A probabilistic-entropy approach of finding thematically similar documents with creating context-semantic graph for investigating evolution of society opinion

International Conference on Computer Simulation in Physics and Beyond 2015

物理学;计算机科学

Moloshnikov, I.A.^1 ; Sboev, A.G.^1 ; Rybka, R.B.^1 ; Gydovskikh, D.V.^1

NRC Kurchatov Institute (Academic Kurachatov Sq. 1 Moscow), Department of Mathematical Modelling and Information Technologies, Russia^1

关键词: Automated analysis;    Composite algorithm;    Event evolutions;    Probabilistic entropy;    Semantic graphs;    Social media;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/681/1/012012/pdf
DOI  :  10.1088/1742-6596/681/1/012012

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

The composite algorithm integrating, on one hand, the algorithm of finding documents on a given topic, and, on the other hand, the method of emotiveness evaluation of topical texts is presented. This method is convenient for analysis of people opinions expressed in social media and, as a result, for automated analysis of event evolutions in social media. Some examples of such analysing are demonstrated and discussed.