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.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Teamwork has become an important form of organization for knowledge innovation today. Exploring the dynamic evolution law of scientific research teams from the perspective of dynamic networks is of great significance to promote the discovery, formation and management of scientific research teams.[Method/process] Taking the field of artificial intelligence as an example, this paper used the Louvain community discovery algorithm to identify research teams in the field of artificial intelligence. The extreme value distribution of the number of nodes, edges, network density, and clustering coefficients in the team cooperation network were calculated. A combination of micro and macro perspective explored the laws and characteristics of the evolution of high-yield teams in this field, aiming at revealing the intrinsic motivation of the evolution of scientific research teams.[Result/conclusion] From the micro perspective, the extreme value distribution of co-authored network topological indicators reveals the dynamic properties of the evolution of high-yield teams in the field of artificial intelligence; from the macro perspective, high-yield teams show evolutionary commonality in network density and network average clustering coefficients, and most teams foster more new cooperative relationships in the evolution process. In view of the evolution path of the team, the phenomenon of "small group" cooperation in high-yield teams in the field of artificial intelligence is significant, and the cooperation between "small groups" directly affects the direction of the overall team.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] This paper discusses the collaboration pattern of research teams in the artificial intelligence field, and compares the differences among research teams in different collaboration pattern.[Method/process] Taking the identified AI leading research team as the research object, and according to the number of scholars and the indicator value of social network indicator in the team, the core scholars in the team were identified, so as to divide the collaboration pattern of the AI research team, and analyze the teams with different collaboration pattern with examples. On this basis, the differences among the leading teams of different collaboration pattern were compared and analyzed from several dimensions of network structure characteristics, research performance and geographical distribution.[Result/conclusion] The cooperative patterns, of research teams in the field of artificial intelligence are divided into four types:single-core pattern, dual-core pattern, multi-core pattern and equilibrium pattern. Among them, the research teams of single-core pattern and dual-core pattern all perform well in the research dimension.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] This paper identifies the research team in the artificial intelligence field, and extracts the leading research team from multi-dimensional indicators, aiming to enrich the process and method of identification of the research team, and provide the basis for analyzing the context, frontier and theme of the field of artificial intelligence from the perspective of the research team.[Method/process] This paper was based on the publication data of the Web of Science category Computer Science, Artificial Intelligence from 2009 to 2018, and did data cleaning via programming and manual check. Global co-author network is constructed based on the fractional counting method, and the Louvain algorithm was used to dynamically tune and identify the research teams. Moreover, the leading research team was extracted based on different indicators with parameter adjustment.[Result/conclusion] From practical view, the study has constructed a set of rules for cleaning publication data of artificial intelligence field. The process of identifying artificial intelligence research teams based on co-authorship is constructed. The study proposes the method of tuning the parameter by eliminating edge nodes in the collaboration network and further taking the known research teams as baseline. The worldwide research teams of artificial intelligence field are systematically and accurately identified. The leading research teams are further extracted based on indicators of six dimensions, i.e. number of publications、number of citations、h index、weighted degree centrality、betweenness centrality、closeness centrality. Exemplary analysis is conducted on leading research teams of each dimension by combining the publication data and web information survey.
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.
