论文部分内容阅读
【目的】构建一组反映期刊内部特征信息的作者特征空间向量,以拓展期刊影响力分析方法。【方法】以图书情报学领域18种核心期刊2011年第1期的380篇论文为研究对象,选取其中3/4的文献为训练样本,构建基于作者特征的期刊影响力预测模型,以剩下的1/4论文为测试样本,检验预测模型的有效性。【结果】实验发现,期刊影响力预测模型与4年后对应期刊的影响因子具有较好的吻合度。【结论】说明由期刊作者特征研究期刊影响力是可行的,为研究期刊影响力提供了一种新方法。
【Objective】 To construct a set of feature space vectors that reflect the internal feature information of journals so as to expand the method of analyzing influence of journals. 【Method】 Based on 380 articles of 18 core journals published in 2011 in the field of library and information science, three-fourths of them were selected as training samples to construct a model of periodical impact prediction based on the author’s characteristics. The 1/4 paper is a test sample to test the validity of the predictive model. 【Result】 The experiment found that the prediction model of periodical impact has a good agreement with the influencing factors of corresponding periodicals after 4 years. 【Conclusion】 It is feasible to study the influence of periodicals by the features of periodical authors, and provide a new method for studying the influence of periodicals.