Extracting significant time varying features from text
Proceedings of the eighth international conference on Information and knowledge management
Bursty and hierarchical structure in streams
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Query based event extraction along a timeline
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Modularities for bipartite networks
Proceedings of the 20th ACM conference on Hypertext and hypermedia
Networks: An Introduction
Hi-index | 0.01 |
We pose a new problem of discovering associations between events in our daily lives and their characteristic items, such as (Halloween, pumpkin) and (Christmas, chimney). To solve the problem, we dopted an approach similar to that of existing research on event detection, which tries to discover events by detecting bursts of occurrence frequency of a relevant term in a document stream, where the term (item) is associated with the discovered event. We extracted events from blog entries available on the Web, while the previous studies mostly used news articles as document streams. Blog entries are shown to have quite different characteristics to news articles. Considering this fact, we developed a method for discovering the associations by integrating existing techniques that can handle and take advantage of the characteristics of blog data. We verified through experiments using actual data that the proposed approach works quite well.