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】研究社交媒体舆情信息传播规律和信息传播效果影响因素, 为政府管理实践和相关决策提供参考依据。【方法】结合5W 传播模式和议程设置理论对信息传播因素提出假设, 采用相关性分析进行验证。【结果】研究发现传播群体中意见领袖群体对传播效果影响最大, 微博发布者属性与传播效果存在正相关关系, 信息传播数量与传播效果成负相关关系。【局限】由于受到时间、技术等限制, 只选择单一话题在单一时间内的传播情况做了实证分析。【结论】对政府机构、新闻媒体、大型企业等管理者了解舆情传播影响情况及舆情信息影响因素探索研究具有重要意义。
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。
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】通过研究《现代图书情报技术》近10年的发文特征,分析其特点与发展趋势, 为今后发展提供 建议。【方法】分别检索《现代图书情报技术》以及 CNKI、万方、WOS 数据库中相似期刊近 10 年的文献, 比 较发文的外部特征和内部特征。【结果】与其他期刊相比,《现代图书情报技术》具有明显的特点, 所发的技术 方法类研究论文对图书情报领域的支持作用显著【局限】仅根据关键词计算出主题, 没有以文献全文为依据。【结论】在信息技术驱动的研究热潮下, 《现代图书情报技术》应该保持自身特点, 抓住现有机会, 在图书情报 技术研究领域保持优势, 推动图书情报技术研究与应用的发展。
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] This paper aims to comprehensively explore the knowledge structure and hotspot distribution of different disciplines, with the help of topic extraction and distribution analysis using LDA (Latent Dirichlet Allocation) model from the perspective of subject classification. [Methods] We collected data from the domestic knowledge flow (KF) field and KF related literature from CNKI and Wangfang database, then grouped these data into 11 categories by Chinese Library Classification. Finally, we extracted 20 hot subjects from documents in 11 disciplines with the help of the LDA topic model. [Results] The content and knowledge points in 11 disciplines were obtained from the analysis of 20 extracted hot topics. [Limitations] We did not compare the proposed method with topic mining research in other fields. The domestic KF hotspots found by our study were not compared to the previous findings. [Conclusions] The proposed method can help us explore the knowledge structure and research trends more comprehensively.
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】用户内容使用行为对学术社交网络的可持续发展具有重要的价值, 本文试图从用户阅读的角度对学术社交网络用户内容使用行为进行探究。【方法】以科学网热门博文为分析对象, 采用方差分析、相关性分析等方法, 从内容基本特征、用户内容使用行为关系、内容贡献者特征等方面对用户内容使用行为特征进行研究。【结果】用户对观点交流以及教学、科研经验分享类的内容比较感兴趣; 大部分类别的博文评论量与被推荐量达到显著相关或高度相关的水平。【局限】研究平台单一, 仅选择中文学术交流网站作为研究平台; 对用户内容使用行为的研究不全面, 仅研究了用户的内容阅读行为。【结论】用户喜欢在学术社交网络上进行思想与观点的表达与交流; 他们更倾向于推荐自己参与互动的内容。
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】分析大数据背景下的需求, 探索社会舆情分析与决策支持的理论依据与重点研究问题。【方法】综合运用图书情报、新闻传播、公共管理、计算机、心理学、系统动力学、复杂网络等理论与方法, 基于社会现实考察与业界实践分析, 总结凝练研究观点。【结果】提出“以‘知识论’、‘决策论’与‘系统论’相结合”等6 个视角引导研究设计与布局研究内容, 并侧重解决社会舆情传播对政府决策影响的理论依据探寻等5 个关键问题。【结论】大数据给社会舆情分析与政府决策支持带来新的机遇, 迫切需要提出与采纳新的研究视角解决关键问题。
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】对海量异构的社会舆情信息进行语义组织, 揭示社会舆情信息之间的多维度关联, 以为后期的挖掘、分析和决策支持提供重要支撑。【方法】从政府决策需求出发, 建立基于本体的社会舆情信息语义组织框架,根据社会舆情信息本体的特点, 采用七步法的本体构建方法, 以ABC 事件本体为参考模型, 明确其中的概念以及概念间的关系, 建立社会舆情信息之间的语义关联。【结果】构建适用于社会舆情信息描述的POIOM 模型, 完成本体管理模块的设计。【局限】论文以访谈和统计分析为主要需求获取渠道, 有待更多的政府决策者用户群体对需求加以验证和完善。【结论】POIOM 模型对社会舆情信息具有良好的描述能力, 从内容角度深层次地揭示同一案例不同特征项内容之间的关联, 以及多舆情事件之间的逻辑关系和内在联系, 基本验证了基于需求的社会舆情信息语义组织方法的可行性和有效性。
Hits
Hits
Downloads
Comment