Hippocampus: Answering Memory Queries using Transactive Search

606 views
409 views

Published on

Published in: Internet
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
606
On SlideShare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
4
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Hippocampus: Answering Memory Queries using Transactive Search

  1. 1. Hippocampus: Answering Memory Queries using Transactive Search Michele @pirroh Catasta Alberto Tonon, Djellel Eddine Difallah, Gianluca Demartini, Karl Aberer, and Philippe Cudre-Mauroux 1
  2. 2. 2 “A transactive memory system is a mechanism through which groups collectively encode, store, and retrieve knowledge.” “[…] a memory system that is more complex and potentially more effective than that of any of its individual constituents.” A transactive search system discovers and aggregates the information stored in a transactive memory. Wikipedia Wikipedia
  3. 3. –Daniel M. Wegner “[…] it is a property of a group. This unique quality of transactive memory brings with it the realization that we are speaking of a constructed system, a mode of group operation that is built up over time by its individual constituents.” 3
  4. 4. 4 INFORMATION NEED reconstruct the attendees’ list of the 86th Academy Awards (2014)
  5. 5. 5
  6. 6. 6
  7. 7. MISTAKES: not all the nominees participate to the ceremony PRECISION :-( ! ! ! MISSING ENTRIES: what about all the people working “behind the scenes”? RECALL :-( 7
  8. 8. FROM THE IDEA… • for data that is stored in the memories of a group of people, the current query strategies are suboptimal • we need a new form of human computation, different from standard crowdsourcing (i.e., no anonymous crowd) 8 Navigational: The immediate intent is to reach a particular Web site. Informational: The intent is to acquire some information assumed to be present on one or more Web pages. Transactional: The intent is to perform some Webmediated activity. Transactive: The intent is to acquire some information that can be reconstructed only by an [ephemeral] social network. “A taxonomy of Web Search” — A. Broder (2002)
  9. 9. …TO THE TESTING ENVIRONMENT • We want to reconstruct the attendees list of two Semantic Web conferences, ISWC2012 and ISWC2013 ! • We were given access to the ground truth but, in general, such lists are not publicly available ! • Additional data sources: authors list (first author, last author, etc.), mentions in Online Social Networks 9
  10. 10. 10
  11. 11. EXPERIMENT ARCHITECTURE • tailored Web UI + results aggregator • iterative reconstruction: every time a new person was mentioned, Hippocampus sent her an invitation to contribute to the attendees list
 11 Hippocampus ! ! ! discovery (Web UI + messaging) results aggregator storage layer
  12. 12. MACHINE LEARNING APPROACHES • we collected the proceedings information and all the tweets with the conference hashtags • we trained state-of-the-art classifiers with these features: 12 not possible without the ground truth!
  13. 13. ML + CROWDSOURCING APPROACHES • Uncertain cases (precision): we asked the crowd to revise the low-confidence results of the ML classifier.
 (e.g., people that didn’t attend the conference but tweeted about it) • Unseen cases (recall): we asked the crowd to actively look for attendees not included in the authors list (e.g., organizers mentioned in the Web site) 13 the crowd has access only to public data on the Web!
  14. 14. Transactive vs ML & Crowdsourcing ISWC 2013 14 Authors and Tweets: baseline (exhaustive list of authors and twitterers) Machine Learning: SVM, M5P Regression Machine Learning + Crowdsourcing: Hybrid_(uncertain, unseen, uncertain_unseen)
  15. 15. attendees found over time Transactive Search 0" 50" 100" 150" 200" 250" 300" 350" 400" 450" 10(Dec" 11(Dec" 12(Dec" 13(Dec" 14(Dec" 15(Dec" 16(Dec" Retrieved(Results( Day( Retrieved"A4endees"2012" Duplicates"Names"2012" Retrieved"A4endees"2013" Duplicates"Names"2013" 15
  16. 16. Transactive Memory Graph in green, two isolated “components” discovered by top-contributors 16
  17. 17. CONCLUSIONS • for a specific class of queries, our Transactive Search performs up to 46% better than the best alternative approach (i.e., Machine Learning + Crowdsourcing) ! • we will explore incentives for Hippocampus, as it is currently two orders of magnitude slower than the alternative approaches • we reported some initial evidences that, as human memories fade with time, our approach works best with recent events 17

×