SlideShare une entreprise Scribd logo
1  sur  51
Télécharger pour lire hors ligne
Juho Kim Phu Nguyen
Sarah Weir Philip J. Guo
Robert C. Miller Krzysztof Z. Gajos
Crowdsourcing Step-by-Step
Information Extraction to
Enhance Existing How-to Videos
how-to videos online
learning from how-to videos:
limited by video player interfaces
Watching Example
Problem in Watching


It’s difficult to navigate to
specific parts you’re interested in.
Problem in Watching


It’s difficult to navigate to
specific parts you’re interested in.
find
repeat
skip
How-to Video: Step-by-Step Nature
Apply
gradient map
Completeness & detail of step-by-step instructions are
integral to task performance.
Eiriksdottir and Catrambone, 2011
Proactive & random access, semantic indices in
instructional videos: better task performance and learner
satisfaction
Zhang et al., 2006
Interactivity can help overcome the difficulties of
perception and comprehension. Stopping, starting and
replaying an animation can allow reinspection.
Tversky et al., 2002
Design Insight
Enable step-by-step navigation with high interactivity
ToolScape: Step-aware video player
work in progress
images
parts with no
visual progress
step labels & links
enhance existing how-to videos with
step-level interactivity & annotation
Research Questions
Does step-by-step navigation help learners?
Preliminary user study
How can we annotate an existing how-to
video with step-by-step information? 
Crowdsourcing annotation workflow
Research Questions
Does step-by-step navigation help learners?
Preliminary user study
How can we annotate an existing how-to
video with step-by-step information? 
Crowdsourcing annotation workflow
Study: Photoshop Design Tasks
12 novice Photoshop users
manually annotated videos
Baseline ToolScape
With ToolScape, learners will…

H1. feel more confident about their design
skills.
- self-efficacy gain

H2. believe they produced better designs.
- self-rating on designs produced

H3. actually produce better designs.
- external rating on designs produced
H1. Higher self-efficacy gain with ToolScape
–  Four 7-Likert scale questions
–  Mann-Whitney’s U test (Z=2.06, p<0.05), error bar: standard error
1.4	
  
0	
   1	
   2	
   3	
   4	
   5	
   6	
   7	
  
ToolScape	
  
Baseline	
   0.1	
  3.8	
  
3.8	
  
H2. Higher self-rating with ToolScape
–  One 7-Likert scale question
–  Mann-Whitney’s U test (Z=2.70, p<0.01), error bar: standard error
5.3	
  
3.5	
  
0	
   1	
   2	
   3	
   4	
   5	
   6	
   7	
  
ToolScape	
  
Baseline	
  
H3. External raters rank ToolScape designs higher.
–  (Ranking: Lower is better)
–  Wilcoxon Signed-rank test (W=317, Z=-2.79, p<0.01, r=0.29) , error bar: standard error
–  Krippendorff’s alpha = 0.753
5.7	
  
7.3	
  
0	
   2	
   4	
   6	
   8	
   10	
   12	
  
ToolScape	
  
Baseline	
  
Non-sequentially navigating video
Step-level navigation: clicked 8.9 times per task
“It is great for skipping straight to relevant
portions of the tutorial.” 

“It was also easier to go back to parts I missed.”
Research Questions
Does step-by-step navigation help learners?
Preliminary user study
How can we annotate an existing how-to
video with step-by-step information? 
Crowdsourcing annotation workflow
Annotations for Step-Aware Video Player
•  step time
•  step label
•  before/after results
Design Goals for Annotation Method
•  domain-independent
•  existing videos
•  untrained annotators
Crowdsourcing
Multi-stage crowdsourcing workflow
When &
What are the
steps?
Vote &
Improve
Before/After
the steps?
FIND
 VERIFY
 EXPAND
When &
What are the
steps?
Vote &
Improve
Before/After
the steps?
FIND
 VERIFY
 EXPAND
Input video
When &
What are the
steps?
Vote &
Improve
Before/After
the steps?
FIND
 VERIFY
 EXPAND
Input video
When &
What are the
steps?
Vote &
Improve
Before/After
the steps?
FIND
 VERIFY
 EXPAND
Input video
When &
What are the
steps?
Vote &
Improve
Before/After
the steps?
FIND
 VERIFY
 EXPAND
Input video
When &
What are the
steps?
Vote &
Improve
Before/After
the steps?
FIND
 VERIFY
 EXPAND
Input video
Output timeline
Stage 1. FIND candidate steps
Labeling a step
Time-based Clustering
Stage 2. VERIFY steps by voting/improving
Quality control for Stage 2
•  Majority voting
•  Breaking ties
– String matching to combine
“similar enough” labels

– Longer string

“grate three cups of cheese” > “grate cheese”
Stage 3. EXPAND with
before/after images
Quality control for Stage 3
•  Majority voting
•  Breaking ties:
– Pixel diff to combine
“similar enough” frames

– Choose what’s closer to the step
Evaluation
•  Generalizable? 

