SlideShare uma empresa Scribd logo
1 de 31
Baixar para ler offline
Learning by Example: training
users through high-quality
query suggestions (SIGIR’15)
A collaboration with Morgan Harvey & David Elsweiler.
Claudia Hauff
Web Information Systems
0
50,000,000
100,000,000
150,000,000
200,000,000
250,000,000
300,000,000
350,000,000
Sep*12 Apr*13 Oct*13 May*14 Dec*14 Jun*15 Jan*16
Data available at https://duckduckgo.com/traffic.html
NSA collecting phone records of millions of Verizon
customers daily. The Guardian. June 6, 2013.
Not everyone
stays around.
I do care about privacy …
until the moment my
searches fail me.
@flickr:eviloars
Can we teach searchers to use an arbitrary search
engine as best as possible?
@flickr:practicalowl
Advanced retrieval algorithms; queries as a given.
Assisting users in creating better queries.
query suggestions related searches query autocompletion
Personalised & context-driven search.
Educate users to become better searchers.Educate users to become better searchers.
complimentary to technical solutions system specific
• Altering the size [Franzen & Karlgren, 2000] and wording [Belkin et al., 2003] of the
search box influences the length of submitted queries
• Exchanging a complex multi-field catalogue interface for a simple search
box radically alters user behaviour [McKay & Buchanan, 2013]
• Training users how to construct boolean logic queries can change search
behaviour [Lucas & Topi, 2004]
• Allowing users to compare their search behaviour to expert searchers
enables them to reflect and change their habits [Bateman et al., 2012]
deeper in the results list [6].
Behaviour change support
systems
“… information systems designed to form, alter, or reinforce
attitudes or behaviours or both without using coercion or
deception” [Oinas-Kukkonen & Harjumaa, 2008]
We created zing
Our questions
Are users able to notice differences between good queries
and their own? Can they abstract these differences to
change their own behaviour?
How effectively can users learn and abstract from good
queries? Do users who are “trained” perform better than
users who did not receive training?
@flickr:eviloars
Our hypotheses
@flickr:carbonnyc
H1: Users can adapt their querying behaviour to pose good queries to
an unfamiliar search system.
H3: A small number of “training queries” are sufficient.
H4: A user who receives training with queries he can relate to, learns
better than a user who receives training with less-relatable queries.
H5: A user who receives training with queries he can relate to, learns
faster than a user who receives training with less-relatable queries.
H2: Users are able to identify salient characteristics of good queries.
A collection of user studies
Piloting zing
User perception of
high-quality queries Main study: zing
Training size study
Generating
training
queries
All studies are based on AQUAINT and the TREC 2005 Robust track topics.
• Query quality is measured in Average Precision
• The queries should intuitively make sense to
humans (instead of relying on quirks in documents)
• The queries should not be overly verbose or
specific
Generating high-quality
queries I
for each TREC topic
relevant
documents
100 single-term
queries
AQUAINT
Hand-crafted filtering rules to avoid unintuitive term selection.
Generating high-quality
queries II
for each TREC topic
relevant
documents
AQUAINT
AP-based
query ranking
top two-term
queries
Hand-crafted filtering rules to avoid unintuitive term selection.
Generating high-quality
queries II
for each TREC topic
relevant
documents
AQUAINT
AP-based
query ranking
3x
: top 100 queries up to length 4
Hand-crafted filtering rules to avoid unintuitive term selection.
Generating high-quality
queries II
Identify positive accomplishments of
the Hubble telescope since it was
launched in 1991. (303)
Identify drugs used in the treatment of
mental illness. (383)
What is the status of The Three Gorges
Project? (416)
* universe astronomer faint hubble
* infrared galaxies universe hubble
* infrared stars universe hubble
* antidepressant risk zoloft prozac
* zoloft studies prozac
* antidepressant effective zoloft
* cofferdams damming generating 2009
* dam corporation phase 2009
* 2009 river construction
Median AP across the 100 generated queries: 0.38
Generating high-quality
queries III
A collection of user studies
Piloting
User perception of
high-quality queries Main study:
Training size study
Generating
training
queries
You are given an information need and a query suggestion that has
been derived for this information need. Rate the suggestion along
four dimensions: knowledge, surprise, usage and relevance.
Identify positive accomplishments of the Hubble telescope
since it was launched in 1991.
universe astronomer faint hubble
Top 15 queries per topic.
Hit: 10 tasks, 12 cents.
3 workers per task.
task
User perception I
1 2 3 4 5
0
100
200
300
400
500
600
Rating
Numberofratings
How surprised were you?
Not
Very
1 2 3 4 5
0
200
400
600
800
Rating
Numberofratings
Would you use the suggestion?
No
Yes
1 2 3 4 5
0
200
400
600
800
Rating
Numberofratings
What will the quality
of the search results be?
Low
High
User perception II
1 2 3 4 5
0
100
200
300
400
500
600
Rating
Numberofratings
How surprised were you?
Not
Very
1 2 3 4 5
0
200
400
600
800
Rating
Numberofratings
Would you use the suggestion?
No
Yes
1 2 3 4 5
0
200
400
600
800
Rating
Numberofratings
What will the quality
of the search results be?
Low
High
User perception II
Indicates that our query
generation approach is valid.
Many of our suggestions are
not very convincing.
Expected search result
quality is mostly average.
• Familiar topics tend to be of broad interest
• Topics covering specific themes attract low
knowledge ratings



