SlideShare une entreprise Scribd logo
1  sur  39
Télécharger pour lire hors ligne
Lightning	
  
Presenta-ons!	
  
Simon	
  Buckingham-­‐Shum	
  
Visualizing	
  and	
  filtering	
  social	
  8es	
  in	
  
             SocialLearn	
  by	
  topic	
  and	
  type	
  




Visualising	
  Social	
  Learning	
  in	
  the	
  SocialLearn	
  Environment.	
  	
  
Bieke	
  Schreurs	
  and	
  Maarten	
  de	
  Laat	
  (Open	
  University,	
  The	
  Netherlands),	
  
Chris	
  Teplovs	
  (ProblemshiB	
  Inc.	
  and	
  University	
  of	
  Windsor),	
  Rebecca	
  
Ferguson	
  and	
  Simon	
  Buckingham	
  Shum	
  (Open	
  University	
  UK),	
  SoLAR	
  
Storm	
  webinar,	
  Open	
  University	
  UK.	
  hGp://bit.ly/LearningAnaly8csOU	
  
Disposi8onal	
  Learning	
  Analy8cs	
  
          for	
  C21/LLL	
  


       Ques8oning	
  and	
                                                                          Different	
  social	
  
         challenging	
                                                                            network	
  paGerns	
  as	
  
        behaviours	
  as	
                                                                        proxies	
  for	
  Learning	
  
      proxies	
  for	
  CriKcal	
                                                                    RelaKonships	
  
          Curiosity	
  




      Cross-­‐contextual	
  
                                                                                                     Persevering	
  
    behaviours	
  as	
  proxies	
  
                                                                                                 behaviours	
  as	
  proxies	
  
    for	
  Meaning	
  Making	
  
                                                                                                    for	
  Resilience	
  

Shaofu Huang: Prototyping Learning Power Modelling in SocialLearn
http://www.open.ac.uk/blogs/SocialLearnResearch/2012/06/20/social-learning-analytics-symposium
Nicola	
  Avery	
  
Medicines	
  &	
  Healthcare	
  Products	
  Regulatory	
  Agency	
  

regulate :




applications :
                                                                                                                                      Life	
  cycle	
  	
  
          Pre-­‐clinical	
            	
  Phase	
  1	
     	
  Phase	
  2	
     	
  Phase	
  3	
         	
  	
  MA	
  Approval	
  
                                                                                                                                      management	
  

                               Clinical	
  Trials	
                                          Licence	
  &	
  Varia-ons	
                                 ▼

900+ staff, agency internal systems, laptops/tablets, workload: 10-300 submissions
Learning & performance - procedures, assessment, consultation, committees,
                          timescales, data & document management / literacy
Learning analytics focus group
                                                      projects

Performance Support                  Data Assurance & Transparency                           Agency BI strategy


currently looking at feedback

      -  text analysis of existing feedback from training, develop examples
      -  ratings & recommendations for procedures – useful, accurate, up-to-date

evaluation report January 2013


“Well	
  done	
  you've	
  used	
  really	
  nice	
  language	
  in	
  that	
  email”	
  

                        “you	
  seem	
  to	
  have	
  been	
  working	
  on	
  this	
  report	
  for	
  7	
  years”	
  

                                              “8	
  out	
  of	
  10	
  assessors	
  said	
  they	
  prefer…”	
  
Doug	
  Clow	
  
 
                                                   	
  

•  Data	
  Wrangling	
  
   – Demographics,	
  	
  
     VLE	
  usage,	
  	
  
     course	
  characteris8cs,	
  	
  
     student	
  feedback	
  
   – Human	
  sense-­‐making	
  


                                Doug	
  Clow	
  
Joseph	
  Corneli	
  
Adam	
  Cooper	
  
Exponen8al	
  Random	
  Graph	
  Models	
  
                                                              A
                                                               d
First	
  Experiments	
  with	
  



                                            Mutuality	
  
                                            	
                 a
                                            	
  
                                            	
  
                                                              m	
  
                                            	
  
                                            Transi8vity	
  
                                                               C
                                            	
                 o
                                            	
  
                                            	
                 o
                                            	
  
                                            	
                 p
                                            Homophily	
  
                                                              er	
  
                                                              (JI
                                                               S
                                                               C	
  
e.g.	
  JISC	
  and	
  CETIS	
  Teams	
  

                                                            •  Showing	
  our	
  colours?	
  
