SlideShare a Scribd company logo
Learning Engineering Initiatives
at Harvard DCE
Jay Luker, Senior Software Engineer Phoebe Miller, Senior Software Engineer
Harvard IT Summit, 2017
What is Learning Engineering?
"Using learning analytics data to help faculty and course designers tailor DCE's
learning environments and improve student outcomes."
— Phoebe & Jay, 2017
"[To achieve] the professional design of learning environments and learning
experiences, [...] the most important step is to find a place on the campus for a
team of individuals who are professionals in the design of learning
environments—learning engineers."
— Herbert A. Simon, The Job of the College President, 1967
Who & What
● DCE's Online Teaching & Learning Development Group
○ 4 Software Engineers*
○ 1 QA Engineer
○ 1 A/V Engineer
○ 1 Benevolent Overlord
● Building Software to benefit students, faculty and producers
● Lecture capture, lecture delivery, Canvas LTI tools, deployment, testing &
monitoring tools
● Java, Python, JavaScript, Ruby, R
● Fully AWS-ified since January 2016
* we're hiring!
Collectable class attendance data
● Online (live) web conference
○ Zoom web conference classes
● Lecture Videos
○ Recorded live lectures with live streaming
○ Republished lectures from past semesters
● Open source video capture and distribution system
● Developed by a robust community, mostly higher-ed institutions
● Viewer Annotation, automatic closed captioning
● v1.0 released August, 2010
● v3.0 to be released this summer!
● Multistream video player designed specifically for lectures
● Supports all major browsers, mobile, live streaming
● Themeable & customizable via plugins
● Extensive user-tracking functionality, i.e., "useraction" events
Paella records useraction events: PLAY, SEEK, HEARTBEAT, etc
Opencast API: IDs user, maintains session, stores in MySQL
Python harvester runs at 2m intervals, adds lecture metadata
SQS used as a buffer queue
Logstash adds geolocation info, parses user-agent data
Elasticsearch: daily rolling indexes; search & aggregation
Apps & APIs, e.g. Kibana dashboards
Useraction Event Pipeline
Example
Useraction
Event
Record
User Activity Dashboard
● Powered by Kibana, an open source
visualization tool for Elasticsearch data
● Time-series graphs of active user sessions
● Filter by:
○ live viewers vs on-demand
○ identified vs anonymous
○ browser/OS, course, geolocation
● Top terms tables for any event field,
geolocation heat map
● Very useful for fixing a few data integrity
issues
Phase One: Proof of Concept
● Attempting to use the data on hand to answer
basic, high-level questions:
○ What is being watched?
○ Who is watching?
○ How is it being watched?
● 3-week "sprint" in late 2016
● Django + Elasticsearch + d3.js + DataTables.js
● Useful!
○ stakeholder feedback
○ refining the questions
○ highlighted gaps and integrity issues with the data
More Data!
● Canvas data from VPAL
○ Office of the Vice Provost for Advances in Learning
○ Research group focused on learning science
○ DCE contributes useraction event data & code
○ VPAL provides access to "data products" generated from Canvas activity data
● Auto-generated lecture transcripts
○ IBM Watson speech-to-text service
● Opencast Social
○ Video annotation text
Data Inventory
● Useraction event data
○ Lecture viewing behavior, timestamps
● Zoom web conferencing data
○ Meetings, Participants, connection data, timestamps
● Banner student information data
○ Course rolls, registration status
● Canvas activity data
○ Discussions, quizzes, time-on-task
● Transcript data
○ Searchable transcript text, auto-transcription confidence scores
● Annotation text
○ Text, timestamps
Phase Two: Answering Questions
● Shifting our development approach
○ from "Hey, look what we can do!"
○ to "What questions do you want us to answer?"
● Switching to R + Shiny
○ Powerful data manipulation
○ Awesome graphs
○ Designed specifically for interactive visualization UIs
○ Allows for more rapid generation of rich graphs and interactive visualizations
○ Smaller, stand-alone apps vs monolithic UI
○ Faster iterations to answer experimental questions
How many students watched the lecture videos
for a course?
How many students watched the lecture or the section videos in a series?
Which students are (and are not)
keeping up with the online lectures?
What parts of the lectures are most watched?
What parts of the lectures are most watched?
What parts of the lectures are most watched?
What topics were discussed by students during a
lecture?
What topics were discussed by students during a
lecture?
Word cloud generated from viewer annotations
during lecture 6 of the course “Organizational
Behavior”
Which students attended a lecture or meeting and were they
there the whole time?
Q: Which students attended a lecture or meeting and were they there the whole
time?
Opencast Lectures
Using the heartbeats
from opencast/paella,
one can see student’s
coverage of one video
Which students attended a lecture or meeting and were they there the whole time?
Zoom Web Conferences
Zoom provides a REST API to
access meetings, reports and
other data.
Participant are identified by
user name and ip address, as
well as connection type, city,
country, duration and other
information
Details of each student’s connection experience can be displayed on one graph
Thanks! Questions?
● These slides: http://bit.ly/2sHcWyo
● Github: https://github.com/harvard-dce
● Opencast: http://www.opencast.org/
● VPAL: https://vpal.harvard.edu/

