Intro to Archival Science: Developing an Undergraduate Archival Elective Outside of a LIS Program

Abstract

This case study describes the development and implementation of a three-credit undergraduate archival science course at Mount St. Mary’s University. Offered through the university’s Department of History, this course was designed to prepare students for positions in archives-related careers, unlike most research-based undergraduate archival electives. Benefits of the course to both students and the archivist profession will be discussed.     

基于LSTM神经网络的学科主题热度预测模型

[目的/意义]作为科学学预测的重要组成部分,学科主题热度预测旨在揭示学术前沿和发展趋势,辅助学者发现前沿选题,支持科研管理机构科学立项。[研究设计/方法]提出基于期刊影响因子的学科主题热度计算指标(TP-JIF),构建基于LSTM神经网络的学科主题热度预测模型(TPP-LSTM),并以LIS领域数据为例,通过时间切片的形式抽取、计算学科主题的热度序列,检验不同长度时间序列下模型的各项误差。[结论/发现]相对于RBF-SVM、Linear-SVM、KNN、Naive Bayesian等模型,TPP-LSTM预测模型可有效表征学科主题热度时间序列的特性,当时间序列长度为4年时预测效果相对较好。[创新/价值]提出的基于期刊影响因子的学科主题热度计算指标,能够有效刻画不同学术刊物对学科影响的差异,规避了单纯依据频率计算热度的弊端;构建的学科主题热度预测模型,有效表征了学科主题的时间序列变化规律,减小了各项预测误差,预测效果较好。