answering complex location-based queries with crowdsourcing

26
ANSWERING COMPLEX LOCATION-BASED QUERIES WITH CROWDSOURCING Karim Benouaret Raman Valliyur-Ramalingam, François Charoy Inria – Université de Lorraine – CNRS LORIA Service and Cooperation Team

Upload: francois-charoy

Post on 17-Jun-2015

344 views

Category:

Technology


2 download

DESCRIPTION

CollaborateCom 2013 presentation

TRANSCRIPT

Page 1: Answering Complex Location-Based Queries with Crowdsourcing

ANSWERING COMPLEX LOCATION-BASED QUERIES WITH CROWDSOURCINGKarim Benouaret

Raman Valliyur-Ramalingam,

François Charoy

Inria – Université de Lorraine – CNRS

LORIA

Service and Cooperation Team

Page 2: Answering Complex Location-Based Queries with Crowdsourcing
Page 3: Answering Complex Location-Based Queries with Crowdsourcing

Nancy

Page 4: Answering Complex Location-Based Queries with Crowdsourcing

?

Page 5: Answering Complex Location-Based Queries with Crowdsourcing
Page 6: Answering Complex Location-Based Queries with Crowdsourcing

Ask the crowd to contribute

Page 7: Answering Complex Location-Based Queries with Crowdsourcing

How to do that Cost Effectively ?

• Express the problem (the query)• Transform it in something executable• Manage the execution• Evaluate the result

Page 8: Answering Complex Location-Based Queries with Crowdsourcing

A Query• <

Object=roads, Context=need repair, Location=Nancy, Assessment = {not damaged, damaged, very

damaged}, Start Date = 10/19/2013, End Date = 10/25/2013, Strategy=Deadline

>

Page 9: Answering Complex Location-Based Queries with Crowdsourcing

Collect

Page 10: Answering Complex Location-Based Queries with Crowdsourcing

Clustering

Page 11: Answering Complex Location-Based Queries with Crowdsourcing

Select

Page 12: Answering Complex Location-Based Queries with Crowdsourcing

Assess

Page 13: Answering Complex Location-Based Queries with Crowdsourcing

A Process• 3 crowdsourcing activities

Page 14: Answering Complex Location-Based Queries with Crowdsourcing

Strategies

• Deadline• One after the other

• Buffer• Start the voting activities

when k photo are available

• FIFO• Start the voting activity

as soon as a data is available

• Wait for k/2 vote

C S A

C

S

A

C

S

A

Page 15: Answering Complex Location-Based Queries with Crowdsourcing

Experimentation• Understand the behavior of each strategy

• Subset of the Gowalla Data Set• Checkins at different places

• The ground truth is generated• Participants have a probability to give a wrong answer.• Variable

• Number of days of the experiment• Number of votes required for each place and photo (k) to be

selected

Page 16: Answering Complex Location-Based Queries with Crowdsourcing

Number of results vs Number of days

Page 17: Answering Complex Location-Based Queries with Crowdsourcing

Evolution of the number of results

Page 18: Answering Complex Location-Based Queries with Crowdsourcing

Quality vs Duration

Page 19: Answering Complex Location-Based Queries with Crowdsourcing

Quality vs Number of vote

Page 20: Answering Complex Location-Based Queries with Crowdsourcing

Conclusion• Promising Preliminary results• Interpretation of context aware crowdsourcing queries

requires more work• Crowdsourcing process orchestration is difficult

• Large scale• Not sequential ?

• Different strategies lead to different results• Quality vs number of results

• The problem of evaluation is an issue

Page 21: Answering Complex Location-Based Queries with Crowdsourcing

Current work• Implementation of the process on a real BPM Systems• Deployment on AWS EC2 and S3• Prepare experimentation with the Lorraine Smart City

Living Lab

Page 22: Answering Complex Location-Based Queries with Crowdsourcing

Questions ?

Page 23: Answering Complex Location-Based Queries with Crowdsourcing

Current Structure of the system

Orchestration Engine

Data Production

Crowd Management

Service

Data Quality Service

Network serviceMobile app

serviceTask

Management

Page 24: Answering Complex Location-Based Queries with Crowdsourcing

Collection

Page 25: Answering Complex Location-Based Queries with Crowdsourcing

Selection

Page 26: Answering Complex Location-Based Queries with Crowdsourcing

Assessment