visualising activity in learning networks using open data and educational analytics
DESCRIPTION
Delivered October13, 2011 in Cape Town South Africa at the 2011 Southern African Association for Institutional Research forum Abstract As more student academic activities involve both institutional and social networks, educational analysts are needing to investigate ways in which this data can be collected and interpreted to enhance learning experiences. Data recorded as students explore personal learning environments is most often not accessible or incomplete. Here we explore some of the approaches that exist to use these social networking platforms along with information from the learning management system and academic records. Combining and analysing this data has allowed us to create a number of interesting visualizations exposing patterns which would have been impossible to glean from looking at the data alone. In an age of data abundance we reflect on using some of these new measures in relation to improving learning design, increasing academic responsiveness and enhanced student experiences.TRANSCRIPT
Visualising activity in learning networks using open data and educational
analytics
Andrew Deacon & Michael Paskevicius
Centre for Educational Technology, University of Cape Town
Southern African Association for Institutional Research
(SAAIR) Forum 2011
Centre for Educational Technology within the Centre for Higher Education Development
– Michael Paskevicius (Learning Technologist)
• Interested in social media and open education
• Previously MIO at Polytechnic of Namibia
– Andrew Deacon (Learning Designer)
• Experienced learning designer
• Significant experience analysing assessment
Agenda
• Definition of educational analytics
• Explore the data landscape of institutional learning environments, personal learning environments and social media
• Learning analytics – approaches & challenges at the University of Cape Town (Michael)
• Visualizing complex data – beyond univariant dashboards (Andrew)
• Available toolsets and concluding thoughts
An age of data
• Massive increase in data storage capability
• What about data collected within learning environments?
Source: Deloitte Consulting Source: Telegraph
Source: The Economist
Educational analytics
• 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: https://tekri.athabascau.ca/analytics)
• Exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings which they learn in. (Baker & Yacef, 2009)
• Academic analytics can be used to profile and even predict students who may be at risk, by analysing demographic and performance data of former students. (Fritz, 2011)
Educational analytics data landscape
Social media
Personal learning environments (PLE)
Institutional learning environments
• ERP Systems • Historical performance data • Learning management system data • Libraries • School application data • Turnitin Reports • Demographics
Attributes • Owned data • Accessible • Found in various databases
Attributes • External data • Mostly difficult to obtain if at all • Difficult to connect to
institutional data
Attributes • External data • Mostly difficult to obtain if at all • Difficult to connect to
institutional data • Perhaps not academic at all
The social web
If our aim is to understand people’s behaviour rather than simply to record it, we want to know about primary groups, neighbourhoods, organizations, social circles, and communities; about interaction, communication, role expectations, and social control. Allen Barton, 1968 cited in Freeman, C. (2004)
Tool name Example
Twitteralytics
Tools used
Data sources
Source: CC BY-SA 3.0
Web and activity log scraping • How do people connect with each other in collaborative
academic environments? • What types of interaction occur in a forum or chat room
discussion?
Social network analysis • What are people saying about our university in social
networks? • How are students related within social networks?
Extract method:
• Query select data via API or script (Python, PHP, screen-scraping programs)
• Group by hashtags, groups, users, topics, keywords • Often requires addition of semantic understanding (and
associated documentation)
Institutional Learning Environments
Starting point: UCT Learning Management System
How and when do students use the learning management system?
Site visits
Chat room activity
Sectioning of students
Polling of students
Content accessed
Submission of assignments
Submission of assignments
Does student LMS activity correlate to course grade?
How do students and academics engage in a course chat room? Academics
and support staff
Days in which chat occurred
Students
Chat messages linked to day of occurrence
What do students who drop the course chat mostly about?
How do students engage with academics in a chat room?
Said more by students
Said more by educators
PLEs / Social Media
Exploratory data analysis
• Getting actual social media data (vs surveys / aggregated data)
• Usage and trends Confirm what happened
• Relationships Explain how things are connected
• Comparisons Serendipity as new questions arise
UCT and social media
• Prominent links to:
– Flickr
– YouTube
Twitter: student survey
Would use on my cell phone Yes
SMS 99%
Webmail 94%
Facebook 92%
Wikipedia 90%
Library journals 85%
Flickr, YouTube 74%
Google Docs 63%
Skype 61%
Twitter 26%
Vula student survey, 2010 data set
Twitter: UCT chatter
• Six months of data (April – Sept 2011)
• Tweets including a UCT hashtag #UCT, #Ikeys, …
• Attributes; how tweets are amplified
• Just over 5,000 tweets
• Cannot capture everything referring to something
• Clean dataset to exclude other uses of hashtags
Twitter: apps & locations
27%
36%
20%
17%
Blackberry Twitter Ubersocial Others
Smartphone geo-location
Cell phones
Cell phones: Blackberry
Twitter: viral #UCT
Varsity Cup final
Helicopter crash
6 months of tweets
Twitter: tweeter relationships
Small number of frequent tweeters
1. Drama student (162)
2. UCT Radio (132)
3. Science student (84)
Flickr: helicopter crash at UCT
Ian Barbour - http://www.flickr.com/people/barbourians/
Twitter: helicopter crash at UCT
2 hours after the
event
• Crash or hard-landing?
• Media outlets getting re-tweeted
• Peak: 140 in 5 min
Facebook: all friend relationships
Paul Butler http://www.facebook.com/notes/facebook-engineering/visualizing-friendships/469716398919
UCT: first-year courses
Psychology and Economics courses have students registered for the largest number of other course (node size is the number of edges)
Data acquisition & preparation
• Social media data challenges
– Tools and data APIs changing
– Being commercialised (and throttled)
– Data cleaning required
Correlation and causation
• Correlation does not imply causation
– Covariation is a necessary but not sufficient condition for causality
– Correlation is not causation (could be a hint)
Conclusions
• Exploring emerging data sources – Combined institutional data sets
– Acknowledge Personal Learning Environments
– Highly fragmented social media data
– Collectively enrich existing information
• Visualisations and multivariant analysis – New exploratory tools
– Making information more accessible
Literature references
• Baker, S.J.D., Yacef, K. (2009) The State of Educational Data Mining in 2009: A Review and Future Visions: http://www.educationaldatamining.org/JEDM/images/articles/vol1/issue1/JEDMVol1Issue1_BakerYacef.pdf
• Freeman, C. (2004) The Development of Social Network Analysis: A Study in the Sociology of Science. Empirical Press: Vancouver, BC Canada.
• Fritz, J. (2011) Learning Analytics. Presentation prepared for Learning and Knowledge Analytics course 2011 (LAK11). http://www.slideshare.net/BCcampus/learning-analytics-fritz
• Kirschner, P.A., Karpinski, A.C. (2010) Facebook and academic performance. Computers in Human Behavior, 26: 1237-1245.
Software references
• Gephi – network analysis, data collection
• NodeXL – network analysis, data collection
• Twitteralytics – data collection (Google Doc)
• Word cloud – R package (wordcloud)
• Geo-location map – R package (RgoogleMaps)
• Excel – spreadsheet, charts
• SPSS – statistical analysis, graphs