LEARNING ANALYTICS IN HIGHER EDUCATION
PROMISING PRACTICES AND LESSONS LEARNED
Bodong Chen,
University of Minnesota
October 27, 2016, Manila, Philippines
@bod0ng
BODONG CHEN
Assistant Professor in Learning Technologies
University of Minnesota-Twin Cities
Research interests: online learning, learning analytics, CSCL,
knowledge building
Credit: Dreamtime.com
... my main concern is the well being of the
plant materials ... And because of the diversity
of plants that we grow, we have to have a
wide range of niches to put those plants into.
Some need it to be a little cooler. Some want it
a little warmer. Some want to be drier. Some
want to be wetter. Our job here is to work with
Mother Nature and to try to provide the
conditions optimal for growth.
Source
PRECISION AGRICULTURE
Credit: Airborne
AMAZON RECOMMENDATIONS
, U.S. Department of Homeland SecurityVisual Analytics Law Enforcement Toolkit (VALET)
Source
LEARNING ANALYTICS IS
“The measurement, collection, analysis, and
reporting of data about learners and their
contexts”
WHAT
Long, P., & Siemens, G. (2011). Penetrating the Fog: Analytics in Learning and Education. Educause
Review, 46(5), 30–32.
LEARNING ANALYTICS IS
“The measurement, collection, analysis, and
reporting of data about learners and their
contexts
for understanding and optimising learning
and the environments in which learning
occurs”
WHY
(Long & Siemens, 2011)
CAN ANY OF THESE PLAYERS AFFORD
NOT USING DATA?
WHAT I'M SEEING AS A PROFESSOR?
Buckingham Shum, S. (2012). . UNESCO Institute for
Information Technologies in Education.
UNESCO Policy Brief: Learning Analytics
AGENDA
A study of Australian universities
University of Minnesota
My Classrooms
Cross-cutting factors
PART 1: A SNAPSHOT OF AUSSIE UNIVERSITIES
Colvin, C., Rogers, T., Wade, A., Dawson, S., Gasevic, D., Buckingham Shum, S., … Fisher, J. (2015).
. Australian Department of Education.
Student retention and learning analytics: A snapshot of Australian practices and a framework for
advancement
AN INTERVIEW STUDY
RESEARCH QUESTION
How senior institutional leaders perceived learning analytics
including the drivers, affordances and constraints?
PARTICIPANTS
Senior institutional leaders
(Deputy Vice Chancellors)
ANALYSES
Qualitative Coding + Cluster Analysis
OVERALL POSITIVE
CLUSTERS NOT DEFINED BY 'YEARS' ...
Cluster 1 (7) Cluster 2 (26)
Purpose Measure Understand
Driver type Ef ciency Learning and
student success
Retention Independent Inter-dependent
Learning
dimensionality
Unidimensional Multidimensional
Analytics Predictive Learning itself
... ... ...
(Colvin et al., 2015)
PART 2: INITAITIVES AT MY UNIVERSITY
University-owned and directed consortium
GETTING PEOPLE INVOLVED!
Instructors
Students
Advisors
Administrators
Research Faculty
Credit: UMN LA Team
UMN LEARNING ANALYTICS
DATA
Student Information System
Learning Management Systems
Student Advising Systems
A COMMON DATA LAYER
ANALYTICS
Dashboards
Predictive engines
ONGOING UNIZIN PILOTS
Canvas LMS
Engage
Snapshot
...
BROADER DISCUSSIONS
Ethics: ethical use of data
Students: interacting with students
Quality: data quality
Leadership: the U's leadership structure
Research: esp. related to Unizin's deidenti ed data
Credit: UMN LA Team
PART 3: AN EXPERIMENTATION IN MY CLASS
MY PEDAGOGICAL GOALS
Promote forum participation from students?
Help students become more aware and re ective
of their participation
SOCIOGRAM
WORDCLOUD
CROSS-CUTTING FACTORS
TO CONSIDER
1. LEARNING ANALYTICS NOT NEUTRAL
Data are not neutral
Our analytics are our pedagogy
(Knight et al., 2014)
Interventionist by nature
educational visions and values
Replicate - Amplify - Transform
(Hughes, Thomas, & Scharber, 2006)
2. CONVERSATIONS
Among datasets
Among people
Between data and people
Across levels
Credits: , ,1 2 3
3. CULTURAL SHIFT AND CAPACITY BUILDING
Data practices
Educator data literacy
Leadership structure
...
OPPORTUNITIES FOR OPEN UNIVERSITIES
Openness
Comprehensiveness of data
Unique local contexts
Cross-institution collaboration
. . .
