G
Gianluca Demartini
Researcher at University of Queensland
Publications - 188
Citations - 3883
Gianluca Demartini is an academic researcher from University of Queensland. The author has contributed to research in topics: Crowdsourcing & Computer science. The author has an hindex of 27, co-authored 156 publications receiving 3169 citations. Previous affiliations of Gianluca Demartini include University of California, Berkeley & Leibniz University of Hanover.
Papers
More filters
Proceedings ArticleDOI
ZenCrowd: leveraging probabilistic reasoning and crowdsourcing techniques for large-scale entity linking
TL;DR: A probabilistic framework to make sensible decisions about candidate links and to identify unreliable human workers is developed and developed to improve the quality of the links while limiting the amount of work performed by the crowd.
Proceedings ArticleDOI
Understanding Malicious Behavior in Crowdsourcing Platforms: The Case of Online Surveys
TL;DR: The prevalent malicious activity on crowdsourcing platforms is analyzed and different types of workers in the crowd are defined, a method to measure malicious activity is proposed, and guidelines for the efficient design of crowdsourced surveys are presented.
Proceedings ArticleDOI
Pick-a-crowd: tell me what you like, and i'll tell you what to do
TL;DR: This paper proposes and extensively evaluate a different Crowdsourcing approach based on a push methodology that carefully selects which workers should perform a given task based on worker profiles extracted from social networks and shows that this approach consistently yield better results than usual pull strategies.
Proceedings ArticleDOI
The Dynamics of Micro-Task Crowdsourcing: The Case of Amazon MTurk
Djellel Eddine Difallah,Michele Catasta,Gianluca Demartini,Panagiotis G. Ipeirotis,Philippe Cudré-Mauroux +4 more
TL;DR: This paper uses the main findings of the five year log analysis to propose features used in a predictive model aiming at determining the expected performance of any batch at a specific point in time, and shows that the number of tasks left in a batch and how recent the batch is are two key features of the prediction.
Book ChapterDOI
Overview of the INEX 2009 entity ranking track
TL;DR: The XER tasks and the evaluation procedure used at the XER track in 2009, where a new version of Wikipedia was used as underlying collection are described; and the approaches adopted by the participants are summarized.