User perception III
What factors contributed to the growth of
consumer on-line shopping? (639) 3.0/5
Identify drugs used in the treatment of mental
illness. (383) 2.89/5
What is the status of The Three Gorges
Project? (416) 1.58/5
A collection of user studies
Piloting zing
User perception of
high-quality queries Main study:
Training size study
Generating
training
queries
A closer look at zing
How well am I doing?
Suggestions
(higher AP than
user queries)
after 2 initial
queries.
Relevant documents are
marked by the system
Piloting
• N=22 undergraduates
• 10 medium difficulty topics
• Randomized topic order
• Reflection prompts
When does fatigue set in?
By topic 7, median AP≈0
Query characteristics
81 reflections encoded
C1: Specific query terms
C2: More general query terms
C3: Queries not in topic description
C4: Unexpected or surprising vocab.
C5: Surprising non-use of vocab.
C6: Terms the user was surprised
at the usefulness of
C7: Thinking creatively
C8: Advanced vocabulary (rare)
C9: Specialist vocabulary (rare)
C10: Good combination of search terms
C11: Synonyms and related concepts
C12: Query requires specialist knowledgeUsers are able to identify salient characteristics of good queries.
A collection of user studies
Piloting
User perception of
high-quality queries Main study: zing
Training size study
Generating
training
queries
• Between-group design, N=91
• 6 medium difficulty topics
• Randomized topic order
• Training & test phase
Main study
Group Gexp_high
Trained on high-quality suggestions,
that were also perceived as high quality.
Group Gexp_low
Trained on high-quality suggestions,
that were perceived as low quality.
Group Gcontrol No training at any stage.
topic
+suggestions
topic
+suggestions
topictopic
+suggestions
topic
+suggestions
topic
topic topic topictopic topic topic
Main study: query effectiveness
Training topics Test topics
Users who receive high-quality training suggestions perform better
on average & achieve considerably higher max. AP scores.
Main study: query sequence
effectiveness
1 2 3 4 5 6 7 8 9 10
0
0.1
0.2
0.3
0.4
Query sequence
AveragePrecision
Control
Exp_High
Exp_Low
Average precision over sequences of queries
on test topics.
Each point represents the mean AP of
all queries submitted as nth query.
Gexp_high & Gexp_low significantly outperform Gcontrol.
No significant differences observed between Gexp_high & Gexp_low.
A collection of user studies
Piloting
User perception of
high-quality queries Main study: zing
Training size study
Generating
training
queries
Training size
study
• Between-group design, N=57
• Analogous setup to Main study
1 2 3 4 5 6 7 8 9 10
0
0.1
0.2
0.3
0.4
Query sequence
AveragePrecision
Control
Exp_High
Exp_Low
Main study:
4 training
&
2 test topics
1 2 3 4 5 6 7 8 9 10
0
0.1
0.2
0.3
0.4
Query sequence
AveragePrecision
Control
Exp_High
Exp_Low
Now:
2 training
&
4 test topics
Less training yields fewer (but still stat. significant) improvements.
Similarity between Gexp_high & Gexp_low remains stable.
Looking back at our
hypotheses
@flickr:carbonnyc
H1: Users can adapt their querying behaviour to pose good queries to
an unfamiliar search system.
H3: A small number of “training queries” are sufficient.
H4: A user who receives training with queries he can relate to, learns
better than a user who receives training with less-relatable queries.
H5: A user who receives training with queries he can relate to, learns
faster than a user who receives training with less-relatable queries.
H2: Users are able to identify salient characteristics of good queries.
• Learning is limited to a single session
• Does the learning effect hold across sessions and
over time?
• How to translate this approach (requiring qrels) into
settings where users are unwilling to train?
• Are implicit relevance indicators sufficient?
• What is the most efficient manner of presenting such
“learning queries” to users?
Looking ahead
@flickr:
Ideas, comments & suggestions
are more than welcome!
Thank you.
c.hauff@tudelft.nl