THANK YOU!
chenbd@umn.edu
bodong.ch
@bod0ng
ACKNOWLEDGEMENT

Learning analytics in higher education: Promising practices and lessons learned

  • 1.
    LEARNING ANALYTICS INHIGHER EDUCATION PROMISING PRACTICES AND LESSONS LEARNED Bodong Chen, University of Minnesota October 27, 2016, Manila, Philippines @bod0ng
  • 2.
    BODONG CHEN Assistant Professorin Learning Technologies University of Minnesota-Twin Cities Research interests: online learning, learning analytics, CSCL, knowledge building
  • 3.
  • 4.
    ... my mainconcern is the well being of the plant materials ... And because of the diversity of plants that we grow, we have to have a wide range of niches to put those plants into. Some need it to be a little cooler. Some want it a little warmer. Some want to be drier. Some want to be wetter. Our job here is to work with Mother Nature and to try to provide the conditions optimal for growth. Source
  • 5.
  • 6.
  • 7.
    , U.S. Departmentof Homeland SecurityVisual Analytics Law Enforcement Toolkit (VALET)
  • 8.
  • 9.
    LEARNING ANALYTICS IS “Themeasurement, collection, analysis, and reporting of data about learners and their contexts” WHAT Long, P., & Siemens, G. (2011). Penetrating the Fog: Analytics in Learning and Education. Educause Review, 46(5), 30–32.
  • 10.
    LEARNING ANALYTICS IS “Themeasurement, collection, analysis, and reporting of data about learners and their contexts for understanding and optimising learning and the environments in which learning occurs” WHY (Long & Siemens, 2011)
  • 12.
    CAN ANY OFTHESE PLAYERS AFFORD NOT USING DATA?
  • 13.
    WHAT I'M SEEINGAS A PROFESSOR?
  • 14.
    Buckingham Shum, S.(2012). . UNESCO Institute for Information Technologies in Education. UNESCO Policy Brief: Learning Analytics
  • 15.
    AGENDA A study ofAustralian universities University of Minnesota My Classrooms Cross-cutting factors
  • 16.
    PART 1: ASNAPSHOT OF AUSSIE UNIVERSITIES Colvin, C., Rogers, T., Wade, A., Dawson, S., Gasevic, D., Buckingham Shum, S., … Fisher, J. (2015). . Australian Department of Education. Student retention and learning analytics: A snapshot of Australian practices and a framework for advancement
  • 17.
    AN INTERVIEW STUDY RESEARCHQUESTION How senior institutional leaders perceived learning analytics including the drivers, affordances and constraints? PARTICIPANTS Senior institutional leaders (Deputy Vice Chancellors) ANALYSES Qualitative Coding + Cluster Analysis
  • 18.
  • 19.
    CLUSTERS NOT DEFINEDBY 'YEARS' ... Cluster 1 (7) Cluster 2 (26) Purpose Measure Understand Driver type Ef ciency Learning and student success Retention Independent Inter-dependent Learning dimensionality Unidimensional Multidimensional Analytics Predictive Learning itself ... ... ... (Colvin et al., 2015)
  • 20.
    PART 2: INITAITIVESAT MY UNIVERSITY
  • 21.
  • 22.
  • 23.
    UMN LEARNING ANALYTICS DATA StudentInformation System Learning Management Systems Student Advising Systems A COMMON DATA LAYER ANALYTICS Dashboards Predictive engines
  • 24.
    ONGOING UNIZIN PILOTS CanvasLMS Engage Snapshot ...
  • 25.
    BROADER DISCUSSIONS Ethics: ethicaluse of data Students: interacting with students Quality: data quality Leadership: the U's leadership structure Research: esp. related to Unizin's deidenti ed data Credit: UMN LA Team
  • 26.
    PART 3: ANEXPERIMENTATION IN MY CLASS
  • 28.
    MY PEDAGOGICAL GOALS Promoteforum participation from students? Help students become more aware and re ective of their participation
  • 29.
  • 30.
  • 34.
  • 35.
    1. LEARNING ANALYTICSNOT NEUTRAL Data are not neutral Our analytics are our pedagogy (Knight et al., 2014) Interventionist by nature educational visions and values Replicate - Amplify - Transform (Hughes, Thomas, & Scharber, 2006)
  • 36.
    2. CONVERSATIONS Among datasets Amongpeople Between data and people Across levels Credits: , ,1 2 3
  • 37.
    3. CULTURAL SHIFTAND CAPACITY BUILDING Data practices Educator data literacy Leadership structure ...
  • 38.
    OPPORTUNITIES FOR OPENUNIVERSITIES Openness Comprehensiveness of data Unique local contexts Cross-institution collaboration . . .
  • 39.