Crowdsourcing image descriptions using gamification: a comparison between game- generated labels and professional descriptors

The traditional approach to achieve high metadata quality in image description is to use subject experts. However, cultural heritage institutions often lack the human resources to handle the amount of material that is in need of description. One of the possible solutions to this problem is applying the gamification approach in the process of description. Many studies have shown that applying game design features outside traditional game environments can increase the motivation and productivity, and that those games can be particularly effective in invoking intrinsic motivations and overall enjoyment. However, there is a need to explore the quality of such game- generated tags in comparison with using controlled vocabularies and traditional approaches. In this paper, we compare game-generated image labels and professional descriptors. First, a subject expert using controlled vocabulary added descriptors for each image. Then, by using a gamified platform for collecting semantic annotations of digitized images, game- generated tags were collected. In the final stage, game-generated labels were evaluated by the subject expert in the context of appropriateness of using them as descriptors within a standardized system. Results have shown that game-generated labels can serve as a basis for high quality labels suitable for including a standardized description in order to enhance description and retrieval