Skip to Main Content
With the advent of Web 2.0, searching and publishing became two major forms of online activities for web users. When an event happens, web users would search for the latest information about the event as well as publish blog posts to discuss the event. Both the queries from users and the blog posts published give strong indications of the real-world events of users' concern. In this paper, we propose to study query-guided event detection from two parallel document streams (i.e., news and blog). Our goal is to group user queries, news articles, and blog posts into events to which they are related. The evolution of an event is reflected by the changes in both the query keywords and news/blogs content during the event happening period. We propose a two-stage real-time event detection framework consisting of event fragment detection and event detection. The proposed framework integrates queries, news articles, and blog posts through the notion of query profile. In our experiments, we evaluate the proposed framework using real-world data collected from Technorati and Google News.