Identifying Genres of Web Pages

In this paper, we present an inferential model for text type and genre identification of web pages, where text types are inferred using a modified form of Bayes’ theorem, and genres are derived using a few simple if-then rules. As the genre system on the web is a complex reality, and web pages are much more unpredictable and individualized than paper documents, we propose this approach as an alternative to unsupervised and supervised techniques. The inferential model allows a classification that can accommodate genres that are not entirely standardized, and is more respectful of the actual nature of a web page, which is mixed, rarely corresponding to an ideal type and often showing a mixture of genres or no genre at all. A proper evaluation of such a model remains an open issue. Mots-clés : genre, typologies textuelles, pages web, modèle déductif-inductif, identification automatique, théorème de Bayes