More Related Content

Similar to Learning Engineering Initiatives at Harvard DCE

A Virtual Infrastructure for Data intensive Analysis (VIDIA)
A Virtual Infrastructure for Data intensive Analysis (VIDIA)A Virtual Infrastructure for Data intensive Analysis (VIDIA)
A Virtual Infrastructure for Data intensive Analysis (VIDIA)
Alexandra M. Pickett
 
Using MS Power BI to create full, interactive reports using Brightspace Data ...
Using MS Power BI to create full, interactive reports using Brightspace Data ...Using MS Power BI to create full, interactive reports using Brightspace Data ...
Using MS Power BI to create full, interactive reports using Brightspace Data ...
D2L Barry
 
Online Onboarding: Increasing the efficiency and effectiveness of library wor...
Online Onboarding: Increasing the efficiency and effectiveness of library wor...Online Onboarding: Increasing the efficiency and effectiveness of library wor...
Online Onboarding: Increasing the efficiency and effectiveness of library wor...
Dr. Monica D.T. Rysavy
 
Are we there yet? Rev up your productivity with project management tools
Are we there yet? Rev up your productivity with project management toolsAre we there yet? Rev up your productivity with project management tools
Are we there yet? Rev up your productivity with project management tools
Margot
 
Are we there yet? Rev up your productivity with project management tools
Are we there yet?  Rev up your productivity with project management toolsAre we there yet?  Rev up your productivity with project management tools
Are we there yet? Rev up your productivity with project management tools
Annis Lee Adams
 
Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...
Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...
Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...
Learnosity
 
Gdsc IIIT Surat Orientation 2022.pdf
Gdsc IIIT Surat Orientation 2022.pdfGdsc IIIT Surat Orientation 2022.pdf
Gdsc IIIT Surat Orientation 2022.pdf
SparshJhariya2
 
Digital Fluencies: Why, What & Where We Are
Digital Fluencies: Why, What & Where We AreDigital Fluencies: Why, What & Where We Are
Digital Fluencies: Why, What & Where We Are
Kimberly Eke
 
User Experience Showcase lightning talks - University of Edinburgh
User Experience Showcase lightning talks - University of EdinburghUser Experience Showcase lightning talks - University of Edinburgh
User Experience Showcase lightning talks - University of Edinburgh
Neil Allison
 
Collaborative learning presentation
Collaborative learning presentationCollaborative learning presentation
Collaborative learning presentation
ShiKia Carter
 
Open edX Conference 2014, McKinsey Academy
Open edX Conference 2014, McKinsey AcademyOpen edX Conference 2014, McKinsey Academy
Open edX Conference 2014, McKinsey Academy
Andy Parsons
 
