Applying contextual advertising to multimodal information content

Abstract

Contextual Advertising, a major sources of income for a large number of websites, is aimed at suggesting products and services to the ever growing population of Internet users. In this paper, we focus on the problem of suggesting suitable advertisements to news aggregation from television and from the Internet. To our best knowledge, this is the first attempt to perform this task in the field of multimodal aggregation. The proposed system suggests from 1 to 5 advertisements related to the main topic of aggregated news items. 15 users were asked to evaluate the relevance of the suggested advertisements. Preliminary results are encouraging for further development and application of contextual advertising in the field of multimodal aggregation. © 2012 Springer-Verlag.