|
|
|
|
|
An Introduction to Hybrid Human-Machine Information Systems
Author(s): Gianluca Demartini;Djellel Eddine Difallah;Ujwal Gadiraju;Michele Catasta
Source: Journal:Foundations and Trends® in Web Science ISSN Print:1555-077X, ISSN Online:1555-0788 Publisher:Now Publishers Volume 7 Number 1, Pages: 91 (1-87) DOI: 10.1561/1800000025
Abstract:
Hybrid Human-Machine Information Systems leverage novel architectures
that make systematic use of Human Computation by means of
crowdsourcing. These architectures are capable of scaling over large
amounts of data and simultaneously maintain high-quality data processing
levels by introducing humans into the loop. Such hybrid systems
have been developed to tackle a variety of problems and come with
inter-disciplinary challenges. They need to deal with the full spectrum
of challenges from the social science standpoint, such as understanding
crowd workers behavior and motivations when performing tasks.
These systems also need to overcome highly technical challenges like
constraint optimization and resource allocation based on limited budgets
and deadlines to be met.
In this paper, we introduce the area of Human Computation and
present an overview of different applications for which Hybrid Human-
Machine Information Systems have already been used in the realms of
data management, information retrieval, natural language processing,
semantic web, machine learning, and multimedia to better solve existing
problems. Finally, we discuss current research directions, opportunities
for the future development of such systems and their application
in practice.
|
|
|
|