Automated Illustration of News Stories

Forgetting what one has just read is, in some cases, linked to insufficient attention. The reader might feel either bored or distracted by something more interesting - a common trace in children and the elderly. The challenge is: how can multimedia systems assist readers in reading and remembering stories? Several studies [2, 7, 14] showed that reading memory is improved by visual stimulus. In this paper we formulate the hypothesis that an automated multimedia system can help users in reading a story by stimulating their reading memory with adequate visual illustrations. These illustrations are intended to increase the readers´ attention towards the story and to help them recalling the story. The framework automatically creates a multimedia presentation of the news story by (1) rendering the news text in a sentence-by-sentence fashion, (2) providing mechanisms to select the best illustration for each sentence and (3) select the set of illustrations that guarantees the best sequence of illustrations. Users may also activate a text-to-speech functionality according to their preference or reading difficulties. Experiments used Flickr images to illustrate BBC news articles: a user survey with 23 users assessed positively the effectiveness of the system.