                                                            ●  Main	
  effect	
  


                                                            ●  Homophily	
  


                                                            ●  Mixing	
  




edges	
  +	
  
sender(base=c(-­‐4,-­‐21,-­‐29,-­‐31))	
  +	
  
receiver(base=c(-­‐14,-­‐19,-­‐23,-­‐28))	
  +	
  
nodematch("team",	
  diff=TRUE,	
  keep=c(1,3,4))	
  +	
  
mutual	
  
                                                                 All	
  images	
  and	
  text	
  CC-­‐By:	
  Adam	
  Cooper,	
  2012	
  
Martyn	
  Cooper	
  
John	
  Doove	
  
Exploring	
  Learning	
  AMore	
  paossibili8es	
  of	
  
                                              naly8cs	
  
                                               the	
  
                                                        wareness	
  


                                          Enthusiasm!	
                                   Lessons	
  Learned	
  

Vak	
  voor	
  
  Vak	
         User	
  
                 Needs	
  

    UvAnaly-­‐
      8cs	
         PinPoint	
  

         MAIS	
  


  ProF	
     Curri	
  	
  
Analy8cs	
   M	
  
                                                     hGp://youtu.be/Xs3MsGPVivg	
  
                                        Seven	
  tangible	
  examples	
  to	
  
                                                    refer	
  to	
  
                                     Community	
  of	
  various	
                 Areas	
  of	
  work	
  to	
  be	
  
                                          experts	
                                        done…	
  
Cath	
  Ellis	
  
Unlikely	
   Very	
  unlikely	
                                          Neither	
  Likely	
  or	
                  Unlikely	
       Very	
  unlikely	
  
                                   7%	
              2%	
                                                     Unlikely	
                               0%	
                  2%	
  
   Neither	
  Likely	
  or	
                                                                                    5%	
  
       Unlikely	
  
        11%	
  


Before	
                                                             Very	
  Likely	
     How	
  likely	
                                                                                    AEer	
  
                                                                        32%	
  
                                                                                          are	
  you	
  to	
                            Likely	
  
                                                                                                                                         29%	
  
                                                                                           use	
  this	
                                                            Very	
  Likely	
  
                                                                                          feedback?	
                                                                  64%	
  


                                           Likely	
  
                                            48%	
  




             Clearer	
  sense	
  of	
  where	
  they	
  sit	
  in	
  comparison	
  to	
  their	
  cohort	
  which	
  mo8vates	
  them	
  to	
  want	
  to	
  do	
  more	
  to	
  improve	
  



                       Shining	
  aGen8on	
  to	
  important	
  areas	
  that	
  they	
  tend	
  to	
  neglect	
  



                          Mo8va8ng	
  high	
  achieving	
  students	
  



                       Seeing	
  a	
  bigger	
  picture	
  



             For	
  some	
  this	
  is	
  emo8onally	
  challenging	
  and	
  sensi8ve	
  but	
  for	
  others	
  it’s	
  not	
  
Rebecca	
  Ferguson	
  
Social	
  learning	
  analy-cs:	
  discourse	
  
Challenge: Locate the exploratory dialogue




                                                                                Manual analysis
                                                                              identifies indicators

Category	
                                          Indicator	
  
Challenge	
                                         But	
  if,	
  have	
  to	
  respond,	
  my	
  view	
  
Cri8que	
                                           However,	
  I’m	
  not	
  sure,	
  maybe	
  
Discussion	
  of	
  resources	
                     Have	
  you	
  read,	
  more	
  links	
  
Evalua8on	
                                         Good	
  example,	
  good	
  point	
  
Explana8on	
                                        Means	
  that,	
  our	
  goals	
  
Explicit	
  reasoning	
                             Next	
  step,	
  relates	
  to,	
  that’s	
  why	
  
Jus8fica8on	
                                        I	
  mean,	
  we	
  learned,	
  we	
  observed	
  
