Transcript Document

Knowing you’re there:
analysing technological
engagement to enhance
retention and success
Professor Jo Smedley &
Professor Clive Mulholland
March 2014
© University of South Wales
Abstract
Student engagement is an important indicator of all
types of academic attachment demonstrating active
citizenship with their learning “world” (Barnett and
Coate (2005), Krause and Coates, 2008). Learning
analytics on technological activity data provide early
predictors of change impacting on retention,
achievement and success. From this learner behaviour
“window”, outcomes are informing student-centred
initiatives at various stages of their learner journeys.
© University of South Wales
2
Session Aims
• Using Big Data
• About Analytics
• Case study: Learner Journey Analytics
© University of South Wales
3
Value of Big Data Analytics
Prescriptive analytics
Advanced
analytics
To determine which decision and/or action will produce the most
effective result against a specific set of objectives and constraints
Predictive analytics
Leverage past data to understand why something happened or to predict what will
happen in the future across various scenarios
Business
intelligence
Descriptive analytics
Mine past data to report, visualize and understand what has already
happened – after the fact or in real time
Computational complexity
•
The goal of all organizations with access to large data collections should be to harness
the most relevant data and use it for better decision making
© University of South Wales
Page 4
Case Study:
Learner Journey Analytics
• Belonging and attachment
• Student life cycle
• Learning Analytics
© University of South Wales
5
Learning Analytics
Target
Setting
Activity
Monitoring
Data
Mining
Induction
Learning
Analytics
Traffic
Lights
© University of South Wales
6
Conclusions/Further Work
• Enhanced data transparency
• Wider engagement
• Links to:– Admissions data
– Achievement
– Credit scores
© University of South Wales
7
Questions/Followup
Webpage: http://celt.southwales.ac.uk/does/sa/
Email:
[email protected]
[email protected]
© University of South Wales
8
Module
surveys x n
Big Data
• Internal data
Internal
data
• Activity monitoring
• External data
Student
experience
surveys x n
Managing Information
© University of South Wales
9
NSS
International
Student
barometer
Big Data
External
data
• Internal data
• Activity monitoring
PRES
DLHE
• External data
PTES
HESA
Managing Information
© University of South Wales
10
Return
Blackboard
Interactions
Library
interactions
Big Data
GlamLife
interactions
Number of
missed QMP
Assignments
Student
Representation
Activity
monitoring
• Internal data
• Activity monitoring
• External data
Estates info
Googlemail
Interactions
(entry etc)
Tier 4 sign-ons
Managing Information
Logons from
student area
© University of South Wales
11
Return
Activity Monitoring
• Technological interactions
– BlackBoard, Googlemail, PC login, GlamLife
• Predictive equation
– Bus./Comp./Music Tech/Drama/Graphics/Acc.
• Data visualisation
Managing Information
© University of South Wales
12
2012-2013
Managing Information
© University of South Wales
13
2012-2013
Managing Information
Return
© University of South Wales
14
Return
© University of South Wales
15
Return
Target setting
Status Quo
Scale of improvement
Actual Return Rate 90%+
Target return rate same
Actual Return Rate 83% to 89%
Target return rate 90%
Actual Return Rate 80% to 82%
Target return rate – increase actual return rate by 5%
Actual Return Rate 70% to 79%
Target return rate – increase actual return rate by 10%
Actual Return Rate below 70%
Target return rate – increase actual return rate by 20%
• Comparison of retention targets with actual
performance in 2011/12 and 2012/13, based on agreed
retention target formula
• Generation of new targets for 2013/14
Managing Information
© University of South Wales
16
Return
Managing Information
© University of South Wales
17
Induction
Return
• Activities
– Funded new induction activities to strengthen
student sense of “belonging”
– Goal: improved student achievement, success and
retention
“The students have
• Impact
”Definite bonding
between them.
And faster than in
previous years... “
Geology
“Decrease in
student
withdrawals
attributed to the
induction activity”
Forensic Science
Managing Information
bonded particularly well,
they have been much
more willing to approach
staff and confident in
how they interact with
us” Chemistry
© University of South Wales
18
Student Life Cycle
Student
Success
Moving
Through
Raising
Aspirations
Student
Life Cycle
Better
Preparation
Return
• Are you aware of the main
reasons why students
withdraw from your
programme?
• Are you aware of the steps
they have to take in order
to officially withdraw?
• What advice would you
give to a student
contemplating withdrawal?
First Steps
in H.E.
Reference: http://www.ulster.ac.uk/star/resources/Anagnostopoulou_Parmar.pdf
Managing Information
© University of South Wales
19
Learning Analytics:
Return
Techniques and Methods
•
•
•
•
•
•
•
Statistics: hypothesis testing
Business Intelligence: effective reporting
Web analytics: technological interactions
Artificial intelligence/data mining: data patterns
Operational research: statistical methods
Social Network Analysis: online/offline links
Information visualisation: making sense of data
Ref: Cooper, Adam. A Brief History of Analytics A Briefing Paper. CETIS Analytics Series. JISC CETIS, November 2012
Managing Information
© University of South Wales
20