{"title":"Comparative Analisys of Texts by F. M. Dostoevsky and Other Authors Using Decision Trees","authors":"Surovtsova T. G, Moskin N. D., Mokerova D. A.","doi":"10.1109/SIST50301.2021.9465932","DOIUrl":null,"url":null,"abstract":"The paper is devoted to the research of the publicistic style of F. M. Dostoevsky compared to other authors (M. M. Dostoevsky, N. N. Strakhov, I. N. Shill, A. A. Golovachev, A. Grigoriev, Y. P. Polonsky) based on articles in the magazines \"Time\" and \"Epoch\" in the period 1861-1865 in pre-revolutionary spelling. Using the distribution of parts of speech and other features of text fragments (the length of such non-intersecting fragments is 1000 words), decision trees with different classification parameters and quality were constructed. Decision trees are easily interpreted as opposed to neural networks. The analysis of these graph-theoretic models has shown good results for works in Russian. It allows the researcher to set and solve various tasks of the text attribution.","PeriodicalId":318915,"journal":{"name":"2021 IEEE International Conference on Smart Information Systems and Technologies (SIST)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Conference on Smart Information Systems and Technologies (SIST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIST50301.2021.9465932","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The paper is devoted to the research of the publicistic style of F. M. Dostoevsky compared to other authors (M. M. Dostoevsky, N. N. Strakhov, I. N. Shill, A. A. Golovachev, A. Grigoriev, Y. P. Polonsky) based on articles in the magazines "Time" and "Epoch" in the period 1861-1865 in pre-revolutionary spelling. Using the distribution of parts of speech and other features of text fragments (the length of such non-intersecting fragments is 1000 words), decision trees with different classification parameters and quality were constructed. Decision trees are easily interpreted as opposed to neural networks. The analysis of these graph-theoretic models has shown good results for works in Russian. It allows the researcher to set and solve various tasks of the text attribution.
本文主要研究陀思妥耶夫斯基与其他作家(m.m.陀思妥耶夫斯基、N. N.斯特拉霍夫、I. N. Shill、A. A. Golovachev、A. Grigoriev、Y. P. Polonsky)在1861-1865年间发表在《时代》(Time)和《时代》(Epoch)杂志上的文章,以革命前的拼写形式进行比较。利用文本片段的词性分布和其他特征(非相交片段的长度为1000 words),构建了不同分类参数和质量的决策树。决策树很容易被解释为神经网络的对立面。这些图论模型的分析在俄文的工作中显示出良好的效果。它允许研究者设置和解决文本归因的各种任务。