• Study and Application of Translation and Prediction of the Scientific Literature Communication Network from the Perspective of Knowledge Evolution

    Subjects: Library Science,Information Science >> Library Science submitted time 2023-08-26 Cooperative journals: 《图书情报工作》

    Abstract: [Purpose/significance] Analyzing and researchingthe development trendof scientific literature communication network can provide reference to the following work: reveal new scientific research achievements, grasp the development context of science and technology context and find the academic foreground.[Method/process] At first, this paper expounded the theory of knowledge evolution and its application. And then, it discussed the feasibility of the scientific literature communication network forecasting method from the perspective of knowledge evolution.Finally, it constructed the forecasting model of scientific literature communication network by analyzing the evolution mechanism of science literature communication network, and verifiedthe forecasting modelthough the keywords network of scientific literature.[Result/conclusion] The empirical analysis of scientific literature shows that the evolution and trend forecasting method of scientific literature communication network is feasible and effective. Besides,this model can providesnew research ideas for the trend analysis of science literature communication network.

  • 科技情报分析中LDA主题模型最优主题数确定方法研究

    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】有效确定科技情报分析中 LDA 主题模型的最优主题数目。【方法】利用主题相似度度量潜在主 题之间的差异, 同时结合困惑度提出一种确定 LDA 最优主题数目的方法, 该方法既考虑主题抽取效果同时也考 虑模型对新文档的泛化能力。 【结果】获取国内新能源领域的科技文献作为数据集, 实证结果表明本文提出的最 优 LDA 主题数确定方法与单纯使用困惑度相比, 具有更高的主题抽取查准率(91.67%)、 F 值(86.27%)及科技文献 推荐精度(71.25%)。 【局限】未针对其他类型的数据集进行新方法的验证, 如微博短文本、XML文档等。 【结论】 本文方法能够有效地从科技文献数据集中抽取辨识度较高的主题, 并能够提高科技文献推荐效果。

  • Topic Mining and Viewpoint Recognition of Different Communicators in the Transmission Cycle of Micro-blog Public Opinion

    Subjects: Library Science,Information Science >> Library Science submitted time 2023-08-27 Cooperative journals: 《图书情报工作》

    Abstract: [Purpose/significance] This paper aims to explore the hot spot of public opinion and the main point view of the communication of different communicators in the transmission cycle of micro-blog public opinion and to discover the characteristics and laws of public opinion transmission, which can provide the basis for public opinion analysis and decision making.[Method/process] This study is based on the text data of a true public opinion event. It adopted life cycle theory and LDA method to design research process and construct research model, and researched topics of different communicators in micro-blog public opinion events, including topic extraction and semantic annotation, semantic analysis of different communicators at various stages, recognition and characterization of theme views of public opinion based on time dimension.[Result/conclusion] It is found that the research model proposed in this paper can excavate topic theme structure, view and characteristics of different communicators in the communication cycle of public opinion. And the words with actual meaning and irritating function are related, representative and important. At the same time, the conclusion also found a hot topic in the mass media or the official micro-blog is totally different from micro-blog users.

  • Research on the Impact of Small-World Characteristics of Patent Cooperation Network on Enterprise Technological Innovation Performance

    Subjects: Library Science,Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》

    Abstract: [Purpose/significance] Based on the moderating effect of patent cooperation network's small-world characteristics, the paper analyzes the impact of enterprise ego-network characteristics on innovation and provides a basis for the management of firm's technological innovation.[Method/process] The paper used co-patentee relationship between enterprises to construct patent cooperation networks and measured innovation of enterprise with the number of patents application and authorization. The paper built the theoretical model, with the scale and density of enterprise ego-network, the proportion of cooperation with small companies as independent variables, with the small-world characteristics of patent cooperation network as a moderator variable. We took enterprises in the field of speech recognition technology as research samples for empirical analysis.[Result/conclusion] Through empirical analysis, this paper reveals the impact of the characteristics of ego-network on innovation of enterprises, and clarifies the mechanism of the impact of the small-world characteristics of the patent cooperation network on innovation. The research finds that the small-world characteristics enhance the negative influence of the density of the ego-network on innovative through its high clustering coefficient. Based on the results, the countermeasures and suggestions to improve innovation are put forward.