Subjects: Library Science,Information Science >> Library Science submitted time 2023-10-08 Cooperative journals: 《知识管理论坛》
Abstract: [Purpose/significance] Under the background of novel coronavirus pneumonia, this paper proposes a method of identifying COVID-19 news elements in multi-task environment based on transfer learning to provide knowledge services of emergency for the public. [Method/process] Firstly, multiple tasks were used to identify news elements: Time elements were identified based on rules; besides, a cross domain element recognition model was constructed by integrating model transfer and deep learning methods. On this basis, the associated data of COVID-19 news elements was constructed, and the relationship between the elements was displayed by knowledge mapping. [Result/conclusion] The experimental results show that the F1 values of news elements except Drug are above 80%, which indicates that the transfer learning model can achieve fine recognition effect. Moreover, the knowledge map of associated data can intuitively display the key elements and main contents of news. In conclusion, the method proposed in this paper can effectively identify elements in COVID-19 news, thus it can help readers obtain important information from the news accurately and efficiently.
Subjects: Library Science,Information Science >> Library Science submitted time 2023-08-27 Cooperative journals: 《图书情报工作》
Abstract: [Purpose/significance]To solve some defects of peer review and scientometrics methods in the evaluation of philosophy and social sciences academic outputs, the reform and realization of the evaluation of the academic achievements are explored, especially the evaluation index system of the academic achievements of philosophy and social sciences based on the big data thinking are designed.[Method/process]Based on the comparative analysis and comprehensive analysis, this paper analyzes the disadvantages of the traditional philosophy and social sciences evaluation methods, and then analyzes the changes brought by the big data to the philosophy and social sciences evaluation, finally, it puts forward the philosophy and social sciences evaluation strategies and the index systems based on the big data environment.[Result/conclusion]In big data era, it is possible to analyze the semantics and its relevance based on all-round academic contents and activity data. By using the citation content and behavior evaluation, the academic activities-centered whole process dynamic evaluation, academic value and social function evaluation, value of academic achievements of philosophy and social sciences can be truly, comprehensively and objectively reflected. Based on above research, an index system for evaluation of academic achievements of philosophy and social sciences is constructed, which is composed of two first-level indicators, five two-level indicators and 34 three-level indicators.
Subjects: Library Science,Information Science >> Library Science submitted time 2023-08-26 Cooperative journals: 《图书情报工作》
Abstract: [Purpose/significance] With the changes of emergency management organization mode and urban risk environment, the corresponding reforms in organizational relationship and technology implementation of intelligence system are carried out. Intelligence platform provides tools for supporting dynamic operation of urban emergency management network.[Method/process] By the methods of literature collection and case analysis, this paper adopted information resource planning method to organize emergency management information flow. And then, aiming at real-time and integrated intelligence work, it deduced and constructed urban emergency management intelligence platform.[Result/conclusion] The urban emergency management intelligence platform provides an information exchange channel and an information production place for isomeric management information system and information system, and it provides continuous updated knowledge base and real-time dynamic information data for emergency management through continuous perception of urban system.
Subjects: Library Science,Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract: [Purpose/significance]The commonly used citation evaluation index ignores the difference of citation content. This study attempts to add 3 factors, namely, citation intensity, citation location and citation sentiment, and combine the author contribution to propose the evaluation index of academic influence based on citation.[Method/process] This paper gave a formula for calculating the author contribution, used Analytic Hierarchy Process to define the weight of citation intensity and citation location, and comprehensively calculated the index of author's academic influence with citation intensity.[Result/conclusion] The example shows that AAI index comprehensively considers citation content and author contribution, increases the discrimination of simple citation frequency, and provides new ideas for the scholar's academic evaluation.
