Interactivity and feedback         Gene Golovchinsky       FX Palo Alto Laboratory           @HCIR_GeneG    Thanks to Tony...
A half-assed analogy    A trivial taxonomySome self-serving examples
What I mean by “task” Information            Multiple               Evolvingseeking occurs        interactions           i...
Two kinds of feedbackPerson System     Person trains system to find documentsSystem  Person     System indicates possibi...
Person  SystemPeople don’t use relevance feedback, right?They do when suitably motivated.Two examples:  Ancestry.com  Pre...
Relevance feedback at Ancestry.comSearch  People find historical records about specific individuals  Facts from records ar...
Relevance Feedback in                Predictive CodingPredictive coding is a technique for training a classifier to findre...
System  PersonSystem provides hints about potential actions  Information scent  Which documents are new  Which terms are ...
Interacting with the pastPreviouslysavedrecords forthis person                       Ancestry.com                         ...
Interacting with the past                               Newly-                               retrieved                    ...
Interacting with the present                                                   mspaceCommerical faceted browsing UI       ...
Interacting with the future                       System  Person
Interacting with the futureQuery preview                 Query nudgesAs searcher types, shows      As searcher types, chan...
Design ChallengesHow do we get people to userelevance feedback?How do we help people discoverwhich queries will be effecti...
Interactivity and feedback
Interactivity and feedback
Interactivity and feedback
Interactivity and feedback
Interactivity and feedback
Interactivity and feedback
Upcoming SlideShare
Loading in …5
×

Interactivity and feedback

924 views

Published on

Slides given at the NSF-sponsored workshop on task-based search at UNC

Published in: Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
924
On SlideShare
0
From Embeds
0
Number of Embeds
85
Actions
Shares
0
Downloads
0
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Interactivity and feedback

  1. 1. Interactivity and feedback Gene Golovchinsky FX Palo Alto Laboratory @HCIR_GeneG Thanks to Tony Dunnigan for the drawings
  2. 2. A half-assed analogy A trivial taxonomySome self-serving examples
  3. 3. What I mean by “task” Information Multiple Evolvingseeking occurs interactions information over time with the system needs Human Computer
  4. 4. Two kinds of feedbackPerson System Person trains system to find documentsSystem  Person System indicates possibilities to guide person
  5. 5. Person  SystemPeople don’t use relevance feedback, right?They do when suitably motivated.Two examples: Ancestry.com Predictive coding
  6. 6. Relevance feedback at Ancestry.comSearch People find historical records about specific individuals Facts from records are saved to individuals in family treesRelevance feedback Saved facts are automatically incorporated into subsequent queries Relevance feedback is inferred from saved recordsMany motivated users Hundreds of hours of system use Lots of interaction Person  System
  7. 7. Relevance Feedback in Predictive CodingPredictive coding is a technique for training a classifier to findrelevant documentsUsed in e-discovery to increase accuracy and reduce costsMachine learning algorithm is trained through hundreds ofrelevance judgments; applied to millions of documentsBig (and getting bigger) business Person  System
  8. 8. System  PersonSystem provides hints about potential actions Information scent Which documents are new Which terms are effective Ways to expand/reformulate the queryExamples Facets indicating numbers of matching documents Previously-saved or viewed documents History of queries, related queries Previews, hints, etc.
  9. 9. Interacting with the pastPreviouslysavedrecords forthis person Ancestry.com System  Person
  10. 10. Interacting with the past Newly- retrieved Re-retrieved Querium System  Person
  11. 11. Interacting with the present mspaceCommerical faceted browsing UI RelationBrowser
  12. 12. Interacting with the future System  Person
  13. 13. Interacting with the futureQuery preview Query nudgesAs searcher types, shows As searcher types, changesdistribution of new vs. re- halo color to encourage longerretrieved documents in a queriessearch session 7 6 5 Number of Query Terms 4 3 2 No instr. 1 0 Instruction No halo System  Person Halo
  14. 14. Design ChallengesHow do we get people to userelevance feedback?How do we help people discoverwhich queries will be effective?How do we help people plan?

×