科技期刊质量分类决策评价方法分析-教育经济与管理专业毕业论文.docxVIP

哈尔滨工业大学管理学硕士学位论文 哈尔滨工业大学管理学硕士学位论文 - - II - Abstract The self-citation of science and technology journal is a normal behavior in reference, but a number of journals do some manipulation in order to improve the impact factor, it is false to the evaluation of the quality of journals, and it has seriously affected the objectivity and fairness of the evaluation. How to effectively identify the true state of the quality of journals is an important problem with scientific value. In order to solve this problem this paper do two aspects of the study, the method of classification decision-making of journal self-citation behavior and a new evaluation method of comprehensive assessment of the journals, the specific content includs the following: First, study of the method of classification decision-making of science and technology journals. I use decision tree classification method in pattern recognition, and collect some time distribution datas about cited and self-cited and some relevant indicator datas from 17 journals which belong to the biology discipline from 2001 to 2010 for ten consecutive years, and establish the model of journal self-citation pattern classification recognition, the software weka do data processing and build the model, and I do evaluation of classification for these journals. The results show that decision tree algorithm on the classification of the different grades of journals is ideal, the cross rate is 91.1765%. Finally, I randomly selecte several groups of journals in biology discipline in the JCR database and do classification, and prove the effective and reliability of this method. Secondly, study of the quality evaluation of science and technology journals. I used principal component analysis method and correlation analysis to select the key indicators, and I excavate some information from the amount of cited and re-amend and definition of the index of discipline diffusion, then I use discipline diffusion, self-citations behavior, reaction rate