75 Photoshop / Cooking / Makeup videos
•  Accurate?
precision and recall
against trained annotators’ labels
Across all domains,
~80% precision and recall
Domain
 Precision
 Recall
Cooking
 0.77
 0.84
Makeup
 0.74
 0.77
Photoshop
 0.79
 0.79
All
 0.77
 0.81
Conceptual Level Differences
•  “Now apply the bronzer to your face
evenly”
•  “Apply the bronzer to the forehead”
•  “Apply the bronzer to the cheekbones”
•  “Apply the bronzer to the jawline”
Timing is 2.7 seconds off on average
Ground truth: one step every 17.3 seconds
2.7 seconds
Cost: $1.07 per minute of video
• 111 HITs / video (3 workers / task)
• $2.50 / video (Find + Verify)
• $4.85 / video (Find + Verify + Expand)
• $0.32 / step (time + label + before/after)
Contributions

•  Study: increased interactivity improved
task performance & self-efficacy
•  Crowd video annotation method &
Find-Verify-Expand design pattern
•  Evaluation: fully extracted 75 existing videos
across 3 domains, 80% accuracy
hierarchical solution structure extraction
Catrambone, R. The subgoal learning model: Creating better examples so that
students can solve novel problems. Journal of Experimental Psychology: General, 127, (1998).
Ongoing Work: Beyond low-level steps
hierarchical solution structure extraction
Ongoing Work: Beyond low-level steps
Learnersourcing: learners as a crowd
•  Motivated, qualified
•  Feedback loop between learners & system
Future of How-to Video Learning
What if we had 1000s of
fully annotated videos?
•  Flexible learning paths with multiple videos
•  Step-level search, recommendation
•  Patterns from multiple solutions
Crowdsourcing Step-by-Step Information Extraction to
Enhance Existing How-to Videos
Juho Kim
MIT CSAIL

juhokim@mit.edu

juhokim.com
Acknowledgement: This work was supported in part by
Quanta Computer & the Samsung Fellowship.

Contenu connexe

Tendances

Subjective questionnaires
Subjective questionnairesSubjective questionnaires
Subjective questionnairesaukee
 
S davis bblteurpoe2012_videofeedback
S davis bblteurpoe2012_videofeedbackS davis bblteurpoe2012_videofeedback
S davis bblteurpoe2012_videofeedbackSimon Davis
 
A deep dive into questions by @cjforms at UxLx
A deep dive into questions by @cjforms at UxLxA deep dive into questions by @cjforms at UxLx
A deep dive into questions by @cjforms at UxLxCaroline Jarrett
 
Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...
Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...
Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...Kelvin Thompson
 
Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...
Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...
Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...D2L Barry
 
Empowering YouTube for Higher Education
Empowering YouTube for Higher EducationEmpowering YouTube for Higher Education
Empowering YouTube for Higher Education3Play Media
 
The Instructor is In: Sustaining Presence in the Online Environment
The Instructor is In: Sustaining Presence in the Online EnvironmentThe Instructor is In: Sustaining Presence in the Online Environment
The Instructor is In: Sustaining Presence in the Online EnvironmentD2L Barry
 
Cobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slides
Cobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slidesCobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slides
Cobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slidesJuho Kim
 
Do Captions & Transcripts Improve Student Learning?
Do Captions & Transcripts Improve Student Learning?Do Captions & Transcripts Improve Student Learning?
Do Captions & Transcripts Improve Student Learning?Sofia Leiva Enamorado
 
Maisie Finalv2.0
Maisie Finalv2.0Maisie Finalv2.0
Maisie Finalv2.0annwarm
 
The affordances of studying in a virtual world.
The affordances of studying in a virtual world.The affordances of studying in a virtual world.
The affordances of studying in a virtual world.jimbbq
 
Moving Student Presentations Online
Moving Student Presentations OnlineMoving Student Presentations Online
Moving Student Presentations OnlineKim Kenward
 
Bb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel Session
Bb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel SessionBb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel Session
Bb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel SessionBlackboard APAC
 
The Future of Closed Captioning in Higher Education
The Future of Closed Captioning in Higher EducationThe Future of Closed Captioning in Higher Education
The Future of Closed Captioning in Higher Education3Play Media
 