Mais conteúdo relacionado

Mais procurados

Internet - Based Research
Internet - Based ResearchInternet - Based Research
Internet - Based ResearchBEzz Zy
 
Internet - Based Research
Internet - Based ResearchInternet - Based Research
Internet - Based Researchbezzydale
 
Turning teaching initiatives into pedagogic publications
Turning teaching initiatives into pedagogic publicationsTurning teaching initiatives into pedagogic publications
Turning teaching initiatives into pedagogic publicationsChris Willmott
 
Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...
Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...
Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...Andrii Vozniuk
 
Laptops vs Desktops in a Google Groups environment
Laptops vs Desktops in a Google Groups environmentLaptops vs Desktops in a Google Groups environment
Laptops vs Desktops in a Google Groups environmentLuis Borges Gouveia
 
Online educa2010
Online educa2010Online educa2010
Online educa2010Jan M.
 
E-Learning in Newborn Health A paradigm shift in continuing professional deve...
E-Learning in Newborn HealthA paradigm shift in continuing professional deve...E-Learning in Newborn HealthA paradigm shift in continuing professional deve...
E-Learning in Newborn Health A paradigm shift in continuing professional deve...nisaiims
 
Content Controller: The easiest way to share content with your customers
Content Controller: The easiest way to share content with your customersContent Controller: The easiest way to share content with your customers
Content Controller: The easiest way to share content with your customersRustici Software
 
Sakai Experience from a Real Setting. (our) current ideas on how to explore ...
Sakai Experience from a Real Setting. (our) current ideas on how to explore ...Sakai Experience from a Real Setting. (our) current ideas on how to explore ...
Sakai Experience from a Real Setting. (our) current ideas on how to explore ...Luis Borges Gouveia
 
insight-centre-galway-learning-analytics
insight-centre-galway-learning-analyticsinsight-centre-galway-learning-analytics
insight-centre-galway-learning-analyticsSimon Buckingham Shum
 
Learning Analytics Community Exchange
Learning Analytics Community ExchangeLearning Analytics Community Exchange
Learning Analytics Community ExchangeDoug Clow
 
2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results
2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results
2017-04-25 IEEE EDUCON MOOQ Interactive Workshop ResultsChristian M. Stracke
 
What is the source of social capital? The association between social network ...
What is the source of social capital? The association between social network ...What is the source of social capital? The association between social network ...
What is the source of social capital? The association between social network ...Vitomir Kovanovic
 
EDUC5103G Week 10 Slides (S18)
EDUC5103G Week 10 Slides (S18)EDUC5103G Week 10 Slides (S18)
EDUC5103G Week 10 Slides (S18)Robert Power
 
Simulating learning networks in a higher education blogosphere – at scale
Simulating learning networks in a higher education blogosphere – at scaleSimulating learning networks in a higher education blogosphere – at scale
Simulating learning networks in a higher education blogosphere – at scalefridolin.wild
 

Mais procurados (18)

Virtual labs
Virtual labsVirtual labs
Virtual labs
 
Internet - Based Research
Internet - Based ResearchInternet - Based Research
Internet - Based Research
 
Internet - Based Research
Internet - Based ResearchInternet - Based Research
Internet - Based Research
 
Turning teaching initiatives into pedagogic publications
Turning teaching initiatives into pedagogic publicationsTurning teaching initiatives into pedagogic publications
Turning teaching initiatives into pedagogic publications
 
Acec2014 RALfieProject
Acec2014 RALfieProjectAcec2014 RALfieProject
Acec2014 RALfieProject
 
Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...
Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...
Towards portable learning analytics dashboards - Andrii Vozniuk, Sten Govaert...
 