Shaping the Open Course at Bucks County Community College
Shaping the Open Course at Bucks County Community CollegeShaping the Open Course at Bucks County Community College
Shaping the Open Course at Bucks County Community College
Bill Hemmig
 
Software Professionals (RSEs) at NCSA
Software Professionals (RSEs) at NCSASoftware Professionals (RSEs) at NCSA
Software Professionals (RSEs) at NCSA
Daniel S. Katz
 
Topic Modeling for Learning Analytics Researchers LAK15 Tutorial
Topic Modeling for Learning Analytics Researchers LAK15 TutorialTopic Modeling for Learning Analytics Researchers LAK15 Tutorial
Topic Modeling for Learning Analytics Researchers LAK15 Tutorial
Vitomir Kovanovic
 
Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019
Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019
Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019
Alex Humphreys
 
Proof of Concept for Learning Analytics Interoperability
Proof of Concept for Learning Analytics InteroperabilityProof of Concept for Learning Analytics Interoperability
Proof of Concept for Learning Analytics Interoperability
Open Cyber University of Korea
 
Better Software, Better Practices, Better Research
Better Software, Better Practices, Better ResearchBetter Software, Better Practices, Better Research
Better Software, Better Practices, Better Research
Shoaib Sufi
 
CliveGHughes-casestudy-SpringerNature
CliveGHughes-casestudy-SpringerNatureCliveGHughes-casestudy-SpringerNature
CliveGHughes-casestudy-SpringerNatureClive G Hughes, M.A.
 
Lak2018: Scaling Nationally: Seven Lesson Learned
Lak2018:  Scaling Nationally: Seven Lesson LearnedLak2018:  Scaling Nationally: Seven Lesson Learned
Lak2018: Scaling Nationally: Seven Lesson Learned
mwebbjisc
 
openEQUELLA Q3 2018 Quarterly Briefing
openEQUELLA Q3 2018 Quarterly BriefingopenEQUELLA Q3 2018 Quarterly Briefing
openEQUELLA Q3 2018 Quarterly Briefing
ChrisBeach22
 

Similar to Learning Engineering Initiatives at Harvard DCE (20)

A Virtual Infrastructure for Data intensive Analysis (VIDIA)
A Virtual Infrastructure for Data intensive Analysis (VIDIA)A Virtual Infrastructure for Data intensive Analysis (VIDIA)
A Virtual Infrastructure for Data intensive Analysis (VIDIA)
 
Using MS Power BI to create full, interactive reports using Brightspace Data ...
Using MS Power BI to create full, interactive reports using Brightspace Data ...Using MS Power BI to create full, interactive reports using Brightspace Data ...
Using MS Power BI to create full, interactive reports using Brightspace Data ...
 
Online Onboarding: Increasing the efficiency and effectiveness of library wor...
Online Onboarding: Increasing the efficiency and effectiveness of library wor...Online Onboarding: Increasing the efficiency and effectiveness of library wor...
Online Onboarding: Increasing the efficiency and effectiveness of library wor...
 
Are we there yet? Rev up your productivity with project management tools
Are we there yet? Rev up your productivity with project management toolsAre we there yet? Rev up your productivity with project management tools
Are we there yet? Rev up your productivity with project management tools
 
Are we there yet? Rev up your productivity with project management tools
Are we there yet?  Rev up your productivity with project management toolsAre we there yet?  Rev up your productivity with project management tools
Are we there yet? Rev up your productivity with project management tools
 
Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...
Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...
Educate 2017: Neverending Story: Exploring Learnosity's ongoing product evolu...
 