University of Wisconsin: Captioning and Transcription Policies, Uses and Work...
University of Wisconsin: Captioning and Transcription Policies, Uses and Work...University of Wisconsin: Captioning and Transcription Policies, Uses and Work...
University of Wisconsin: Captioning and Transcription Policies, Uses and Work...3Play Media
 
The State of Closed Captioning in Higher Education
The State of Closed Captioning in Higher EducationThe State of Closed Captioning in Higher Education
The State of Closed Captioning in Higher Education3Play Media
 
Choose your own Adventure, Increase Student Engagement in Brightspace
Choose your own Adventure, Increase Student Engagement in BrightspaceChoose your own Adventure, Increase Student Engagement in Brightspace
Choose your own Adventure, Increase Student Engagement in BrightspaceD2L Barry
 

Tendances (20)

Subjective questionnaires
Subjective questionnairesSubjective questionnaires
Subjective questionnaires
 
S davis bblteurpoe2012_videofeedback
S davis bblteurpoe2012_videofeedbackS davis bblteurpoe2012_videofeedback
S davis bblteurpoe2012_videofeedback
 
A deep dive into questions by @cjforms at UxLx
A deep dive into questions by @cjforms at UxLxA deep dive into questions by @cjforms at UxLx
A deep dive into questions by @cjforms at UxLx
 
Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...
Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...
Cultivating Information Literacy Among Students: Lessons Learned from UCF’s I...
 
Webinar REC:all
Webinar REC:allWebinar REC:all
Webinar REC:all
 
Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...
Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...
Using Brightspaceto Create a Virtual Message Center for an Entire Academic Pr...
 
Empowering YouTube for Higher Education
Empowering YouTube for Higher EducationEmpowering YouTube for Higher Education
Empowering YouTube for Higher Education
 
The Instructor is In: Sustaining Presence in the Online Environment
The Instructor is In: Sustaining Presence in the Online EnvironmentThe Instructor is In: Sustaining Presence in the Online Environment
The Instructor is In: Sustaining Presence in the Online Environment
 
Digital Badges @ UCF
Digital Badges @ UCFDigital Badges @ UCF
Digital Badges @ UCF
 
Cobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slides
Cobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slidesCobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slides
Cobi: A Community-Informed Conference Scheduling Tool. UIST 2013 slides
 
Do Captions & Transcripts Improve Student Learning?
Do Captions & Transcripts Improve Student Learning?Do Captions & Transcripts Improve Student Learning?
Do Captions & Transcripts Improve Student Learning?
 
Maisie Finalv2.0
Maisie Finalv2.0Maisie Finalv2.0
Maisie Finalv2.0
 
The affordances of studying in a virtual world.
The affordances of studying in a virtual world.The affordances of studying in a virtual world.
The affordances of studying in a virtual world.
 
Moving Student Presentations Online
Moving Student Presentations OnlineMoving Student Presentations Online
Moving Student Presentations Online
 
Bb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel Session
Bb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel SessionBb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel Session
Bb on Tour 2016 | Innovation and Your Institution (Part 1) | Panel Session
 
The Future of Closed Captioning in Higher Education
The Future of Closed Captioning in Higher EducationThe Future of Closed Captioning in Higher Education
The Future of Closed Captioning in Higher Education
 
University of Wisconsin: Captioning and Transcription Policies, Uses and Work...
University of Wisconsin: Captioning and Transcription Policies, Uses and Work...University of Wisconsin: Captioning and Transcription Policies, Uses and Work...
University of Wisconsin: Captioning and Transcription Policies, Uses and Work...
 
The State of Closed Captioning in Higher Education
The State of Closed Captioning in Higher EducationThe State of Closed Captioning in Higher Education
The State of Closed Captioning in Higher Education
 
DLA 2010 Who Done It?
DLA 2010 Who Done It?DLA 2010 Who Done It?
DLA 2010 Who Done It?
 
Choose your own Adventure, Increase Student Engagement in Brightspace
Choose your own Adventure, Increase Student Engagement in BrightspaceChoose your own Adventure, Increase Student Engagement in Brightspace
Choose your own Adventure, Increase Student Engagement in Brightspace
 

En vedette

Understanding the Effects of Streamlining the Orchestration of Learning Activ...
Understanding the Effects of Streamlining the Orchestration of Learning Activ...Understanding the Effects of Streamlining the Orchestration of Learning Activ...
Understanding the Effects of Streamlining the Orchestration of Learning Activ...Lighton Phiri
 
Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...
Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...
Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...Lighton Phiri
 
Presenting your Research at the ECTEL Doctoral Consortium
Presenting your Research at the ECTEL Doctoral ConsortiumPresenting your Research at the ECTEL Doctoral Consortium
Presenting your Research at the ECTEL Doctoral ConsortiumChristian Glahn
 
Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2
Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2
Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2Cesc Alcaraz
 
Tackling workload in general practice, Pulse Live 18 Oct 2016
Tackling workload in general practice, Pulse Live 18 Oct 2016Tackling workload in general practice, Pulse Live 18 Oct 2016
Tackling workload in general practice, Pulse Live 18 Oct 2016Robert Varnam Coaching
 
Releasing capacity in General Practice, N Staffs
Releasing capacity in General Practice, N StaffsReleasing capacity in General Practice, N Staffs
Releasing capacity in General Practice, N StaffsRobert Varnam Coaching
 
Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...
Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...
Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...Yasser Sami Abdel Dayem Amer
 
Telephone triage nurse: current role and skills
Telephone triage nurse: current role and skillsTelephone triage nurse: current role and skills
Telephone triage nurse: current role and skillsSheila Wheeler
 
Transforming Big Data into Big Value
Transforming Big Data into Big ValueTransforming Big Data into Big Value
Transforming Big Data into Big ValueThomas Kelly, PMP
 
Clinical reasoning in physiotherapy
Clinical reasoning in physiotherapyClinical reasoning in physiotherapy
Clinical reasoning in physiotherapySaurab Sharma
 
Elsevier Medical Graph – mit Machine Learning zu Precision Medicine
Elsevier Medical Graph – mit Machine Learning zu Precision MedicineElsevier Medical Graph – mit Machine Learning zu Precision Medicine
Elsevier Medical Graph – mit Machine Learning zu Precision MedicineRising Media Ltd.
 
Application of graph theory in drug design
Application of graph theory in drug designApplication of graph theory in drug design
Application of graph theory in drug designReihaneh Safavi
 
Evidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGY
Evidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGYEvidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGY
Evidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGYYasser Sami Abdel Dayem Amer
 
CLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINES
CLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINESCLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINES
CLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINESMary Ann Adiong
 
Shallow introduction for Deep Learning Retinal Image Analysis
Shallow introduction for Deep Learning Retinal Image AnalysisShallow introduction for Deep Learning Retinal Image Analysis
Shallow introduction for Deep Learning Retinal Image AnalysisPetteriTeikariPhD
 
Evaluation – concepts and principles
Evaluation – concepts and principlesEvaluation – concepts and principles
Evaluation – concepts and principlesAruna Ap
 
Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...
Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...
Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...Lighton Phiri
 

En vedette (20)

Understanding the Effects of Streamlining the Orchestration of Learning Activ...
Understanding the Effects of Streamlining the Orchestration of Learning Activ...Understanding the Effects of Streamlining the Orchestration of Learning Activ...
Understanding the Effects of Streamlining the Orchestration of Learning Activ...
 
Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...
Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...
Ad hoc vs. organised orchestration: A comparative analysis of technology-driv...
 
Presenting your Research at the ECTEL Doctoral Consortium
Presenting your Research at the ECTEL Doctoral ConsortiumPresenting your Research at the ECTEL Doctoral Consortium
Presenting your Research at the ECTEL Doctoral Consortium
 
Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2
Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2
Tefen feed background_ls lean quality diag_implementation_support_2012 v1.2
 
Practice Manager networking event
Practice Manager networking eventPractice Manager networking event
Practice Manager networking event
 
Tackling workload in general practice, Pulse Live 18 Oct 2016
Tackling workload in general practice, Pulse Live 18 Oct 2016Tackling workload in general practice, Pulse Live 18 Oct 2016
Tackling workload in general practice, Pulse Live 18 Oct 2016
 
Releasing capacity in General Practice, N Staffs
Releasing capacity in General Practice, N StaffsReleasing capacity in General Practice, N Staffs
Releasing capacity in General Practice, N Staffs
 
Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...
Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...
Evidence-Based Clinical Practice Guidelines (CPGs) Adaptation & Implementati...
 
