Tid: Torsdagen 24 februari kl. 15-17 Plats: C307

Postseminarium med förfriskningar äger rum direkt efter seminariet i institutionens pentry.

Abstract

Broadly speaking, “genre” is a classification concept. Simply put, genres are recurring and recognized patterns of communication that have specific names. For instance, the communicative and social pattern underlying the personal blog genre has been defined as “self-expression and community development” (Miller & Shepherd, 2004).
The web hosts many recognised genres, such as FAQs, press releases, product descriptions, instructions, guides, e-magazine, blogs, professional profiles, how-tos, web ads and reviews. Each of these genres serves a number of communicative and social purposes and carries additional contextual information that helps the reader interpret the content. When the genre of a web text is unknown or not declared explicitly, users feel often at a loss and do not know how to assess how reliable, objective or useful information is. For instance, information coming from a web ad is persuasive and emotional, rather than neutral and unbiased. This characterization of information can or cannot satisfy users’ needs. Can web genres be identified and detected automatically in order to help users to orientate themselves in the rough ocean of information on the web? Which computational models have been tried out so far in automatic genre identification research? How well do they perform? In this talk, I will present and discuss the latest findings in automatic genre identification and suggest viable future directions.

Hjärtligt välkomna!

Ljuba Veselinova & Mats Wirén