Laptops vs Desktops in a Google Groups environment
Laptops vs Desktops in a Google Groups environmentLaptops vs Desktops in a Google Groups environment
Laptops vs Desktops in a Google Groups environment
 
Online educa2010
Online educa2010Online educa2010
Online educa2010
 
E-Learning in Newborn Health A paradigm shift in continuing professional deve...
E-Learning in Newborn HealthA paradigm shift in continuing professional deve...E-Learning in Newborn HealthA paradigm shift in continuing professional deve...
E-Learning in Newborn Health A paradigm shift in continuing professional deve...
 
Content Controller: The easiest way to share content with your customers
Content Controller: The easiest way to share content with your customersContent Controller: The easiest way to share content with your customers
Content Controller: The easiest way to share content with your customers
 
Sakai Experience from a Real Setting. (our) current ideas on how to explore ...
Sakai Experience from a Real Setting. (our) current ideas on how to explore ...Sakai Experience from a Real Setting. (our) current ideas on how to explore ...
Sakai Experience from a Real Setting. (our) current ideas on how to explore ...
 
insight-centre-galway-learning-analytics
insight-centre-galway-learning-analyticsinsight-centre-galway-learning-analytics
insight-centre-galway-learning-analytics
 
Learning Analytics Community Exchange
Learning Analytics Community ExchangeLearning Analytics Community Exchange
Learning Analytics Community Exchange
 
LTB Demo - Healthcare Evaluation
LTB Demo - Healthcare EvaluationLTB Demo - Healthcare Evaluation
LTB Demo - Healthcare Evaluation
 
2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results
2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results
2017-04-25 IEEE EDUCON MOOQ Interactive Workshop Results
 
What is the source of social capital? The association between social network ...
What is the source of social capital? The association between social network ...What is the source of social capital? The association between social network ...
What is the source of social capital? The association between social network ...
 
EDUC5103G Week 10 Slides (S18)
EDUC5103G Week 10 Slides (S18)EDUC5103G Week 10 Slides (S18)
EDUC5103G Week 10 Slides (S18)
 
Simulating learning networks in a higher education blogosphere – at scale
Simulating learning networks in a higher education blogosphere – at scaleSimulating learning networks in a higher education blogosphere – at scale
Simulating learning networks in a higher education blogosphere – at scale
 

Destaque

2015 hypertext-election prediction
2015 hypertext-election prediction2015 hypertext-election prediction
2015 hypertext-election predictionClaudia Hauff
 
janice mister cv_03.17
janice mister cv_03.17janice mister cv_03.17
janice mister cv_03.17Janice Mister
 
Dagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introductionDagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introductionClaudia Hauff
 
Tutorial on query auto-completion
Tutorial on query auto-completionTutorial on query auto-completion
Tutorial on query auto-completionYichen Feng
 
Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1Claudia Hauff
 
Big Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday LearningBig Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday LearningStefan Dietze
 
How to give a good 10min presentation
How to give a good 10min presentation How to give a good 10min presentation
How to give a good 10min presentation Jodie Martin
 

Destaque (7)

2015 hypertext-election prediction
2015 hypertext-election prediction2015 hypertext-election prediction
2015 hypertext-election prediction
 
janice mister cv_03.17
janice mister cv_03.17janice mister cv_03.17
janice mister cv_03.17
 
Dagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introductionDagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introduction
 
Tutorial on query auto-completion
Tutorial on query auto-completionTutorial on query auto-completion
Tutorial on query auto-completion
 
Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1
 
Big Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday LearningBig Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday Learning
 
How to give a good 10min presentation
How to give a good 10min presentation How to give a good 10min presentation
How to give a good 10min presentation
 

Semelhante a Learning by example: training users through high-quality query suggestions

Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Xavier Amatriain
 
ICELW Conference Slides
ICELW Conference SlidesICELW Conference Slides
ICELW Conference Slidestoolboc
 