1 Year PhD Presentation
1 Year PhD Presentation1 Year PhD Presentation
1 Year PhD Presentation
 
8. diy rating
8. diy rating8. diy rating
8. diy rating
 
Telephone triage nurse: current role and skills
Telephone triage nurse: current role and skillsTelephone triage nurse: current role and skills
Telephone triage nurse: current role and skills
 
Transforming Big Data into Big Value
Transforming Big Data into Big ValueTransforming Big Data into Big Value
Transforming Big Data into Big Value
 
Clinical reasoning in physiotherapy
Clinical reasoning in physiotherapyClinical reasoning in physiotherapy
Clinical reasoning in physiotherapy
 
Elsevier Medical Graph – mit Machine Learning zu Precision Medicine
Elsevier Medical Graph – mit Machine Learning zu Precision MedicineElsevier Medical Graph – mit Machine Learning zu Precision Medicine
Elsevier Medical Graph – mit Machine Learning zu Precision Medicine
 
Application of graph theory in drug design
Application of graph theory in drug designApplication of graph theory in drug design
Application of graph theory in drug design
 
Evidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGY
Evidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGYEvidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGY
Evidence-Based Clinical Practice Guidelines for OBSTETRICS AND GYNECOLOGY
 
CLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINES
CLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINESCLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINES
CLINICAL PATHWAY and CLINICAL PRACTICE GUIDELINES
 
Shallow introduction for Deep Learning Retinal Image Analysis
Shallow introduction for Deep Learning Retinal Image AnalysisShallow introduction for Deep Learning Retinal Image Analysis
Shallow introduction for Deep Learning Retinal Image Analysis
 
Evaluation – concepts and principles
Evaluation – concepts and principlesEvaluation – concepts and principles
Evaluation – concepts and principles
 
Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...
Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...
Streamlined Technology-driven Orchestration: Towards Streamlined Technology-d...
 

Similaire à CHI2014 - Crowdsourcing Step-by-Step Information Extraction to Enhance Existing How-to Videos

Do Screencasts Really Work? Assessing Student Learning through Instructional ...
Do Screencasts Really Work? Assessing Student Learning through Instructional ...Do Screencasts Really Work? Assessing Student Learning through Instructional ...
Do Screencasts Really Work? Assessing Student Learning through Instructional ...juliepia
 
Hci – Project Presentation
Hci – Project PresentationHci – Project Presentation
Hci – Project Presentationslmsaady
 
tcc conference 2011 tsunami preparedness web module
tcc conference 2011 tsunami preparedness web moduletcc conference 2011 tsunami preparedness web module
tcc conference 2011 tsunami preparedness web moduleLulu Liu
 
Art Center Interactive Design 4 - #4 Usability Testing
Art Center Interactive Design 4 - #4 Usability TestingArt Center Interactive Design 4 - #4 Usability Testing
Art Center Interactive Design 4 - #4 Usability TestingJoy Liu
 
Rapid usability testing
Rapid usability testingRapid usability testing
Rapid usability testinglisarex
 
Planetizen Courses Website Usability Testing
Planetizen Courses Website Usability TestingPlanetizen Courses Website Usability Testing
Planetizen Courses Website Usability TestingH. Helen Brown
 
eLearning Content Development Code and Pixels.pdf
eLearning Content Development Code and Pixels.pdfeLearning Content Development Code and Pixels.pdf
eLearning Content Development Code and Pixels.pdfDigital Teacher
 
Reactome: Usability testing - is it useful?
Reactome: Usability testing - is it useful? Reactome: Usability testing - is it useful?
Reactome: Usability testing - is it useful? Francis Rowland
 
Learning Lunch Box Sept 2013 - Elizabeth Davis presentation
Learning Lunch Box Sept 2013 - Elizabeth Davis presentationLearning Lunch Box Sept 2013 - Elizabeth Davis presentation
Learning Lunch Box Sept 2013 - Elizabeth Davis presentationrachelsaffer
 
Remote usability testing and remote user research for usability
Remote usability testing and remote user research for usabilityRemote usability testing and remote user research for usability
Remote usability testing and remote user research for usabilityUser Vision
 
UserTesting 2016 webinar: Research to inform product design in Agile environm...
UserTesting 2016 webinar: Research to inform product design in Agile environm...UserTesting 2016 webinar: Research to inform product design in Agile environm...
UserTesting 2016 webinar: Research to inform product design in Agile environm...Steve Fadden
 
Eye tracking in usability studies
Eye tracking in usability studiesEye tracking in usability studies
Eye tracking in usability studiesNana Nielsen
 
Podcamp11: DIY Usability Testing
Podcamp11: DIY Usability TestingPodcamp11: DIY Usability Testing
Podcamp11: DIY Usability Testingmandyhb
 
Learning Lunch Box Sept 2013 - Kris Ryan presentation
Learning Lunch Box Sept 2013 - Kris Ryan presentationLearning Lunch Box Sept 2013 - Kris Ryan presentation
Learning Lunch Box Sept 2013 - Kris Ryan presentationrachelsaffer
 

Similaire à CHI2014 - Crowdsourcing Step-by-Step Information Extraction to Enhance Existing How-to Videos (20)

Do Screencasts Really Work? Assessing Student Learning through Instructional ...
Do Screencasts Really Work? Assessing Student Learning through Instructional ...Do Screencasts Really Work? Assessing Student Learning through Instructional ...
Do Screencasts Really Work? Assessing Student Learning through Instructional ...
 
