Title :
Hot topic extraction using time window
Author_Institution :
Dept. of Comput. Sci., Northwest Normal Univ., Lanzhou Gansu, China
Abstract :
This paper presents a novel time window based hot topic extraction model for news stream. The model considers both pervasiveness and burst feature of topic terms. Pervasiveness is evaluated by terms´ occurrences reported from different channels and burst is assessed by terms´ abnormal occurrence frequencies from different time intervals. An energy ratio threshold based approach for burst detection is adopted and time window is introduced for news text stream analysis. TF-PDF is then combined to weigh the terms. Experiment results demonstrate that our model is effective in topic extraction for news texts.
Keywords :
information retrieval systems; text analysis; burst detection; burst feature; electronic news document archives; energy ratio threshold based approach; hot topic extraction model; news text stream analysis; pervasiveness feature; term abnormal occurrence frequencies; time window; Cybernetics; Data mining; Educational institutions; Feature extraction; Heuristic algorithms; Machine learning; Machine learning algorithms; Burst Detection; Data Stream; Hot Topic; TF-PDF; Time Window;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2011 International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-1-4577-0305-8
DOI :
10.1109/ICMLC.2011.6016664
