for Week 3:
If you're using VUE or CMAP to develop your concept map, add new concepts from this week and detail connections to previous concepts.
To prepare for Week 4, start tagging (in delicious/diigo) resources and tools for conducting analysis of data.
Review NodeXL:

Week 4 (Jan 31-Feb 6): Tools for, and examples of, analytics

Topic Introduction:

Analytics tools for learning are still developing, with limited consensus to date on their role in organizations. Many analytics tools adopt or extend functionality of innovations in emerging technologies. While nascent, these tools provide an indication of how educator/learner/technology roles will be reshaped in the next decade. This week will lay the foundation for discussion in Week 6, where we'll consider what a data-driven world of education will look like...and what we can do to ensure it doesn't become a nightmare.

Visualization of data is an important aspect of analytics. Once patterns are discernible in data, we need to present that data in a way that is clear, concise, and visually appealing. Resources and discussion this week will explore visualization briefly. However, visualization is a reasonably well-developed discipline and requires greater study than is possible in a quick overview.

Readings & Resources:
Play around with a few of these tools:
Darwin Awareness Engine:

New technologies used this week:
RealTime, Springer
OECD Factbook
Darwing Awereness Engine

Guest Speaker:

Dave Snowden: - CANCELLED - No live session this week

Participate in forums for Week 4:
Try playing with a few analytics tools:
- Gephi: Download dataset:
- OECD Factbook:
- Gapminder
If you're using VUE or CMAP to develop your concept map, add new concepts from this week and detail connections to previous concepts.

Additional Resources:
Wang, T. and Ren, Y. (2009). Research on Personalized Recommendation Based on Web Usage Mining Using Collaborative Filtering Technique, WSEAS TRANSACTIONS on INFORMATION SCIENCE and APPLICATIONS 1(6).

Week 5 (Feb 7-Feb 13): Organizational Implementation of Learning and Knowledge Analytics

Topic Introduction:

Analytics can be deployed at individual classroom (course) levels. Greatest impact, however, will be when analytics are integrated (integrated Knowledge and Learning Analytics Model - iKLAM) and planned at a systemic level. Analytics should also incorporate online/offline (library, clickers in classroom) data sources. Reducing barriers to information flow is important for systemic-level analytics.

Readings & Resources:
Guest Speaker:
Linda Baer, Gates Foundation:
Time: Tuesday, Feb 8, 1:00 pm Mountain time - see conversions to other time zones

New technologies used this week:

As determined by course participants and discussions.

Activities this week:
Participate in forums for Week 5:
If you're using VUE or CMAP to develop your concept map, add new concepts (models of data collection, use, analysis, and refinement (Campbell, Oblinger) as well as the organizational action analytics model (Norris, Baer, et al)) from this week and detail connections to previous concepts.

Week 6 (Feb 14-Feb 20): What’s next for Learning and Knowledge Analytics?

Topic Introduction:

Learning and knowledge analytics are developing quickly, partly driven by developments in peripheral fields such as business intelligence and analytics in big data and online. Analytics models are fragmented, with limited agreement on: a) how to deploy analytics, b) their role in educational reform, c) success metrics (i.e. patterns of success in learner data), and d) evaluation models of analytics. Additionally, many of the technical components of learning analytics are not yet developed. For example, what is the technical infrastructure underlying learning analytics: identity, tracking distributed activity, educational and knowledge protocols for discovery, recommendation, and ethics? To some degree, existing tools (such as Open ID) can be appropriated for learning and developed. Other technical components of learning and knowledge analytics, however, need to be developed.

Readings & Resources:

Mainly a discussion week - were are we going with analytics? What is needed? What are opportunities? What are the ethical issues around their use? (this topic will likely be a strand throughout the course, so we'll review and extend the discussion this week). What type of technical/conceptual infrastructure is needed for learning analytics deployment?

New technologies used this week:
As determined by course participants and discussions.

Guest Speaker:

Jeff Dougherty, Thomson Reuters
Time: February 14, 1 pm MST... see time zone conversions
Location: Elluminate -

Jon Dron, Athabasca University
Time: February 15, 12, pm MST...see time zone conversions
Location: Elluminate -

Simon Buckingham Shum:
Date: February 17, 1 pm MST...see time zone conversions
Location: Elluminate -

Participate in forums for Week 6:
Finalize your concept map of course elements and share with others in the course

Additional Resources & Readings

Analytics Biblio

Analytics Glossary

Analytics Tools

Educational Data Mining Conference

Handbook of Educational Data Mining

Knowledge Cartography

Learning Analytics Methods and Techniques

Visual Analytics

Community Detection and Mining in Social Media