基于主成分和集对分析法的期刊评价方法研究

摘要

[Purpose/Significance]With the increasing attention of the journal ranking, the research on the evaluation method of periodicals is of great significance.In order to study the periodical evaluation methods, analysis and evaluation index of journals between the degree of separation and structure, and finally improve the quality of the Journal evaluation.[Method/Process]the article selects 16 indicators to evaluate the Journal, including influence index, fund paper ratio, the total cited frequency, cited journals and so on.Through the principal component analysis, the evaluation index was selected, and the evaluation index system was constructed.The degree of separation between the indexes was analyzed by set pair analysis method.[Result/Conclusion]Empirical results show the index of higher grade journals is higher, the difference is relatively low, and the index of the lower grade journals is relatively low, and the difference is relatively high.But there was no significant difference in the degree of opposition.The results obtained by the index system are basically not different from the official results.That shows that the set pair analysis method not only can analyze the index characteristics of the journal, but also has high reliability and validity in the evaluation of journals.%[目的/意义]随着期刊排名关注度的增加,期刊评价方法的研究具有十分重要的意义.为了研究期刊评价方法,分析期刊评价指标间的分离程度及其结构关系,最终达到提高期刊评价质量的目的.[方法/过程]选取影响力指数、基金论文比、总被引频次、引用期刊数等16个指标对期刊进行评价.通过主成分分析筛选指标,构建评价指标体系,再运用集对分析法分析指标间的分离程度.[结果/结论]实证结果显示较高等级期刊的指标同一度较高,差异度较低;较低等级期刊的指标同一度较低,差异度较高;而在对立度方面则没有明显的区分.评价结果和官方给出的期刊排名相差无几,说明集对分析法可对期刊评价指标间的分离度进行分析,在期刊评价方面具有可靠性和有效性.