Reflec8on	
  of	
  perspec8ves	
  of	
  others	
     Agree,	
  here	
  is	
  another,	
  take	
  your	
  point	
  
                                                                                                                    23	
  
Self-­‐training	
  framework	
  for	
  automa-c	
  
     exploratory	
  discourse	
  detec-on	
  
•  Framework	
  uses	
  cue	
  phrases	
  to	
  make	
  
   use	
  of	
  discourse	
  features	
  for	
  
   classifica8on	
  

•  Uses	
  a	
  k-­‐nearest	
  neighbours	
  instance	
  
   selec8on	
  approach	
  to	
  draw	
  on	
  
   topical	
  features	
  	
  
Dai	
  Griffiths	
  
Mar8n	
  Hawksey	
  
c   MOOC Architecture	
  

        Blogs                               Daily Alert
                                              (email/RSS)

        LMS     “
                                               Central
                                                store




                                   filter
                    Black box
       Social   “   (aggregator)
    Bookmarking

      Twitter &                             Comments
     Social media

                                            Adapted from Siemens, 2012
c   MOOC Analytics	
  

Opportunity
•  Open (ish) data

Issues
•  Time limited
•  "analytically cloaked"
•  Darksocial
•  Infrastructure/messy data
Jean	
  MuGon	
  
 
        Engagement	
  	
  AnalyKcs	
  
                	
  
Jean	
  MuGon,	
  Project	
  Manager	
  	
  
                    	
  
        TwiGer	
  @myderbi	
  
                     	
  

                   	
  	
  
     www.derby.ac.uk/ssis/JISC-­‐projects	
  
                    	
  
                        	
  
                          	
  
                          	
  

                        	
  
Jonathan	
  San	
  Diego	
  
•  hGp://infiniterooms.co.uk/poster/	
  
Mark	
  Stubbs	
  
1.    Uniview	
  -­‐	
  Oracle-­‐based	
  data	
  warehouse	
  /	
  BI	
  repor8ng	
  since	
  2009	
  
2.    Used	
  R	
  randomForest	
  for	
  learning	
  tech	
  review	
  &	
  NSS	
  analysis	
  since	
  2010	
  
3.    Consistent	
  student	
  sa8sfac8on	
  data	
  collec8on,	
  10,770	
  respondents	
  2011	
  
4.    Star8ng	
  major	
  Analy8cs	
  project	
  (SQL	
  Server,	
  SSAS,	
  SSRS,	
  SP2010)	
  



                 A
                                                                                                                                      League	
  table	
  rankings	
  
                     Marke)ng	
  &	
  
                     Recruitment	
                                            Reputa)on	
  
                      Processes	
  
                                                     C	
  
                                                                                                       B

                                                                 Learning,	
  Teaching,	
  Assessment	
  	
  
                 Student	
  Intake	
                                                                              Student	
  Reten)on	
  
                                                                    &	
  Personal	
  Development	
  
              (Aspira)ons,	
  A8tude	
                                                                                Success	
  &	
  	
  
                                                                         Processes,	
  Facili)es	
  
                   &	
  Abili)es)	
                                                                                  Sa)sfac)on	
  
                                                                              &	
  Resources	
  


                                                                         Resource	
  alloca)on	
  


                                                                          All	
  Year	
  Numbers	
  

                A      Recruit	
  to	
  target	
             B     Improve	
  sa8sfac8on,	
  reten8on	
  &	
  success	
       C	
      Inform	
  decision-­‐makers	
  



Prof	
  Mark	
  Stubbs	
  |	
  Head	
  of	
  Learning	
  &	
  Research	
  Tech	
  |	
  m.stubbs@mmu.ac.uk	
  |	
  twiGer.com/thestubbs	
  
Annika	
  Wolff	
  
students	
  



     Data	
  sources	
  
      VLE	
         TMA	
      Demographic	
        Other..	
  
                                                                  Who	
  is	
  
                                                                  struggling?	
  
                      RETAIN	
  predic8ve	
  models	
  

                                                                        Why	
  are	
  they	
  
Dashboard	
  visualisa8ons	
                                            struggling?	
  
