A Human in the Loop Approach to Capture Bias and Support Media Scientists in News Video Analysis
Files
Publication date
2018
Authors
Jong, Markus de
Mavridis, Panagiotis
Aroyo, Lora
Bozzon, Alessandro
Vos, Jesse de
Oomen, Johan
Dimitrova, Antoaneta
Badenoch, Alec
Editors
Advisors
Supervisors
DOI
Document Type
Part of book
Metadata
Show full item recordCollections
License
Abstract
Bias is inevitable and inherent in any form of communication. News often appear biased to citizens with different political orientations, and understood differently by news media scholars and the broader public. In this paper we advocate the need for accurate methods for bias identification in video news item, to enable rich analytics capabilities in order to assist humanities media scholars and social political scientists. We propose to analyze biases that are typical in video news (including framing, gender and racial biases) by means of a human-in-the-loop approach that combines text and image analysis with human computation techniques.
Keywords
Bias detection, bias in news video files, machine learning, crowdsourcing, human computation, human in the loop, digital humanities, Arts and Humanities (miscellaneous), General Computer Science
Citation
Jong, M D, Mavridis, P, Aroyo, L, Bozzon, A, Vos, J D, Oomen, J, Dimitrova, A & Badenoch, A 2018, A Human in the Loop Approach to Capture Bias and Support Media Scientists in News Video Analysis. in Joint Proceedings SAD 2018 and CrowdBias 2018. vol. 2276, Zurich, pp. 32-40. < http://ceur-ws.org/Vol-2276/paper11.pdf >