Interesting new research from the Journal of the American Society for Information Science and Technology that grew out of another recent study of classifying (tagging) music by its evocative response. I liked the addition of using sliders as a means to measure intensity of the response.
It’s worth a click-through to the full-text (Cal Poly only) for a look at the sample images from Flickr accompanied by tables detailing the responses. The authors bring up some of the interesting challenges with measuring subjective response and with folksonomies in general, as well as the potential application of such a system not only to images but to other media that affect an emotional response.
Collective indexing of emotions in images. A study in emotional information retrieval
Stefanie Schmidt, Wolfgang G. Stock
Heinrich-Heine-University Düsseldorf, Dept. for Information Science, Universitätsstr. 1, D-40225 Düsseldorf, Germany
email: Stefanie Schmidt (email@example.com) Wolfgang G. Stock (firstname.lastname@example.org)
affect • image indexing • image retrieval • informal classification schemes • image information systems
Some documents provoke emotions in people viewing them. Will it be possible to describe emotions consistently and use this information in retrieval systems? We tested collective (statistically aggregated) emotion indexing using images as examples. Considering psychological results, basic emotions are anger, disgust, fear, happiness, and sadness. This study follows an approach developed by Lee and Neal (2007) for music emotion retrieval and applies scroll bars for tagging basic emotions and their intensities. A sample comprising 763 persons tagged emotions caused by images (retrieved from www.Flickr.com) applying scroll bars and (linguistic) tags. Using SPSS, we performed descriptive statistics and correlation analysis. For more than half of the images, the test persons have clear emotion favorites. There are prototypical images for given emotions. The document-specific consistency of tagging using a scroll bar is, for some images, very high. Most of the (most commonly used) linguistic tags are on the basic level (in the sense of Rosch’s basic level theory). The distributions of the linguistic tags in our examples follow an inverse power-law. Hence, it seems possible to apply collective image emotion tagging to image information systems and to present a new search option for basic emotions. This article is one of the first steps in the research area of emotional information retrieval (EmIR).
Received: 20 August 2008; Revised: 11 December 2008; Accepted: 8 January 2009
Digital Object Identifier (DOI)