BUILDING	
  THE	
  PREDICTIVE	
  MODELS	
  
	
  
Developed	
  and	
  tested	
  on	
  3	
  historic	
  data	
  sets	
  
Compared:	
  decision	
  trees	
  and	
  SVM’s.	
  
Compared:	
  VLE	
  only,	
  TMA	
  and	
  combined	
  
	
  
MAIN	
  FINDINGS	
  
	
  
•  No	
  overall	
  clicking	
  measure	
  correlated	
  with	
  pass/fail:	
  focus	
  on	
  change	
  in	
  student	
  
   behaviour	
  instead	
  

•  High	
  precision	
  can	
  be	
  achieved	
  in	
  predic8ng	
  both	
  performance	
  drop	
  and	
  final	
  
   outcome	
  (pass/fail)	
  for	
  all	
  3	
  modules,	
  using	
  combined	
  VLE	
  and	
  TMA	
  data	
  

•  Demographic	
  data	
  can	
  improve	
  performance,	
  but	
  in	
  early	
  stages	
  the	
  VLE	
  ac8vity	
  is	
  
   the	
  most	
  informa8ve	
  data	
  source.	
  

•  Successfully	
  applied	
  2010	
  model	
  to	
  2011	
  data.	
  Even	
  some	
  success	
  across	
  modules.	
  
Labs	
                                                          www.triballabs.net	
  




         Learning	
  Analy8cs	
  R&D	
  Project	
  
•  Partnership	
  with	
  a	
  university	
  to	
  develop	
  a	
  Learning	
  
   Analy8cs	
  PoC:	
  
    –  Predic8ve	
  model	
  which	
  can	
  predict	
  student	
  success	
  
    –  Combine	
  data	
  from	
  mul8ple	
  administra8ve	
  and	
  ac8vity	
  
       sources	
  
    –  Test	
  how	
  support	
  staff	
  can	
  interact	
  with	
  the	
  model	
  and	
  
       correctly	
  interpret	
  predic8ons	
  
    –  Bring	
  together	
  visualisa8on	
  and	
  ac8on	
  –	
  onen	
  a	
  missing	
  
       element	
  
                                                                           @chrisaballard	
  
Labs	
                                                                       www.triballabs.net	
  
                          Mapping	
  Success	
  Factors	
  


     Academic	
  Integra-on	
                Engagement	
                      Circumstances	
  
Grades	
                          VLE	
  Ac8vity	
                     Social	
  Background	
  
                                  Library	
  Ac8vity	
                 Proximity	
  
                                                                       Finance	
  




       Social	
  Integra-on	
            Prepara-on	
  for	
  HE	
  

Forum	
  interac8on	
             Demographics	
  
                                  Qualifica8ons	
  



                                                                                                   @chrisaballard	
  

Contenu connexe

Similaire à SoLAR-FlareUK-2012.11.19-lightningtalks

Adapting Rankers Online, Maarten de Rijke
Adapting Rankers Online, Maarten de RijkeAdapting Rankers Online, Maarten de Rijke
Adapting Rankers Online, Maarten de Rijke
yaevents
 
Adapto\ing Rankers Online, Maarten de Rijke
Adapto\ing Rankers Online, Maarten de RijkeAdapto\ing Rankers Online, Maarten de Rijke
Adapto\ing Rankers Online, Maarten de Rijke
yaevents
 
Creative Advance Industry Best Practice workshop - Dr Kion Ahadi
Creative Advance Industry Best Practice workshop - Dr Kion AhadiCreative Advance Industry Best Practice workshop - Dr Kion Ahadi
Creative Advance Industry Best Practice workshop - Dr Kion Ahadi
Creative Skillset
 
Project planning forms_final
Project planning forms_finalProject planning forms_final
Project planning forms_final
pcaryee
 
Project planning forms_final
Project planning forms_finalProject planning forms_final
Project planning forms_final
liljann
 
Final product project planning forms
Final product project planning formsFinal product project planning forms
Final product project planning forms
jcl1566
 
Project Planner (MT)
Project Planner (MT)Project Planner (MT)
Project Planner (MT)
dhyl
 
OAE User Needs Process
OAE User Needs ProcessOAE User Needs Process
OAE User Needs Process
rachelache
 