[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation Systems[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation SystemsAxel de Romblay
 
See to believe: capturing insights using contextual inquiry
See to believe: capturing insights using contextual inquirySee to believe: capturing insights using contextual inquiry
See to believe: capturing insights using contextual inquiryDeirdre Costello
 
Udacity webinar on Recommendation Systems
Udacity webinar on Recommendation SystemsUdacity webinar on Recommendation Systems
Udacity webinar on Recommendation SystemsAxel de Romblay
 
Rinse and Repeat : The Spiral of Applied Machine Learning
Rinse and Repeat : The Spiral of Applied Machine LearningRinse and Repeat : The Spiral of Applied Machine Learning
Rinse and Repeat : The Spiral of Applied Machine LearningAnna Chaney
 
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.comHABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.comHABIB FIGA GUYE
 
Benchmarking search relevance in industry vs academia
Benchmarking search relevance in industry vs academiaBenchmarking search relevance in industry vs academia
Benchmarking search relevance in industry vs academiaNick Craswell
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learningShareDocView.com
 
2017 10-10 (netflix ml platform meetup) learning item and user representation...
2017 10-10 (netflix ml platform meetup) learning item and user representation...2017 10-10 (netflix ml platform meetup) learning item and user representation...
2017 10-10 (netflix ml platform meetup) learning item and user representation...Ed Chi
 
Machine Learning for Data Extraction
Machine Learning for Data ExtractionMachine Learning for Data Extraction
Machine Learning for Data ExtractionDasha Herrmannova
 
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.Carol Smith
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
 
Machine Learned Relevance at A Large Scale Search Engine
Machine Learned Relevance at A Large Scale Search EngineMachine Learned Relevance at A Large Scale Search Engine
Machine Learned Relevance at A Large Scale Search EngineSalford Systems
 
A flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TVA flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TVIntoTheMinds
 
A Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TVA Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TVFrancisco Couto
 

Semelhante a Learning by example: training users through high-quality query suggestions (20)

De carlo rizk 2010 icelw
De carlo rizk 2010 icelwDe carlo rizk 2010 icelw
De carlo rizk 2010 icelw
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
 
ICELW Conference Slides
ICELW Conference SlidesICELW Conference Slides
ICELW Conference Slides
 
Role of Data Science in eCommerce
Role of Data Science in eCommerceRole of Data Science in eCommerce
Role of Data Science in eCommerce
 
[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation Systems[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation Systems
 
See to believe: capturing insights using contextual inquiry
See to believe: capturing insights using contextual inquirySee to believe: capturing insights using contextual inquiry
See to believe: capturing insights using contextual inquiry
 
Udacity webinar on Recommendation Systems
Udacity webinar on Recommendation SystemsUdacity webinar on Recommendation Systems
Udacity webinar on Recommendation Systems
 
Rinse and Repeat : The Spiral of Applied Machine Learning
Rinse and Repeat : The Spiral of Applied Machine LearningRinse and Repeat : The Spiral of Applied Machine Learning
Rinse and Repeat : The Spiral of Applied Machine Learning
 
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.comHABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
 
Benchmarking search relevance in industry vs academia
Benchmarking search relevance in industry vs academiaBenchmarking search relevance in industry vs academia
Benchmarking search relevance in industry vs academia
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learning
 
2017 10-10 (netflix ml platform meetup) learning item and user representation...
2017 10-10 (netflix ml platform meetup) learning item and user representation...2017 10-10 (netflix ml platform meetup) learning item and user representation...
2017 10-10 (netflix ml platform meetup) learning item and user representation...
 
