slide1
Download
Skip this Video
Download Presentation
U C L

Loading in 2 Seconds...

play fullscreen
1 / 42

U C L - PowerPoint PPT Presentation


  • 123 Views
  • Uploaded on

Inter-Context Trust Bootstrapping for Mobile Content Sharing (daniele quercia) (stephen hailes & licia capra). U C L. What do I do?. Research @. what I research?. Reputation Systems for Mobiles. What’s that?. Example: antique markets. Problem: Visitors cannot see prices of everything!.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' U C L' - paki-garrett


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
slide1

Inter-Context Trust Bootstrappingfor Mobile Content Sharing(daniele quercia)(stephen hailes & licia capra)

UCL

slide13

Daniele Quercia

Trust model on A:how A decideswhether to rely on Bto visit a stall

slide14

Daniele Quercia

To decide whether to rely on B, A has to

set its initial trust in B

slide15

3 Existing Solutions

Daniele Quercia

slide16

Daniele Quercia

  • 1. Fixed values
  • ( over-simplified)
slide17

Daniele Quercia

  • 2. Recommendations
  • ( fake ones)
slide18

3. Similar contexts

  • ( universal ontology)

Daniele Quercia

slide19

Daniele Quercia

Two cases: B is

1. unknown

2. partly known

slide20

Daniele Quercia

  • 1. B is unknown
slide21

Daniele Quercia

  • Popular way:
  • Trust propagation (transitivity)

C

?

A

B

slide22

Daniele Quercia

  • Meant for the Web &

Proved on “binary” ratings

slide23

Algorithm rating

  • unrated trust relationships (needed)

Daniele Quercia

  • unrated nodes (chosen)

?

AB

AC

CB

1

2

C

1

2

?

A

B

slide24

?

  • Idea:
    • 1. Similar nodes together
    • 2. Find function:
    • same ratings for rated nodes
    • similar ratings for neighbours
slide25

Daniele Quercia

  • Tested on real data
  • (Advogato: > 55K user ratings)
slide26

Daniele Quercia

  • 2. B is partly known
slide27

Daniele Quercia

Popular way:

Inter-context Lifting 

Antiques

Coins

Chairs

Roman Coins

Greek Coins

slide28

Idea: Users …

    • > Don’t share ontology
    • > Extract “features”
    • from their own ratings

Daniele Quercia

slide29

Idea: Users …

    • > Don’t share ontology
    • > Extract “features”
    • from their own ratings

Daniele Quercia

slide30

Daniele Quercia

  • How to extract?
slide31

Daniele Quercia

  • Singular
    • Value
    • Decomposition
slide32

Beauty: features

  • not user-specified
  • BUT learnt

Daniele Quercia

slide34

Daniele Quercia

  • Tested on Nokia 3230
  • Max: 3.2 ms !
slide35

Daniele Quercia

  • What I’ve told you is on
  • “mobblog UCL” (google it)
  • under tag: “bootstrapping”
slide37

Daniele Quercia

  • And User Privacy?
slide38

Daniele Quercia

  • Private filtering
  • (Google for “mobblog private filtering”)
slide39

Daniele Quercia

  • And Resource Discovery?
slide40

Daniele Quercia

  • Folksonomy for mobiles 
slide41

Daniele Quercia

  • And Attacks?
slide42

Daniele Quercia

Further Research

(join mobblog !)

ad