Similaire à SoLAR-FlareUK-2012.11.19-lightningtalks (20)

Adapting Rankers Online, Maarten de Rijke
Adapting Rankers Online, Maarten de RijkeAdapting Rankers Online, Maarten de Rijke
Adapting Rankers Online, Maarten de Rijke
 
Adapto\ing Rankers Online, Maarten de Rijke
Adapto\ing Rankers Online, Maarten de RijkeAdapto\ing Rankers Online, Maarten de Rijke
Adapto\ing Rankers Online, Maarten de Rijke
 
CBL - Creating an iOS App in the Classroom
CBL - Creating an iOS App in the ClassroomCBL - Creating an iOS App in the Classroom
CBL - Creating an iOS App in the Classroom
 
Creative Advance Industry Best Practice workshop - Dr Kion Ahadi
Creative Advance Industry Best Practice workshop - Dr Kion AhadiCreative Advance Industry Best Practice workshop - Dr Kion Ahadi
Creative Advance Industry Best Practice workshop - Dr Kion Ahadi
 
Project planning forms_final
Project planning forms_finalProject planning forms_final
Project planning forms_final
 
Project planning forms_final
Project planning forms_finalProject planning forms_final
Project planning forms_final
 
Final product project planning forms
Final product project planning formsFinal product project planning forms
Final product project planning forms
 
Project Planner (MT)
Project Planner (MT)Project Planner (MT)
Project Planner (MT)
 
Cloud Learning: Learning Environments in the Cloud Era
Cloud Learning: Learning Environments in the Cloud EraCloud Learning: Learning Environments in the Cloud Era
Cloud Learning: Learning Environments in the Cloud Era
 
Rockets Rock!!!
Rockets Rock!!!Rockets Rock!!!
Rockets Rock!!!
 
Building Analytics Capability @open.edu
Building Analytics Capability @open.eduBuilding Analytics Capability @open.edu
Building Analytics Capability @open.edu
 
OAE User Needs Process
OAE User Needs ProcessOAE User Needs Process
OAE User Needs Process
 
OAE User Needs Process
OAE User Needs ProcessOAE User Needs Process
OAE User Needs Process
 
Ulearn08: AFL & ePortfolios
Ulearn08: AFL & ePortfoliosUlearn08: AFL & ePortfolios
Ulearn08: AFL & ePortfolios
 
Applying Learner Centered Methodology - Case Studies
Applying Learner Centered Methodology - Case StudiesApplying Learner Centered Methodology - Case Studies
Applying Learner Centered Methodology - Case Studies
 
Paul Henning Krogh A New Dawn For E Collaboration In Science
Paul Henning Krogh   A New Dawn For E Collaboration In SciencePaul Henning Krogh   A New Dawn For E Collaboration In Science
Paul Henning Krogh A New Dawn For E Collaboration In Science
 
Integrated Learning
Integrated LearningIntegrated Learning
Integrated Learning
 
Narrated Storyboard
Narrated StoryboardNarrated Storyboard
Narrated Storyboard
 
Exploitation of results of the Web2LLP project
Exploitation of results of the Web2LLP projectExploitation of results of the Web2LLP project
Exploitation of results of the Web2LLP project
 
Ontology Maturing for Searching, Managing, and Retrieving Resources
Ontology Maturing for Searching, Managing, and Retrieving ResourcesOntology Maturing for Searching, Managing, and Retrieving Resources
Ontology Maturing for Searching, Managing, and Retrieving Resources
 

Plus de Simon Buckingham Shum

Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...
Simon Buckingham Shum
 
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
Simon Buckingham Shum
 
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
Simon Buckingham Shum
 
Learning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • AgencyLearning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • Agency
Simon Buckingham Shum
 
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group DataTowards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Simon Buckingham Shum
 
Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018
Simon Buckingham Shum
 

Plus de Simon Buckingham Shum (20)

The Generative AI System Shock, and some thoughts on Collective Intelligence ...
The Generative AI System Shock, and some thoughts on Collective Intelligence ...The Generative AI System Shock, and some thoughts on Collective Intelligence ...
The Generative AI System Shock, and some thoughts on Collective Intelligence ...
 