Deep learning for NLP
Deep learning for NLPDeep learning for NLP
Deep learning for NLP
 
Machine Learning for Data Extraction
Machine Learning for Data ExtractionMachine Learning for Data Extraction
Machine Learning for Data Extraction
 
My experiment
My experimentMy experiment
My experiment
 
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
Machine Learned Relevance at A Large Scale Search Engine
Machine Learned Relevance at A Large Scale Search EngineMachine Learned Relevance at A Large Scale Search Engine
Machine Learned Relevance at A Large Scale Search Engine
 
A flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TVA flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TV
 
A Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TVA Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TV
 

Último

FREE NURSING BUNDLE FOR NURSES.PDF by na
FREE NURSING BUNDLE FOR NURSES.PDF by naFREE NURSING BUNDLE FOR NURSES.PDF by na
FREE NURSING BUNDLE FOR NURSES.PDF by naJASISJULIANOELYNV
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRlizamodels9
 
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPirithiRaju
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxmalonesandreagweneth
 
The dark energy paradox leads to a new structure of spacetime.pptx
The dark energy paradox leads to a new structure of spacetime.pptxThe dark energy paradox leads to a new structure of spacetime.pptx
The dark energy paradox leads to a new structure of spacetime.pptxEran Akiva Sinbar
 
Harmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms PresentationHarmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms Presentationtahreemzahra82
 
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...Universidade Federal de Sergipe - UFS
 
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...navyadasi1992
 
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptxGenBio2 - Lesson 1 - Introduction to Genetics.pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptxBerniceCayabyab1
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxJorenAcuavera1
 
Davis plaque method.pptx recombinant DNA technology
Davis plaque method.pptx recombinant DNA technologyDavis plaque method.pptx recombinant DNA technology
Davis plaque method.pptx recombinant DNA technologycaarthichand2003
 
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXDole Philippines School
 
User Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationUser Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationColumbia Weather Systems
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxmaryFF1
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxpriyankatabhane
 
Dubai Calls Girl Lisa O525547819 Lexi Call Girls In Dubai
Dubai Calls Girl Lisa O525547819 Lexi Call Girls In DubaiDubai Calls Girl Lisa O525547819 Lexi Call Girls In Dubai
Dubai Calls Girl Lisa O525547819 Lexi Call Girls In Dubaikojalkojal131
 
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPirithiRaju
 
Environmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial BiosensorEnvironmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial Biosensorsonawaneprad
 

Último (20)

FREE NURSING BUNDLE FOR NURSES.PDF by na
FREE NURSING BUNDLE FOR NURSES.PDF by naFREE NURSING BUNDLE FOR NURSES.PDF by na
FREE NURSING BUNDLE FOR NURSES.PDF by na
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
 
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
 
The dark energy paradox leads to a new structure of spacetime.pptx
The dark energy paradox leads to a new structure of spacetime.pptxThe dark energy paradox leads to a new structure of spacetime.pptx
The dark energy paradox leads to a new structure of spacetime.pptx
 
Harmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms PresentationHarmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms Presentation
 
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
 
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...
 
Volatile Oils Pharmacognosy And Phytochemistry -I
Volatile Oils Pharmacognosy And Phytochemistry -IVolatile Oils Pharmacognosy And Phytochemistry -I
Volatile Oils Pharmacognosy And Phytochemistry -I
 
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptxGenBio2 - Lesson 1 - Introduction to Genetics.pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptx
 
Davis plaque method.pptx recombinant DNA technology
Davis plaque method.pptx recombinant DNA technologyDavis plaque method.pptx recombinant DNA technology
Davis plaque method.pptx recombinant DNA technology
 
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
 
User Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationUser Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather Station
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
 
Dubai Calls Girl Lisa O525547819 Lexi Call Girls In Dubai
Dubai Calls Girl Lisa O525547819 Lexi Call Girls In DubaiDubai Calls Girl Lisa O525547819 Lexi Call Girls In Dubai
Dubai Calls Girl Lisa O525547819 Lexi Call Girls In Dubai
 
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
 
Environmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial BiosensorEnvironmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial Biosensor
 