Gdsc IIIT Surat Orientation 2022.pdf
Gdsc IIIT Surat Orientation 2022.pdfGdsc IIIT Surat Orientation 2022.pdf
Gdsc IIIT Surat Orientation 2022.pdf
 
Digital Fluencies: Why, What & Where We Are
Digital Fluencies: Why, What & Where We AreDigital Fluencies: Why, What & Where We Are
Digital Fluencies: Why, What & Where We Are
 
User Experience Showcase lightning talks - University of Edinburgh
User Experience Showcase lightning talks - University of EdinburghUser Experience Showcase lightning talks - University of Edinburgh
User Experience Showcase lightning talks - University of Edinburgh
 
Collaborative learning presentation
Collaborative learning presentationCollaborative learning presentation
Collaborative learning presentation
 
Open edX Conference 2014, McKinsey Academy
Open edX Conference 2014, McKinsey AcademyOpen edX Conference 2014, McKinsey Academy
Open edX Conference 2014, McKinsey Academy
 
Shaping the Open Course at Bucks County Community College
Shaping the Open Course at Bucks County Community CollegeShaping the Open Course at Bucks County Community College
Shaping the Open Course at Bucks County Community College
 
Software Professionals (RSEs) at NCSA
Software Professionals (RSEs) at NCSASoftware Professionals (RSEs) at NCSA
Software Professionals (RSEs) at NCSA
 
Topic Modeling for Learning Analytics Researchers LAK15 Tutorial
Topic Modeling for Learning Analytics Researchers LAK15 TutorialTopic Modeling for Learning Analytics Researchers LAK15 Tutorial
Topic Modeling for Learning Analytics Researchers LAK15 Tutorial
 
Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019
Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019
Expanding JSTOR's Support for Higher Education in Prison - NCHEP 2019
 
Proof of Concept for Learning Analytics Interoperability
Proof of Concept for Learning Analytics InteroperabilityProof of Concept for Learning Analytics Interoperability
Proof of Concept for Learning Analytics Interoperability
 
Better Software, Better Practices, Better Research
Better Software, Better Practices, Better ResearchBetter Software, Better Practices, Better Research
Better Software, Better Practices, Better Research
 
CliveGHughes-casestudy-SpringerNature
CliveGHughes-casestudy-SpringerNatureCliveGHughes-casestudy-SpringerNature
CliveGHughes-casestudy-SpringerNature
 
Lak2018: Scaling Nationally: Seven Lesson Learned
Lak2018:  Scaling Nationally: Seven Lesson LearnedLak2018:  Scaling Nationally: Seven Lesson Learned
Lak2018: Scaling Nationally: Seven Lesson Learned
 
openEQUELLA Q3 2018 Quarterly Briefing
openEQUELLA Q3 2018 Quarterly BriefingopenEQUELLA Q3 2018 Quarterly Briefing
openEQUELLA Q3 2018 Quarterly Briefing
 

More from Jay Luker

Coinage
CoinageCoinage
Coinage
Jay Luker
 
Using SweetSpotSimilarity for Solr Fulltext Indexing
Using SweetSpotSimilarity for Solr Fulltext IndexingUsing SweetSpotSimilarity for Solr Fulltext Indexing
Using SweetSpotSimilarity for Solr Fulltext Indexing
Jay Luker
 
N Characters in Search of an Author: Improving Author Name Indexing & Searchi...
N Characters in Search of an Author: Improving Author Name Indexing & Searchi...N Characters in Search of an Author: Improving Author Name Indexing & Searchi...
N Characters in Search of an Author: Improving Author Name Indexing & Searchi...Jay Luker
 
Letting In the Light: Using Solr as an External Search Component
Letting In the Light: Using Solr as an External Search ComponentLetting In the Light: Using Solr as an External Search Component
Letting In the Light: Using Solr as an External Search Component
Jay Luker
 
LexFarm Busa Farm Site Plan
LexFarm Busa Farm Site PlanLexFarm Busa Farm Site Plan
LexFarm Busa Farm Site PlanJay Luker
 
LexFarm Presentation
LexFarm PresentationLexFarm Presentation
LexFarm PresentationJay Luker
 
LexFarm Proposal
LexFarm ProposalLexFarm Proposal
LexFarm ProposalJay Luker
 

More from Jay Luker (7)

Coinage
CoinageCoinage
Coinage
 
Using SweetSpotSimilarity for Solr Fulltext Indexing
Using SweetSpotSimilarity for Solr Fulltext IndexingUsing SweetSpotSimilarity for Solr Fulltext Indexing
Using SweetSpotSimilarity for Solr Fulltext Indexing
 
N Characters in Search of an Author: Improving Author Name Indexing & Searchi...
N Characters in Search of an Author: Improving Author Name Indexing & Searchi...N Characters in Search of an Author: Improving Author Name Indexing & Searchi...
N Characters in Search of an Author: Improving Author Name Indexing & Searchi...
 