Could Generative AI Augment Reflection, Deliberation and Argumentation?
Could Generative AI Augment Reflection, Deliberation and Argumentation?Could Generative AI Augment Reflection, Deliberation and Argumentation?
Could Generative AI Augment Reflection, Deliberation and Argumentation?
 
Conversational, generative AI as a cognitive tool for critical thinking
Conversational, generative AI as a cognitive tool for critical thinkingConversational, generative AI as a cognitive tool for critical thinking
Conversational, generative AI as a cognitive tool for critical thinking
 
On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...
On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...
On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...
 
SBS_ISLS2022.pdf
SBS_ISLS2022.pdfSBS_ISLS2022.pdf
SBS_ISLS2022.pdf
 
Is “The Matter With Things” also what’s the matter with Learning Analytics?
Is “The Matter With Things” also what’s the matter with Learning Analytics?Is “The Matter With Things” also what’s the matter with Learning Analytics?
Is “The Matter With Things” also what’s the matter with Learning Analytics?
 
Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...
 
Knowledge Art or… “Participatory Improvisational DVN”
Knowledge Art or… “Participatory Improvisational DVN”Knowledge Art or… “Participatory Improvisational DVN”
Knowledge Art or… “Participatory Improvisational DVN”
 
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
 
ICQE20: Quantitative Ethnography Visualizations as Tools for Thinking
ICQE20: Quantitative Ethnography Visualizations as Tools for ThinkingICQE20: Quantitative Ethnography Visualizations as Tools for Thinking
ICQE20: Quantitative Ethnography Visualizations as Tools for Thinking
 
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
 
Argumentation 101 for Learning Analytics PhDs!
Argumentation 101 for Learning Analytics PhDs!Argumentation 101 for Learning Analytics PhDs!
Argumentation 101 for Learning Analytics PhDs!
 
Learning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • AgencyLearning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • Agency
 
AI/Data Analytics (AIDA): Key concepts, examples & risks
AI/Data Analytics (AIDA): Key concepts, examples & risksAI/Data Analytics (AIDA): Key concepts, examples & risks
AI/Data Analytics (AIDA): Key concepts, examples & risks
 
Learning Analytics as Educational Knowledge Infrastructure
Learning Analytics as Educational Knowledge InfrastructureLearning Analytics as Educational Knowledge Infrastructure
Learning Analytics as Educational Knowledge Infrastructure
 
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group DataTowards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
 
Knowledge Art - MDSI Guest Lecture - 1st May 2019
Knowledge Art - MDSI Guest Lecture - 1st May 2019Knowledge Art - MDSI Guest Lecture - 1st May 2019
Knowledge Art - MDSI Guest Lecture - 1st May 2019
 
UX/LX for PLSA: Workshop Welcome
UX/LX for PLSA: Workshop WelcomeUX/LX for PLSA: Workshop Welcome
UX/LX for PLSA: Workshop Welcome
 
Educational Data Scientists: A Scarce Breed
Educational Data Scientists: A Scarce BreedEducational Data Scientists: A Scarce Breed
Educational Data Scientists: A Scarce Breed
 
Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018
 

Dernier

Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
Chris Hunter
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
heathfieldcps1
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
SanaAli374401
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch Letter
MateoGardella
 

Dernier (20)

Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
PROCESS RECORDING FORMAT.docx
PROCESS      RECORDING        FORMAT.docxPROCESS      RECORDING        FORMAT.docx
PROCESS RECORDING FORMAT.docx
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
SECOND SEMESTER TOPIC COVERAGE SY 2023-2024 Trends, Networks, and Critical Th...
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch Letter
 