Learning by example: training users through high-quality query suggestions

  • 1. Learning by Example: training users through high-quality query suggestions (SIGIR’15) A collaboration with Morgan Harvey & David Elsweiler. Claudia Hauff Web Information Systems
  • 2. 0 50,000,000 100,000,000 150,000,000 200,000,000 250,000,000 300,000,000 350,000,000 Sep*12 Apr*13 Oct*13 May*14 Dec*14 Jun*15 Jan*16 Data available at https://duckduckgo.com/traffic.html NSA collecting phone records of millions of Verizon customers daily. The Guardian. June 6, 2013. Not everyone stays around.
  • 3. I do care about privacy … until the moment my searches fail me. @flickr:eviloars Can we teach searchers to use an arbitrary search engine as best as possible?
  • 4. @flickr:practicalowl Advanced retrieval algorithms; queries as a given. Assisting users in creating better queries. query suggestions related searches query autocompletion Personalised & context-driven search. Educate users to become better searchers.Educate users to become better searchers. complimentary to technical solutions system specific
  • 5. • Altering the size [Franzen & Karlgren, 2000] and wording [Belkin et al., 2003] of the search box influences the length of submitted queries • Exchanging a complex multi-field catalogue interface for a simple search box radically alters user behaviour [McKay & Buchanan, 2013] • Training users how to construct boolean logic queries can change search behaviour [Lucas & Topi, 2004] • Allowing users to compare their search behaviour to expert searchers enables them to reflect and change their habits [Bateman et al., 2012] deeper in the results list [6]. Behaviour change support systems “… information systems designed to form, alter, or reinforce attitudes or behaviours or both without using coercion or deception” [Oinas-Kukkonen & Harjumaa, 2008]
  • 7. Our questions Are users able to notice differences between good queries and their own? Can they abstract these differences to change their own behaviour? How effectively can users learn and abstract from good queries? Do users who are “trained” perform better than users who did not receive training? @flickr:eviloars
  • 8. Our hypotheses @flickr:carbonnyc H1: Users can adapt their querying behaviour to pose good queries to an unfamiliar search system. H3: A small number of “training queries” are sufficient. H4: A user who receives training with queries he can relate to, learns better than a user who receives training with less-relatable queries. H5: A user who receives training with queries he can relate to, learns faster than a user who receives training with less-relatable queries. H2: Users are able to identify salient characteristics of good queries.
  • 9. A collection of user studies Piloting zing User perception of high-quality queries Main study: zing Training size study Generating training queries All studies are based on AQUAINT and the TREC 2005 Robust track topics.
  • 10. • Query quality is measured in Average Precision • The queries should intuitively make sense to humans (instead of relying on quirks in documents) • The queries should not be overly verbose or specific Generating high-quality queries I
  • 11. for each TREC topic relevant documents 100 single-term queries AQUAINT Hand-crafted filtering rules to avoid unintuitive term selection. Generating high-quality queries II
  • 12. for each TREC topic relevant documents AQUAINT AP-based query ranking top two-term queries Hand-crafted filtering rules to avoid unintuitive term selection. Generating high-quality queries II
  • 13. for each TREC topic relevant documents AQUAINT AP-based query ranking 3x : top 100 queries up to length 4 Hand-crafted filtering rules to avoid unintuitive term selection. Generating high-quality queries II
  • 14. Identify positive accomplishments of the Hubble telescope since it was launched in 1991. (303) Identify drugs used in the treatment of mental illness. (383) What is the status of The Three Gorges Project? (416) * universe astronomer faint hubble * infrared galaxies universe hubble * infrared stars universe hubble * antidepressant risk zoloft prozac * zoloft studies prozac * antidepressant effective zoloft * cofferdams damming generating 2009 * dam corporation phase 2009 * 2009 river construction Median AP across the 100 generated queries: 0.38 Generating high-quality queries III
  • 15. A collection of user studies Piloting User perception of high-quality queries Main study: Training size study Generating training queries
  • 16. You are given an information need and a query suggestion that has been derived for this information need. Rate the suggestion along four dimensions: knowledge, surprise, usage and relevance. Identify positive accomplishments of the Hubble telescope since it was launched in 1991. universe astronomer faint hubble Top 15 queries per topic. Hit: 10 tasks, 12 cents. 3 workers per task. task User perception I
  • 17. 1 2 3 4 5 0 100 200 300 400 500 600 Rating Numberofratings How surprised were you? Not Very 1 2 3 4 5 0 200 400 600 800 Rating Numberofratings Would you use the suggestion? No Yes 1 2 3 4 5 0 200 400 600 800 Rating Numberofratings What will the quality of the search results be? Low High User perception II
  • 18. 1 2 3 4 5 0 100 200 300 400 500 600 Rating Numberofratings How surprised were you? Not Very 1 2 3 4 5 0 200 400 600 800 Rating Numberofratings Would you use the suggestion? No Yes 1 2 3 4 5 0 200 400 600 800 Rating Numberofratings What will the quality of the search results be? Low High User perception II Indicates that our query generation approach is valid. Many of our suggestions are not very convincing. Expected search result quality is mostly average.
  • 19. • Familiar topics tend to be of broad interest • Topics covering specific themes attract low knowledge ratings
 