Letting In the Light: Using Solr as an External Search Component
Letting In the Light: Using Solr as an External Search ComponentLetting In the Light: Using Solr as an External Search Component
Letting In the Light: Using Solr as an External Search Component
 
LexFarm Busa Farm Site Plan
LexFarm Busa Farm Site PlanLexFarm Busa Farm Site Plan
LexFarm Busa Farm Site Plan
 
LexFarm Presentation
LexFarm PresentationLexFarm Presentation
LexFarm Presentation
 
LexFarm Proposal
LexFarm ProposalLexFarm Proposal
LexFarm Proposal
 

Recently uploaded

原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
u86oixdj
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
apvysm8
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 
Nanandann Nilekani's ppt On India's .pdf
Nanandann Nilekani's ppt On India's .pdfNanandann Nilekani's ppt On India's .pdf
Nanandann Nilekani's ppt On India's .pdf
eddie19851
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
TravisMalana
 
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdfEnhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
GetInData
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
slg6lamcq
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
kuntobimo2016
 
Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
vikram sood
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
roli9797
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
manishkhaire30
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
slg6lamcq
 
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data LakeViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
Walaa Eldin Moustafa
 
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptxData_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
AnirbanRoy608946
 
Everything you wanted to know about LIHTC
Everything you wanted to know about LIHTCEverything you wanted to know about LIHTC
Everything you wanted to know about LIHTC
Roger Valdez
 
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
ahzuo
 
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
74nqk8xf
 
The Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series DatabaseThe Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series Database
javier ramirez
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 

Recently uploaded (20)

原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
 
Nanandann Nilekani's ppt On India's .pdf
Nanandann Nilekani's ppt On India's .pdfNanandann Nilekani's ppt On India's .pdf
Nanandann Nilekani's ppt On India's .pdf
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
 
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdfEnhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
 
Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
 
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data LakeViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
 
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptxData_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
 
Everything you wanted to know about LIHTC
Everything you wanted to know about LIHTCEverything you wanted to know about LIHTC
Everything you wanted to know about LIHTC
 
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
 
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
 
The Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series DatabaseThe Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series Database
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 