Hci – Project Presentation
Hci – Project PresentationHci – Project Presentation
Hci – Project Presentation
 
Kirsty barnes conf_10
Kirsty barnes conf_10Kirsty barnes conf_10
Kirsty barnes conf_10
 
tcc conference 2011 tsunami preparedness web module
tcc conference 2011 tsunami preparedness web moduletcc conference 2011 tsunami preparedness web module
tcc conference 2011 tsunami preparedness web module
 
Art Center Interactive Design 4 - #4 Usability Testing
Art Center Interactive Design 4 - #4 Usability TestingArt Center Interactive Design 4 - #4 Usability Testing
Art Center Interactive Design 4 - #4 Usability Testing
 
Rapid usability testing
Rapid usability testingRapid usability testing
Rapid usability testing
 
Planetizen Courses Website Usability Testing
Planetizen Courses Website Usability TestingPlanetizen Courses Website Usability Testing
Planetizen Courses Website Usability Testing
 
eLearning Content Development Code and Pixels.pdf
eLearning Content Development Code and Pixels.pdfeLearning Content Development Code and Pixels.pdf
eLearning Content Development Code and Pixels.pdf
 
Module 10: Usability Testing
Module 10: Usability TestingModule 10: Usability Testing
Module 10: Usability Testing
 
The feedback loop revisited
The feedback loop revisitedThe feedback loop revisited
The feedback loop revisited
 
Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?
 
Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?
 
Reactome: Usability testing - is it useful?
Reactome: Usability testing - is it useful? Reactome: Usability testing - is it useful?
Reactome: Usability testing - is it useful?
 
Learning Lunch Box Sept 2013 - Elizabeth Davis presentation
Learning Lunch Box Sept 2013 - Elizabeth Davis presentationLearning Lunch Box Sept 2013 - Elizabeth Davis presentation
Learning Lunch Box Sept 2013 - Elizabeth Davis presentation
 
Remote usability testing and remote user research for usability
Remote usability testing and remote user research for usabilityRemote usability testing and remote user research for usability
Remote usability testing and remote user research for usability
 
Say what?
Say what?Say what?
Say what?
 
UserTesting 2016 webinar: Research to inform product design in Agile environm...
UserTesting 2016 webinar: Research to inform product design in Agile environm...UserTesting 2016 webinar: Research to inform product design in Agile environm...
UserTesting 2016 webinar: Research to inform product design in Agile environm...
 
Eye tracking in usability studies
Eye tracking in usability studiesEye tracking in usability studies
Eye tracking in usability studies
 
Podcamp11: DIY Usability Testing
Podcamp11: DIY Usability TestingPodcamp11: DIY Usability Testing
Podcamp11: DIY Usability Testing
 
Learning Lunch Box Sept 2013 - Kris Ryan presentation
Learning Lunch Box Sept 2013 - Kris Ryan presentationLearning Lunch Box Sept 2013 - Kris Ryan presentation
Learning Lunch Box Sept 2013 - Kris Ryan presentation
 

Dernier

4.9.24 School Desegregation in Boston.pptx
4.9.24 School Desegregation in Boston.pptx4.9.24 School Desegregation in Boston.pptx
4.9.24 School Desegregation in Boston.pptxmary850239
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSMae Pangan
 
4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptxmary850239
 
Reading and Writing Skills 11 quarter 4 melc 1
Reading and Writing Skills 11 quarter 4 melc 1Reading and Writing Skills 11 quarter 4 melc 1
Reading and Writing Skills 11 quarter 4 melc 1GloryAnnCastre1
 
ICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfVanessa Camilleri
 
Grade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptxGrade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptxkarenfajardo43
 
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...DhatriParmar
 
Expanded definition: technical and operational
Expanded definition: technical and operationalExpanded definition: technical and operational
Expanded definition: technical and operationalssuser3e220a
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management systemChristalin Nelson
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptx
Unraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptxUnraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptx
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptxDhatriParmar
 
Using Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea DevelopmentUsing Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea Developmentchesterberbo7
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDhatriParmar
 
Scientific Writing :Research Discourse
Scientific  Writing :Research  DiscourseScientific  Writing :Research  Discourse
Scientific Writing :Research DiscourseAnita GoswamiGiri
 
ARTERIAL BLOOD GAS ANALYSIS........pptx
ARTERIAL BLOOD  GAS ANALYSIS........pptxARTERIAL BLOOD  GAS ANALYSIS........pptx
ARTERIAL BLOOD GAS ANALYSIS........pptxAneriPatwari
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQuiz Club NITW
 