 User perception III What factors contributed to the growth of consumer on-line shopping? (639) 3.0/5 Identify drugs used in the treatment of mental illness. (383) 2.89/5 What is the status of The Three Gorges Project? (416) 1.58/5
  • 20. A collection of user studies Piloting zing User perception of high-quality queries Main study: Training size study Generating training queries
  • 21. A closer look at zing How well am I doing? Suggestions (higher AP than user queries) after 2 initial queries. Relevant documents are marked by the system
  • 22. Piloting • N=22 undergraduates • 10 medium difficulty topics • Randomized topic order • Reflection prompts When does fatigue set in? By topic 7, median AP≈0 Query characteristics 81 reflections encoded C1: Specific query terms C2: More general query terms C3: Queries not in topic description C4: Unexpected or surprising vocab. C5: Surprising non-use of vocab. C6: Terms the user was surprised at the usefulness of C7: Thinking creatively C8: Advanced vocabulary (rare) C9: Specialist vocabulary (rare) C10: Good combination of search terms C11: Synonyms and related concepts C12: Query requires specialist knowledgeUsers are able to identify salient characteristics of good queries.
  • 23. A collection of user studies Piloting User perception of high-quality queries Main study: zing Training size study Generating training queries
  • 24. • Between-group design, N=91 • 6 medium difficulty topics • Randomized topic order • Training & test phase Main study Group Gexp_high Trained on high-quality suggestions, that were also perceived as high quality. Group Gexp_low Trained on high-quality suggestions, that were perceived as low quality. Group Gcontrol No training at any stage. topic +suggestions topic +suggestions topictopic +suggestions topic +suggestions topic topic topic topictopic topic topic
  • 25. Main study: query effectiveness Training topics Test topics Users who receive high-quality training suggestions perform better on average & achieve considerably higher max. AP scores.
  • 26. Main study: query sequence effectiveness 1 2 3 4 5 6 7 8 9 10 0 0.1 0.2 0.3 0.4 Query sequence AveragePrecision Control Exp_High Exp_Low Average precision over sequences of queries on test topics. Each point represents the mean AP of all queries submitted as nth query. Gexp_high & Gexp_low significantly outperform Gcontrol. No significant differences observed between Gexp_high & Gexp_low.
  • 27. A collection of user studies Piloting User perception of high-quality queries Main study: zing Training size study Generating training queries
  • 28. Training size study • Between-group design, N=57 • Analogous setup to Main study 1 2 3 4 5 6 7 8 9 10 0 0.1 0.2 0.3 0.4 Query sequence AveragePrecision Control Exp_High Exp_Low Main study: 4 training & 2 test topics 1 2 3 4 5 6 7 8 9 10 0 0.1 0.2 0.3 0.4 Query sequence AveragePrecision Control Exp_High Exp_Low Now: 2 training & 4 test topics Less training yields fewer (but still stat. significant) improvements. Similarity between Gexp_high & Gexp_low remains stable.
  • 29. Looking back at our hypotheses @flickr:carbonnyc H1: Users can adapt their querying behaviour to pose good queries to an unfamiliar search system. H3: A small number of “training queries” are sufficient. H4: A user who receives training with queries he can relate to, learns better than a user who receives training with less-relatable queries. H5: A user who receives training with queries he can relate to, learns faster than a user who receives training with less-relatable queries. H2: Users are able to identify salient characteristics of good queries.
  • 30. • Learning is limited to a single session • Does the learning effect hold across sessions and over time? • How to translate this approach (requiring qrels) into settings where users are unwilling to train? • Are implicit relevance indicators sufficient? • What is the most efficient manner of presenting such “learning queries” to users? Looking ahead @flickr:
  • 31. Ideas, comments & suggestions are more than welcome! Thank you. c.hauff@tudelft.nl