Foundations and Trends® in Web Science > Vol 7 > Issue 1

An Introduction to Hybrid Human-Machine Information Systems

Gianluca Demartini, University of Queensland, Australia, g.demartini@uq.edu.au Djellel Eddine Difallah, Center for Data Science, New York University, USA, djellel@nyu.edu Ujwal Gadiraju, L3S Research Center, Leibniz Universität Hannover, Germany, gadiraju@L3S.de Michele Catasta, Stanford University, USA, pirroh@cs.stanford.edu
 
Suggested Citation
Gianluca Demartini, Djellel Eddine Difallah, Ujwal Gadiraju and Michele Catasta (2017), "An Introduction to Hybrid Human-Machine Information Systems", Foundations and TrendsĀ® in Web Science: Vol. 7: No. 1, pp 1-87. http://dx.doi.org/10.1561/1800000025

Published: 20 Dec 2017
© 2017 G. Demartini, D. E. Difallah, U. Gadiraju and M. Catasta
 
Subjects
Agents and the Semantic Web,  Collective Intelligence,  Data Mining,  Databases on the Web,  Hypertext/Hypermedia,  Search,  Semantic Web,  User Interfaces,  Web search,  Text mining,  Evaluation issues and test collections for IR,  Data Integration and Exchange
 

Free Preview:

Article Help

Share

Download article
In this article:
1. Crowdsourcing and Human Computation
2. Hybrid Systems for Databases
3. Hybrid Systems for Information Retrieval
4. Hybrid Systems for Natural Language Processing
5. Hybrid Systems for Semantic Web
6. Hybrid Systems for Machine Learning
7. Hybrid Systems for Multimedia Processing
8. Discussion and Research Directions
Acknowledgements
References

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.

DOI:10.1561/1800000025
ISBN: 978-1-68083-374-4
106 pp. $75.00
Buy book
 
ISBN: 978-1-68083-375-1
106 pp. $135.00
Buy E-book
Table of contents:
1. Crowdsourcing and Human Computation
2. Hybrid Systems for Databases
3. Hybrid Systems for Information Retrieval
4. Hybrid Systems for Natural Language Processing
5. Hybrid Systems for Semantic Web
6. Hybrid Systems for Machine Learning
7. Hybrid Systems for Multimedia Processing
8. Discussion and Research Directions
Acknowledgements
References

An Introduction to Hybrid Human-Machine Information Systems

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.

This monograph introduces 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, it discusses current research directions, opportunities for the future development of such systems and their application in practice.

 
WEB-025