Content-based RSS and broadcast news streams aggregation and retrieval

Nowadays, the global diffusion of the Internet is enabling the distribution of informative content through dynamic media such as RSS feeds and blogs. At the same time, the decreasing cost of electronic devices is increasing the pervasive availability of the same informative content in the form of digital audiovisual items. Hence, efficient and low-cost solutions for semantic aggregation of heterogeneous multimedia content are needed, in order to enable users to retrieve the desired information from this variety of channels. In this paper, we present an unsupervised framework for content-based Web newspaper articles and broadcast news stories aggregation and retrieval. The core of our system is based on a hybrid clustering algorithm that uses RSS feeds and television newscasts programmes as information sources and builds up a multimodal service made up of items including both contributions. Extensive experiments prove the effectiveness of our method.