The article The Impact of Image Descriptions on User Tagging Behavior: A Study of the Nature and Functionality of Crowdsourced Tags that was co-authored by Christoph Trattner (Know-Center), has been published in the renowned renommierten Journal of the Association for Information Science and Technology (JASIST).
The article investigates which impacts Image Description have on socially generated annotations. The study has been conducted with the Carnegie Museum of Art and is especially relevant for curators of digital libraries. They often face the problem of annotating a vast amount of images manually in order to make them searchable. The application of Amazon Mechanical Turk shows how this process can be significantly accelerated and which impacts primaries, such as image description have on the annotation process.
Read the full article here.