A Hotspot Discovery Method Based on Improved FIHC Clustering Algorithm

• Published in: Tehnički vjesnik Vol. 28; no. 5; pp. 1790 - 1796
• Main Authors: Lin, Lina, Wei, Dezhi
• Format: Journal Article Web Resource
• Language: English
• Published: Slavonski Baod University of Osijek 01.10.2021; Josipa Jurja Strossmayer University of Osijek; Strojarski fakultet u Slavonskom Brodu; Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek; Građevinski i arhitektonski fakultet Osijek; Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
• Subjects: Algorithms; Analysis; Clustering; hotspot detection; internet public opinion; Methods; microblog; TOPSIS; China
• ISSN: 1330-3651; 1848-6339
• DOI: 10.17559/TV-20210610120531

It was difficult to find the microblog hotspot because the characteristics of microblog were short, rapid, change and so on. A microblog hotspot detection method based on MFIHC and TOPSIS was proposed in order to solve the problem. Firstly, the calculation of HowNet similarity was used in the score function of FIHC, the semantic links between frequent words were considered, and the initial clusters based on frequent words were produced more accurately. Then the initial cluster of the text repletion of mircoblog was reduced, and the idea of Single-Pass clustering was used to the reduced topic cluster in order to get the Hotspot. At last, an improved TOPSIS model was used to sort the hot topics in order to get the rank of the hot topics. Compared with the other text clustering algorithms and hotspot detection methods, the method has good effect, and can be a more comprehensive response to the current hot topics.