Subjects: Library Science,Information Science >> Information Science submitted time 2017-12-05 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】精确地呈现网络社交中信息传播状态和传播过程, 从而更深入理解网络信息的传播机制。【方法】 在无标度网络模型和传染病模型基础上, 加入可调整参数, 构建改进的网络信息传播模型, 并在 NetLogo 平台上 进行舆情传播演化仿真。【结果】仿真实验结果表明: 在信息传播过程中, 不断变化的传播速率能够更好地描述 网络信息传播; 在集群度大的网络中对信息传播进行引导和控制的最佳时机是在传播速率增大阶段。【局限】模 型对人群分类仍然不够精细。【结论】模型不仅能够在设定条件下模拟不同类型信息的传播过程, 还可以为网络 舆情监测、引导和控制提供支持。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-12-05 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】利用 LSTM 模型和字嵌入的方法构建分类系统, 提出一种中文图书分类中多标签分类的解决方 案。【方法】引入深度学习算法, 利用字嵌入方法和 LSTM 模型构建分类系统, 对题名、主题词等字段组成的字 符串进行学习以训练模型, 并采用构建多个二元分类器的方法解决多标签分类问题, 选择 3 所高校 5 个类别的书 目数据进行实验。【结果】从整体准确率、各类别精度、召回率、F1 值多个指标进行分析, 本文提出的模型均有 良好表现, 有较强的实际应用价值。【局限】数据仅涉及中图分类法 5 个类别, 考虑的分类粒度较粗等。【结论】 基于 LSTM 模型的中文图书分类系统具有预处理简单、增量学习、可迁移性高等优点, 具备可行性和实用性。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-12-05 Cooperative journals: 《数据分析与知识发现》
Abstract: 【目的】通过分析中国农产品品牌评价领域的文献题名总结该领域的研究现状。【方法】对该领域的文献 题名进行 K-means 聚类, 分析每簇研究的重点内容, 分别使用因子分析、多维尺度分析和层次聚类分析进一步解 析聚类得到的每簇文献的特点。【结果】文献数量总体呈现“M”型趋势, 文献多采用模糊综合法, 从多个评价角 度集中探讨评价指标体系、评价模型、影响因素等方面。【局限】仅针对题名进行分析, 未涉及关键词与摘要文 本。【结论】聚类结果较好地揭示了中国该领域的研究现状, 但没有反映出种类农产品、Interband 品牌评估法相 关内容。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-11-08 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】通过实验对比分析, 比较不同停用词表对于不同类型的文本数据的作用效果, 对停用词表的构建与使用提供参考意见。【方法】选取百度停用词表、哈尔滨工业大学停用词表以及四川大学机器智能实验室停用词表, 基于三个不同语料库运用汉语分词技术、TF-IDF 特征评估函数以及VSM 模型进行文本处理, 并且采用Java 编写的K-means 算法进行聚类实验, 通过准确率P、召回率R 和F1 三个评价指标对不同聚类结果进行效果评估。【结果】不同停用词表对于不同类型的文本数据作用效果差异明显, 词表的长度、内容结构是影响作用效果的直接因素, 其中两字停用词作用效果最为明显。【局限】实验文本类型及数量有限, 同时对于不同停用词表仅在词语数量及内容上做了简单的分析比较, 未对停用词按照类别分类进行实验分析。【结论】停用词表对于文本聚类准确度有很大的影响, 构建或选取适宜的中文停用词表极为重要。同时, 过度增加停用词的数量并不会一直改善聚类结果。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-10-11 Cooperative journals: 《数据分析与知识发现》
Abstract:【目的】探讨冶金领域中文专利术语抽取模型的最优条件, 用于有效地抽取冶金领域专利术语。【方法】使用尚不完善的核心语料库, 在无需人工标引的情况下, 采用条件随机场(CRFs)构建字角色标注的冶金领域中文专利术语识别模型。详细说明模型的构建过程, 同时重点对比CFRs 的各个因素(特征组合、字长窗口等)对识别效果的影响。【结果】实验结果表明字序列、级别特征、领域特征、温度特征的组合在字长窗口为3, c 等于1,f 等于1 时, 准确率达到94.26%, 召回率达到94.37%, F1 值达到94.5%。【局限】核心词典欠完善, 使得部分词语标注不够准确; 未与其他方法作详细比较, 未详细说明CRFs 的可靠性。【结论】CRFs 在适当的角色和特征以及特征模板的组合下能较好地识别出冶金领域的中文专利术语。
Subjects: Library Science,Information Science >> Information Science submitted time 2017-10-11 Cooperative journals: 《数据分析与知识发现》
Abstract: [Objective] Discuss how to obtain the terminology taxonomic relation from Chinese domain unstructured text. [Methods] Based on Digital Library domain text from CNKI, construct terminology hierarchy by terminology extraction, terminology Vector Space Model construction, BIRCH clustering and cluster tag distribution. [Results]Obtain the terminology taxonomic relation of Digital Library domain, and evaluate the effectiveness. The accuracy of clustering reaches up to 80.88%, and the accuracy of cluster tag extraction reaches up to 89.71%. [Limitations]Evaluate the effectiveness by random sampling, and in comparison with one method only. [Conclusions] Making use of BIRCH algorithm to construct terminology taxonomic relation, this algorithm has obvious advantage compared with K-means clustering method, and has higher execution and clustering effectiveness.