Learning Engineering Initiatives at Harvard DCE

  • 1. Learning Engineering Initiatives at Harvard DCE Jay Luker, Senior Software Engineer Phoebe Miller, Senior Software Engineer Harvard IT Summit, 2017
  • 2. What is Learning Engineering? "Using learning analytics data to help faculty and course designers tailor DCE's learning environments and improve student outcomes." — Phoebe & Jay, 2017 "[To achieve] the professional design of learning environments and learning experiences, [...] the most important step is to find a place on the campus for a team of individuals who are professionals in the design of learning environments—learning engineers." — Herbert A. Simon, The Job of the College President, 1967
  • 3. Who & What ● DCE's Online Teaching & Learning Development Group ○ 4 Software Engineers* ○ 1 QA Engineer ○ 1 A/V Engineer ○ 1 Benevolent Overlord ● Building Software to benefit students, faculty and producers ● Lecture capture, lecture delivery, Canvas LTI tools, deployment, testing & monitoring tools ● Java, Python, JavaScript, Ruby, R ● Fully AWS-ified since January 2016 * we're hiring!
  • 4. Collectable class attendance data ● Online (live) web conference ○ Zoom web conference classes ● Lecture Videos ○ Recorded live lectures with live streaming ○ Republished lectures from past semesters
  • 5. ● Open source video capture and distribution system ● Developed by a robust community, mostly higher-ed institutions ● Viewer Annotation, automatic closed captioning ● v1.0 released August, 2010 ● v3.0 to be released this summer! ● Multistream video player designed specifically for lectures ● Supports all major browsers, mobile, live streaming ● Themeable & customizable via plugins ● Extensive user-tracking functionality, i.e., "useraction" events
  • 6. Paella records useraction events: PLAY, SEEK, HEARTBEAT, etc Opencast API: IDs user, maintains session, stores in MySQL Python harvester runs at 2m intervals, adds lecture metadata SQS used as a buffer queue Logstash adds geolocation info, parses user-agent data Elasticsearch: daily rolling indexes; search & aggregation Apps & APIs, e.g. Kibana dashboards Useraction Event Pipeline
  • 8. User Activity Dashboard ● Powered by Kibana, an open source visualization tool for Elasticsearch data ● Time-series graphs of active user sessions ● Filter by: ○ live viewers vs on-demand ○ identified vs anonymous ○ browser/OS, course, geolocation ● Top terms tables for any event field, geolocation heat map ● Very useful for fixing a few data integrity issues
  • 9. Phase One: Proof of Concept ● Attempting to use the data on hand to answer basic, high-level questions: ○ What is being watched? ○ Who is watching? ○ How is it being watched? ● 3-week "sprint" in late 2016 ● Django + Elasticsearch + d3.js + DataTables.js ● Useful! ○ stakeholder feedback ○ refining the questions ○ highlighted gaps and integrity issues with the data
  • 10. More Data! ● Canvas data from VPAL ○ Office of the Vice Provost for Advances in Learning ○ Research group focused on learning science ○ DCE contributes useraction event data & code ○ VPAL provides access to "data products" generated from Canvas activity data ● Auto-generated lecture transcripts ○ IBM Watson speech-to-text service ● Opencast Social ○ Video annotation text
  • 11. Data Inventory ● Useraction event data ○ Lecture viewing behavior, timestamps ● Zoom web conferencing data ○ Meetings, Participants, connection data, timestamps ● Banner student information data ○ Course rolls, registration status ● Canvas activity data ○ Discussions, quizzes, time-on-task ● Transcript data ○ Searchable transcript text, auto-transcription confidence scores ● Annotation text ○ Text, timestamps
  • 12. Phase Two: Answering Questions ● Shifting our development approach ○ from "Hey, look what we can do!" ○ to "What questions do you want us to answer?" ● Switching to R + Shiny ○ Powerful data manipulation ○ Awesome graphs ○ Designed specifically for interactive visualization UIs ○ Allows for more rapid generation of rich graphs and interactive visualizations ○ Smaller, stand-alone apps vs monolithic UI ○ Faster iterations to answer experimental questions
  • 13. How many students watched the lecture videos for a course?
  • 14. How many students watched the lecture or the section videos in a series?
  • 15. Which students are (and are not) keeping up with the online lectures?
  • 16.
  • 17. What parts of the lectures are most watched?
  • 18. What parts of the lectures are most watched?
  • 19. What parts of the lectures are most watched?
  • 20. What topics were discussed by students during a lecture?
  • 21. What topics were discussed by students during a lecture? Word cloud generated from viewer annotations during lecture 6 of the course “Organizational Behavior”
  • 22. Which students attended a lecture or meeting and were they there the whole time?
  • 23. Q: Which students attended a lecture or meeting and were they there the whole time? Opencast Lectures Using the heartbeats from opencast/paella, one can see student’s coverage of one video
  • 24. Which students attended a lecture or meeting and were they there the whole time? Zoom Web Conferences Zoom provides a REST API to access meetings, reports and other data. Participant are identified by user name and ip address, as well as connection type, city, country, duration and other information
  • 25. Details of each student’s connection experience can be displayed on one graph
  • 26. Thanks! Questions? ● These slides: http://bit.ly/2sHcWyo ● Github: https://github.com/harvard-dce ● Opencast: http://www.opencast.org/ ● VPAL: https://vpal.harvard.edu/