SoLAR-FlareUK-2012.11.19-lightningtalks

  • 3. Visualizing  and  filtering  social  8es  in   SocialLearn  by  topic  and  type   Visualising  Social  Learning  in  the  SocialLearn  Environment.     Bieke  Schreurs  and  Maarten  de  Laat  (Open  University,  The  Netherlands),   Chris  Teplovs  (ProblemshiB  Inc.  and  University  of  Windsor),  Rebecca   Ferguson  and  Simon  Buckingham  Shum  (Open  University  UK),  SoLAR   Storm  webinar,  Open  University  UK.  hGp://bit.ly/LearningAnaly8csOU  
  • 4. Disposi8onal  Learning  Analy8cs   for  C21/LLL   Ques8oning  and   Different  social   challenging   network  paGerns  as   behaviours  as   proxies  for  Learning   proxies  for  CriKcal   RelaKonships   Curiosity   Cross-­‐contextual   Persevering   behaviours  as  proxies   behaviours  as  proxies   for  Meaning  Making   for  Resilience   Shaofu Huang: Prototyping Learning Power Modelling in SocialLearn http://www.open.ac.uk/blogs/SocialLearnResearch/2012/06/20/social-learning-analytics-symposium
  • 6. Medicines  &  Healthcare  Products  Regulatory  Agency   regulate : applications : Life  cycle     Pre-­‐clinical    Phase  1    Phase  2    Phase  3      MA  Approval   management   Clinical  Trials   Licence  &  Varia-ons   ▼ 900+ staff, agency internal systems, laptops/tablets, workload: 10-300 submissions Learning & performance - procedures, assessment, consultation, committees, timescales, data & document management / literacy
  • 7. Learning analytics focus group projects Performance Support Data Assurance & Transparency Agency BI strategy currently looking at feedback -  text analysis of existing feedback from training, develop examples -  ratings & recommendations for procedures – useful, accurate, up-to-date evaluation report January 2013 “Well  done  you've  used  really  nice  language  in  that  email”   “you  seem  to  have  been  working  on  this  report  for  7  years”   “8  out  of  10  assessors  said  they  prefer…”  
  • 9.     •  Data  Wrangling   – Demographics,     VLE  usage,     course  characteris8cs,     student  feedback   – Human  sense-­‐making   Doug  Clow  
  • 11.
  • 12.
  • 14. Exponen8al  Random  Graph  Models   A d First  Experiments  with   Mutuality     a     m     Transi8vity   C   o     o     p Homophily   er   (JI S C  
  • 15. e.g.  JISC  and  CETIS  Teams   •  Showing  our  colours?   ●  Main  effect   ●  Homophily   ●  Mixing   edges  +   sender(base=c(-­‐4,-­‐21,-­‐29,-­‐31))  +   receiver(base=c(-­‐14,-­‐19,-­‐23,-­‐28))  +   nodematch("team",  diff=TRUE,  keep=c(1,3,4))  +   mutual   All  images  and  text  CC-­‐By:  Adam  Cooper,  2012  
  • 18. Exploring  Learning  AMore  paossibili8es  of   naly8cs   the   wareness   Enthusiasm!   Lessons  Learned   Vak  voor   Vak   User   Needs   UvAnaly-­‐ 8cs   PinPoint   MAIS   ProF   Curri     Analy8cs   M   hGp://youtu.be/Xs3MsGPVivg   Seven  tangible  examples  to   refer  to   Community  of  various   Areas  of  work  to  be   experts   done…  
  • 20.
  • 21. Unlikely   Very  unlikely   Neither  Likely  or   Unlikely   Very  unlikely   7%   2%   Unlikely   0%   2%   Neither  Likely  or   5%   Unlikely   11%   Before   Very  Likely   How  likely   AEer   32%   are  you  to   Likely   29%   use  this   Very  Likely   feedback?   64%   Likely   48%   Clearer  sense  of  where  they  sit  in  comparison  to  their  cohort  which  mo8vates  them  to  want  to  do  more  to  improve   Shining  aGen8on  to  important  areas  that  they  tend  to  neglect   Mo8va8ng  high  achieving  students   Seeing  a  bigger  picture   For  some  this  is  emo8onally  challenging  and  sensi8ve  but  for  others  it’s  not  
