Emerging User Intentions: Matching User Queries with Topic Evolution in News Text Streams

Codrina Lauth, Ernestina Menasalvas.

Topic and event evolution analysis aiming at trend detection and tracking (TDT) from news data streams has considerably gained in interest during the last years. Consolidated studies have concentrated on identifying and visualizing dynamically evolving text patterns from news data streams. Detecting and understanding user behavior and relating user intentions to emerging topic trends in news data streams still continues to remain a huge challenge for making search engines in “real-time” responsive to user’s information needs. In this paper, we will describe a three-layered approach (user-system-content) and how we can merge and process the relevant sources of highly evolving information on a news portal. This approach is a further step on building more streamline user-adaptive newswire search, based on topic and trend detection systems [9], able to deal in a userfriendly way with the permanently changing variety of news data streams that are embedded in the complex structure of a news portal.

PDF full paper