Title :
Research on algorithm of extracting micro-blog´s hot topics
Author :
Peng, Feifei ; Qian, Xu ; Meng, Hui ; Zhou, Dan ; Li, Gaoren
Author_Institution :
Sch. of Mech. Electron. & Inf. Eng., China Univ. of Min. & Technol., Beijing, China
Abstract :
Because of a large number of micro-blog´s junk posts, how to instantly browse hot topics in micro-blog is faced with severe challenges. We propose a new extraction algorithm of hot topics to remove the false hot topics. The algorithm sets a group of parameters what is a determine condition. Parameters contain word frequency, users´ number, occurrence number, users´ discrete degrees, and time distribution of release or forward posts. The preliminary results show that the new algorithm can effectively extract hot topics from micro-blog and remove the false hot topics at the same time.
Keywords :
Web sites; extraction algorithm; false hot topics removal; forward posts; microblog hot topics; microblog junk posts; occurrence number; release posts; time distribution; user discrete degrees; user number; word frequency; Algorithm design and analysis; Blogs; Classification algorithms; Clustering algorithms; Data mining; Feature extraction; Heuristic algorithms; classify; fuzzy clustering; micro-blog; posts dissemination; soft real-time;
Conference_Titel :
Electronics, Communications and Control (ICECC), 2011 International Conference on
Conference_Location :
Ningbo
Print_ISBN :
978-1-4577-0320-1
DOI :
10.1109/ICECC.2011.6066517