4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptx4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptxmary850239
 
ClimART Action | eTwinning Project
ClimART Action    |    eTwinning ProjectClimART Action    |    eTwinning Project
ClimART Action | eTwinning Projectjordimapav
 

Dernier (20)

4.9.24 School Desegregation in Boston.pptx
4.9.24 School Desegregation in Boston.pptx4.9.24 School Desegregation in Boston.pptx
4.9.24 School Desegregation in Boston.pptx
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHS
 
4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx
 
Reading and Writing Skills 11 quarter 4 melc 1
Reading and Writing Skills 11 quarter 4 melc 1Reading and Writing Skills 11 quarter 4 melc 1
Reading and Writing Skills 11 quarter 4 melc 1
 
ICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdf
 
Grade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptxGrade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptx
 
INCLUSIVE EDUCATION PRACTICES FOR TEACHERS AND TRAINERS.pptx
INCLUSIVE EDUCATION PRACTICES FOR TEACHERS AND TRAINERS.pptxINCLUSIVE EDUCATION PRACTICES FOR TEACHERS AND TRAINERS.pptx
INCLUSIVE EDUCATION PRACTICES FOR TEACHERS AND TRAINERS.pptx
 
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
 
Expanded definition: technical and operational
Expanded definition: technical and operationalExpanded definition: technical and operational
Expanded definition: technical and operational
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management system
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptx
Unraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptxUnraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptx
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptx
 
Using Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea DevelopmentUsing Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea Development
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
 
Faculty Profile prashantha K EEE dept Sri Sairam college of Engineering
Faculty Profile prashantha K EEE dept Sri Sairam college of EngineeringFaculty Profile prashantha K EEE dept Sri Sairam college of Engineering
Faculty Profile prashantha K EEE dept Sri Sairam college of Engineering
 
Scientific Writing :Research Discourse
Scientific  Writing :Research  DiscourseScientific  Writing :Research  Discourse
Scientific Writing :Research Discourse
 
ARTERIAL BLOOD GAS ANALYSIS........pptx
ARTERIAL BLOOD  GAS ANALYSIS........pptxARTERIAL BLOOD  GAS ANALYSIS........pptx
ARTERIAL BLOOD GAS ANALYSIS........pptx
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
 
4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptx4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptx
 
ClimART Action | eTwinning Project
ClimART Action    |    eTwinning ProjectClimART Action    |    eTwinning Project
ClimART Action | eTwinning Project
 

CHI2014 - Crowdsourcing Step-by-Step Information Extraction to Enhance Existing How-to Videos

