Finding Emotional-Laden Resources on the World Wide Web

Some content in multimedia resources can depict or evoke certain emotions inusers. The aim of Emotional Information Retrieval (EmIR) and of our research is toidentify knowledge about emotional-laden documents and to use these findings in a newkind of World Wide Web information service that allows users to search and browse byemotion. Our prototype, called Media EMOtion SEarch (MEMOSE), is largely based onthe results of research regarding emotive music pieces, images and videos. In order toindex both evoked and depicted emotions in these three media types and to make themsearchable, we work with a controlled vocabulary, slide controls to adjust the emotions’intensities, and broad folksonomies to identify and separate the correct resource-specificemotions. This separation of so-called power tags is based on a tag distribution whichfollows either an inverse power law (only one emotion was recognized) or aninverse-logistical shape (two or three emotions were recognized). Both distributions arewell known in information science. MEMOSE consists of a tool for tagging basic emotionswith the help of slide controls, a processing device to separate power tags, a retrievalcomponent consisting of a search interface (for any topic in combination with one or moreemotions) and a results screen. The latter shows two separately ranked lists of items foreach media type (depicted and felt emotions), displaying thumbnails of resources, rankedby the mean values of intensity. In the evaluation of the MEMOSE prototype, studyparticipants described our EmIR system as an enjoyable Web 2.0 service