webscience guest lecture 1-12-2017
TRANSCRIPT
WEB SCIENCE
GUEST LECTURE
Using Web Science for Educational ResearchDr Christian Bokhove
About me
• Dr Christian Bokhove
• Lecturer in Mathematics Education at Southampton
Education School
• Background maths and computer science, teacher
secondary school for years
• Use of ICT to support learning
• Use of technology for analysing learning
• Research methodology.
I especially like to integrate
computer science with
social science methodology.
Aim of this presentation
• Impression of various topics working on
• A. Educational datamining: mining log files, automatic
text book analysis, inspection reports
B. Analysing the edu blogosphere
C. Social network analysis (classrooms, organizations)
D. Gamification. Times Tables Rockstars. Other games.
E. Tools for data analysis
4
Educational Data Mining
• “Educational Data Mining is an emerging discipline,
concerned with developing methods for 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.”
• www.educationaldatamining.org
A. Educational datamining
• Log files, electronic books, student actions
• What can we say about their ‘learning behaviour’? Or
about textbooks?
• Learning Analytics/datamining: using algorithms to
explore this
• But I prefer to look at it somewhat broader
Example 1
• Log files with student
activity (PhD student
Chris Osborne)
• Classification,
predictions (e.g. bored,
on-task, Ryan Baker has
done a lot of work on
this)
• European project where
Learning Analytics
important role in maths
digital textbooks
USING
RAPIDMINER
http://is.gd/quadrilaterals
Example 2
• Online resources or a
textbook (non-edu:
tweets)
• Can we extract its
meaning?
• e.g. Latent semantic
analysis
USING R
https://eprints.soton.ac.uk/393849/1/websci_bokhove_FINAL.pdf
• Web scraper
• Mass download
• Convert from pdf
• Stop-words, stemming
etc
• Sentiment analysis
• Topic modelling with
Latent Dirichlet
Allocation
link
B. Analysing the edu blogosphere
• Sarah Hewitt, PhD student (contents used with
permission)
• Blog at https://sarahhewittsblog.wordpress.com/
• “My corpus is a sample of 9,262 blog posts gathered last
year.”
• “to see what Edu-professionals talk about, and to see if
the topics they discuss change over time.”
Technical side
Education side
Challenging at times
“Teachers and other Edu-professionals, Gods-damn them,
like to be creative and cryptic when it comes to titling their
blogs, and they often draw on metaphors to explain the
points they’re trying to make, all of which expose
algorithms that reduce language to numbers as the
miserable , soulless and devoid-of-any-real-intelligence
things they are. How very dare they.”
Comments
• A lot of digital resources are produced used in
education; they create a lot of data (‘Big Data’)
• What can we learn from their contents and usage?
• Can be applied to multiple disciplines (For me:
education) and types of data.
• Highly interdisciplinary: on one hand need the skills to
extract and analyse, on the other hand you need
domain knowledge to interpret
C. Social Network Analysis
• Started with social sciences (eg friendship networks)
• Then Watts and Strogatz took it into physics
• Now very multidisciplinary
• See Freeman (2004) for the history
• The rest is history
• Dynamic Social Network Analysis: over time, statistical
models, simulations, animations
Freeman, L.C. (2004). The Development of Social Network Analysis: A Study in the Sociology of Science. Vancouver: Empirical Press.
Example
• Using tools
o R
o Gephi
o nodeXL
o UCInet
o Pajek
o ….
McFarland, D.A. (2001). Student Resistance: How the Formal and Informal Organization of Classrooms Facilitate Everyday
Forms of Student Defiance. American Journal of Sociology107(3), 612-78.
Moody, J., McFarland, D.A., & Bender-deMoll, S. (2005). Dynamic Network Visualization: Methods for Meaning with
Longitudinal Network Movies. American Journal of Sociology, 110, 1206-1241.
Snijders, T.A.B. (2001). The Statistical Evaluation of Social Network Dynamics.Sociological Methodology, 31(1).361-395.
SNA for classroom interaction
• Case to use SNA for
classroom interaction
• Making it dynamic
• Classroom interaction
(Moody, McFarland,
& Bender-deMoll, 2005)
• Technological and methodological advances
• Observation apps
• Video recording easier
• Statistical techniques and packages to capture temporal aspects
like Gephi, ERGMs, Rsiena, Statnet, Relevent
This project
• Use dynamic social network analysis to describe classroom interaction
• Data analysis and visualization software• Gephi 0.8.2 beta
• R and Rstudio with the packages statnet (Handcock, Hunter, Butts, Goodreau, & Morris, 2008) and ndtv (Bender-deMoll, 2014)
Observation apps
Comments
• Use existing methodologies from Social Network
Analysis (SNA) and apply them to social sciences (here:
education)
• Use existing metrics from SNA to explore (community)
patterns and new metrics (for me: for educational
effectiveness, for example)
• Project proposal to apply SNA to educational context
• Logical application might be: interactions between
students in online environments, the role of social
media in maintaining professional teacher networks,
Personal Learning Networks (Nic Fair)
D. Gamification
• Trying to use game principles for learning
• Word of warning
• Involved in project online Times Tables practice
• Gamified environment
• Competitive element
• How does this influence times tables skills
• Insight how times tables acquired at scale
AAA games?
E. Tools for data analysis
• There are a lot of data analysis tools out there
• Although I use many, I try to focus on open source tools
• Would also love to build capacity for all these tools we
use
o R
o Rapidminer
o nodeXL, Gephi, UCInet, Pajek
o etc.
Thank you
• Questions?
• Twitter: @cbokhove
• Blog: www.bokhove.net (blog sporadically ;-)