  • 1. Juho Kim Phu Nguyen Sarah Weir Philip J. Guo Robert C. Miller Krzysztof Z. Gajos Crowdsourcing Step-by-Step Information Extraction to Enhance Existing How-to Videos
  • 3.
  • 4. learning from how-to videos: limited by video player interfaces
  • 5.
  • 7. Problem in Watching It’s difficult to navigate to specific parts you’re interested in.
  • 8. Problem in Watching It’s difficult to navigate to specific parts you’re interested in. find repeat skip
  • 9. How-to Video: Step-by-Step Nature Apply gradient map
  • 10. Completeness & detail of step-by-step instructions are integral to task performance. Eiriksdottir and Catrambone, 2011 Proactive & random access, semantic indices in instructional videos: better task performance and learner satisfaction Zhang et al., 2006 Interactivity can help overcome the difficulties of perception and comprehension. Stopping, starting and replaying an animation can allow reinspection. Tversky et al., 2002
  • 11.
  • 12. Design Insight Enable step-by-step navigation with high interactivity
  • 14. work in progress images parts with no visual progress step labels & links
  • 15. enhance existing how-to videos with step-level interactivity & annotation
  • 16. Research Questions Does step-by-step navigation help learners? Preliminary user study How can we annotate an existing how-to video with step-by-step information? Crowdsourcing annotation workflow
  • 17. Research Questions Does step-by-step navigation help learners? Preliminary user study How can we annotate an existing how-to video with step-by-step information? Crowdsourcing annotation workflow
  • 18. Study: Photoshop Design Tasks 12 novice Photoshop users manually annotated videos
  • 20. With ToolScape, learners will… H1. feel more confident about their design skills. - self-efficacy gain H2. believe they produced better designs. - self-rating on designs produced H3. actually produce better designs. - external rating on designs produced
  • 21. H1. Higher self-efficacy gain with ToolScape –  Four 7-Likert scale questions –  Mann-Whitney’s U test (Z=2.06, p<0.05), error bar: standard error 1.4   0   1   2   3   4   5   6   7   ToolScape   Baseline   0.1  3.8   3.8  
  • 22. H2. Higher self-rating with ToolScape –  One 7-Likert scale question –  Mann-Whitney’s U test (Z=2.70, p<0.01), error bar: standard error 5.3   3.5   0   1   2   3   4   5   6   7   ToolScape   Baseline  
  • 23. H3. External raters rank ToolScape designs higher. –  (Ranking: Lower is better) –  Wilcoxon Signed-rank test (W=317, Z=-2.79, p<0.01, r=0.29) , error bar: standard error –  Krippendorff’s alpha = 0.753 5.7   7.3   0   2   4   6   8   10   12   ToolScape   Baseline  
  • 24. Non-sequentially navigating video Step-level navigation: clicked 8.9 times per task “It is great for skipping straight to relevant portions of the tutorial.” “It was also easier to go back to parts I missed.”
  • 25. Research Questions Does step-by-step navigation help learners? Preliminary user study How can we annotate an existing how-to video with step-by-step information? Crowdsourcing annotation workflow
  • 26. Annotations for Step-Aware Video Player •  step time •  step label •  before/after results
  • 27. Design Goals for Annotation Method •  domain-independent •  existing videos •  untrained annotators
  • 29. Multi-stage crowdsourcing workflow When & What are the steps? Vote & Improve Before/After the steps? FIND VERIFY EXPAND
  • 30. When & What are the steps? Vote & Improve Before/After the steps? FIND VERIFY EXPAND Input video
  • 31. When & What are the steps? Vote & Improve Before/After the steps? FIND VERIFY EXPAND Input video
  • 32. When & What are the steps? Vote & Improve Before/After the steps? FIND VERIFY EXPAND Input video
  • 33. When & What are the steps? Vote & Improve Before/After the steps? FIND VERIFY EXPAND Input video
  • 34. When & What are the steps? Vote & Improve Before/After the steps? FIND VERIFY EXPAND Input video Output timeline
  • 35. Stage 1. FIND candidate steps
  • 38. Stage 2. VERIFY steps by voting/improving
  • 39. Quality control for Stage 2 •  Majority voting •  Breaking ties – String matching to combine “similar enough” labels – Longer string “grate three cups of cheese” > “grate cheese”
  • 40. Stage 3. EXPAND with before/after images
  • 41. Quality control for Stage 3 •  Majority voting •  Breaking ties: – Pixel diff to combine “similar enough” frames – Choose what’s closer to the step
  • 42. Evaluation •  Generalizable? 75 Photoshop / Cooking / Makeup videos •  Accurate? precision and recall against trained annotators’ labels
  • 43. Across all domains, ~80% precision and recall Domain Precision Recall Cooking 0.77 0.84 Makeup 0.74 0.77 Photoshop 0.79 0.79 All 0.77 0.81
  • 44. Conceptual Level Differences •  “Now apply the bronzer to your face evenly” •  “Apply the bronzer to the forehead” •  “Apply the bronzer to the cheekbones” •  “Apply the bronzer to the jawline”
  • 45. Timing is 2.7 seconds off on average Ground truth: one step every 17.3 seconds 2.7 seconds
  • 46. Cost: $1.07 per minute of video • 111 HITs / video (3 workers / task) • $2.50 / video (Find + Verify) • $4.85 / video (Find + Verify + Expand) • $0.32 / step (time + label + before/after)
  • 47. Contributions •  Study: increased interactivity improved task performance & self-efficacy •  Crowd video annotation method & Find-Verify-Expand design pattern •  Evaluation: fully extracted 75 existing videos across 3 domains, 80% accuracy
  • 48. hierarchical solution structure extraction Catrambone, R. The subgoal learning model: Creating better examples so that students can solve novel problems. Journal of Experimental Psychology: General, 127, (1998). Ongoing Work: Beyond low-level steps
  • 49. hierarchical solution structure extraction Ongoing Work: Beyond low-level steps Learnersourcing: learners as a crowd •  Motivated, qualified •  Feedback loop between learners & system
  • 50. Future of How-to Video Learning What if we had 1000s of fully annotated videos? •  Flexible learning paths with multiple videos •  Step-level search, recommendation •  Patterns from multiple solutions
  • 51. Crowdsourcing Step-by-Step Information Extraction to Enhance Existing How-to Videos Juho Kim MIT CSAIL juhokim@mit.edu juhokim.com Acknowledgement: This work was supported in part by Quanta Computer & the Samsung Fellowship.