  • 23. Social  learning  analy-cs:  discourse   Challenge: Locate the exploratory dialogue Manual analysis identifies indicators Category   Indicator   Challenge   But  if,  have  to  respond,  my  view   Cri8que   However,  I’m  not  sure,  maybe   Discussion  of  resources   Have  you  read,  more  links   Evalua8on   Good  example,  good  point   Explana8on   Means  that,  our  goals   Explicit  reasoning   Next  step,  relates  to,  that’s  why   Jus8fica8on   I  mean,  we  learned,  we  observed   Reflec8on  of  perspec8ves  of  others   Agree,  here  is  another,  take  your  point   23  
  • 24. Self-­‐training  framework  for  automa-c   exploratory  discourse  detec-on   •  Framework  uses  cue  phrases  to  make   use  of  discourse  features  for   classifica8on   •  Uses  a  k-­‐nearest  neighbours  instance   selec8on  approach  to  draw  on   topical  features    
  • 27. c MOOC Architecture   Blogs Daily Alert (email/RSS) LMS “ Central store filter Black box Social “ (aggregator) Bookmarking Twitter & Comments Social media Adapted from Siemens, 2012
  • 28. c MOOC Analytics   Opportunity •  Open (ish) data Issues •  Time limited •  "analytically cloaked" •  Darksocial •  Infrastructure/messy data
  • 30.   Engagement    AnalyKcs     Jean  MuGon,  Project  Manager       TwiGer  @myderbi         www.derby.ac.uk/ssis/JISC-­‐projects            
  • 31.
  • 32. Jonathan  San  Diego   •  hGp://infiniterooms.co.uk/poster/  
  • 34. 1.  Uniview  -­‐  Oracle-­‐based  data  warehouse  /  BI  repor8ng  since  2009   2.  Used  R  randomForest  for  learning  tech  review  &  NSS  analysis  since  2010   3.  Consistent  student  sa8sfac8on  data  collec8on,  10,770  respondents  2011   4.  Star8ng  major  Analy8cs  project  (SQL  Server,  SSAS,  SSRS,  SP2010)   A League  table  rankings   Marke)ng  &   Recruitment   Reputa)on   Processes   C   B Learning,  Teaching,  Assessment     Student  Intake   Student  Reten)on   &  Personal  Development   (Aspira)ons,  A8tude   Success  &     Processes,  Facili)es   &  Abili)es)   Sa)sfac)on   &  Resources   Resource  alloca)on   All  Year  Numbers   A Recruit  to  target   B Improve  sa8sfac8on,  reten8on  &  success   C   Inform  decision-­‐makers   Prof  Mark  Stubbs  |  Head  of  Learning  &  Research  Tech  |  m.stubbs@mmu.ac.uk  |  twiGer.com/thestubbs  
  • 36. students   Data  sources   VLE   TMA   Demographic   Other..   Who  is   struggling?   RETAIN  predic8ve  models   Why  are  they   Dashboard  visualisa8ons   struggling?  
  • 37. BUILDING  THE  PREDICTIVE  MODELS     Developed  and  tested  on  3  historic  data  sets   Compared:  decision  trees  and  SVM’s.   Compared:  VLE  only,  TMA  and  combined     MAIN  FINDINGS     •  No  overall  clicking  measure  correlated  with  pass/fail:  focus  on  change  in  student   behaviour  instead   •  High  precision  can  be  achieved  in  predic8ng  both  performance  drop  and  final   outcome  (pass/fail)  for  all  3  modules,  using  combined  VLE  and  TMA  data   •  Demographic  data  can  improve  performance,  but  in  early  stages  the  VLE  ac8vity  is   the  most  informa8ve  data  source.   •  Successfully  applied  2010  model  to  2011  data.  Even  some  success  across  modules.  
  • 38. Labs   www.triballabs.net   Learning  Analy8cs  R&D  Project   •  Partnership  with  a  university  to  develop  a  Learning   Analy8cs  PoC:   –  Predic8ve  model  which  can  predict  student  success   –  Combine  data  from  mul8ple  administra8ve  and  ac8vity   sources   –  Test  how  support  staff  can  interact  with  the  model  and   correctly  interpret  predic8ons   –  Bring  together  visualisa8on  and  ac8on  –  onen  a  missing   element   @chrisaballard  
  • 39. Labs   www.triballabs.net   Mapping  Success  Factors   Academic  Integra-on   Engagement   Circumstances   Grades   VLE  Ac8vity   Social  Background   Library  Ac8vity   Proximity   Finance   Social  Integra-on   Prepara-on  for  HE   Forum  interac8on   Demographics   Qualifica8ons   @chrisaballard