Subjects: Library Science，Information Science >> Library Science submitted time 2023-10-08 Cooperative journals: 《知识管理论坛》
Abstract： [Purpose/Significance] In the context of deep digital development, digital humanities as a development field of interdisciplinary deep integration, the scientific research cooperation among scholars is becoming more and more frequent. It is necessary to analyze and excavate the increasingly complex cooperation relationship, to help scholars obtain potential cooperation opportunities to promote academic exchanges. [Method/Process] In this paper, scholars, institutions and keywords were used as node data, and coauthors, citations, posts and research topics were used as relational data to build scholar-collaboration graphs, which was stored based on the graph database Neo4j. Cypher query language and GDS algorithm library were used to analyze the cooperation community discovery, core scholar identification and cooperation trend prediction of scholars in the field of digital humanities. [Results/Conclusion] The experimental results show that Neo4j can better realize the construction and analysis of scholars’ cooperation network in the field of digital humanities. It can help scholars quickly find interdisciplinary scholars who are highly related to their research interests and directions among many researchers, so as to promote scholars’ cooperation and discipline development in the field of digital humanities.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-10-08 Cooperative journals: 《知识管理论坛》
Abstract： [Purpose/Significance] Keyword is the most widely used literature knowledge unit, and the in-depth mining of its semantic relationship can provide underlying support for knowledge association and resource recommendation. [Method/Process] Based on the relationship between the direct co-occurrence and indirect co-occurrence of keywords, the correlation between keywords was mined, and on this basis, the distribution of keywords was analyzed, and the hierarchical structure between keywords was constructed according to the size of the concept range of keywords. [Result/Conclusion] Taking “knowledge graph” as the root node, this paper demonstrates the steps of construction of keywords hierarchy. The research shows that the method is feasible and effective, and it can construct the hierarchical structure of keywords better．
Subjects: Library Science，Information Science >> Library Science submitted time 2023-10-08 Cooperative journals: 《知识管理论坛》
Abstract： [Purpose/significance] Aiming at shortcomings of the current service quality of digital archives, such as insufficient intelligence and single service content, this paper proposed to build an overall framework of knowledge graph of digital archives, so as to achieve statistical analysis of big data for digital archive, integration and optimization of digital archiving resources, and improvement on the overall service level of digital archives. [Method/process] By collecting literatures, service deficiencies of digital archives were analyzed. This paper investigated the web page service level of digital archives in various provinces and cities, summarized deficiencies of the current service mode of each archive, and improved the framework process of digital archives’ knowledge graph, finally the framework process was presented in the form of flow chart. [Result/conclusion] Knowledge graph can transform multiple types of digital archive text into data that computers can understand, and improve the level of computer intelligent identification. At the same time, dynamic timing and pertinence of the graph can improve the degree of integration archives according to the time node, user data can be updated based on users’ retrieval trace to improve the service quality, enhance the cooperation and communication between digital archives to achieve the result of resources integration, and provide a useful reference to better optimize the digital archiving service.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-08-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Intangible cultural heritage resources have important social value. If the topic map technology can be applied to the digital resources integration of intangible cultural heritage, it will be beneficial to the digital resources protection and inheritance of intangible cultural heritage. [Method/process] In reaction to the digital resources of intangible cultural heritage, this paper first analyzed the theme, relevance and resource indexing, and then, constructed a topic map and visualized it. [Result/conclusion] The research results show that the construction of topic map of digital cultural heritage digital resources can provide semantic integration, visually present the association of different topics to users, as well as provide visual navigation for users.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-08-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance]For the current tag recommendation methods' results not satisfied, this paper aims to improve the traditional similarity calculation method and combine a variety of tag recommendation methods to improve the recommended accuracy.[Method/process]Based on the idea of content and collaborative filtering, LDA is used to calculate the similarity then find the neighbor of resources and users, and combine keywords which are extracted from resource contents to construct the tag hybrid recommendation model. Finally, "Douban reading" is taken as an example to verify the model's effectiveness and compared with several tag recommendation methods.[Result/conclusion]In the social tagging system,three dimensions including user, resource and tag should be considered.Only from one single angle will inevitably cause incomplete results.At the same time, the introduction of LDA in similarity calculation can exploit the potential semantic relation and improve the recommended quality. And the combination of a variety of ways to learn from each other can make the results more satisfactory.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] For the application of the famous sequence alignment algorithm in bioinformatics in text similarity, this paper improves the methods of predecessors and improves the accuracy of text similarity calculation. [Method/process] First, the target text was normalized to form a Chinese sequence set. Subsequently, The trained Skip-Gram model in Word2vec is used to construct the scoring matrix of the Chinese sequence set and formulate the scoring rules. Finally, the Chinese sequences were compared two-two and the optimal solution was obtained. The comparison path of the optimal solution was obtained backtracked, and the similarity of the Chinese sequence was calculated. [Result/conclusion] The empirical results show that compared with the traditional methods, the fusion word vector model of this method improves the accuracy of text similarity calculation and effectively solves the problem of repeated word pairs in traditional methods.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Aiming at the application of sequence alignment algorithm in text similarity, the global alignment algorithm is improved and the accuracy of the algorithm is improved. At the same time, the local alignment algorithm is used to effectively solve the problem of comparing two texts with different content or with different length. [Method/process] First, the CRF model in HanLP was used to normalize the Chinese text data set of the online academic resources and constitute the Chinese sequence set. Then, Word2Vec model was trained with the latest Chinese Wikipedia corpus to construct the word pair scoring matrix. Finally, based on the scoring matrix and the improved scoring rules, the two Chinese sequences of global/local alignment were compared and the optimal solution of the alignment was obtained. The optimal solution was backtracked to obtain the alignment path of the optimal solution and the similarity of the two Chinese sequences was calculated. [Result/conclusion] The experiment results show that compared with the current research of global alignment algorithm, the method based on the results of the part-of-speech tagging and Word2Vec build words to further improve the global alignment score matrix algorithm and applied to the accuracy of computing text similarity of local alignment algorithm can effectively solve the content differences or differences in the length of two text comparing problems.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Community tags generated based on the mining of community topics and users' interests in network social platforms can improve the timeliness and accuracy of the definition of community, and solve the difficulties of user information acquisition and network community selection. [Method/process] Through in-depth analysis of the network community, it was determined that the community features can be represented according to the community topics and users' interests. Firstly, the BTM model of topic extraction was used to train the topic model of network social topics, and the pre-label of network social topics was obtained. Then, based on the different important node indexes of community members' interest tag network, the TOPSIS multi-index comprehensive evaluation method was used to mine the overall interest of members, so as to obtain the interest pre-label of members of the network community. After combining the two results, the community tag was generated and optimized. And this paper took "Douban Group" as an example for demonstration. [Result/conclusion] The community tag generation model based on community topics and members' interests can accurately mine the main interests and recent concerns. Tag generation of the community as a whole is conducive to the selection of interest groups of network users.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/Significance] Considering the dynamic changes of users’ interests and social relationships, this paper proposes a scholar recommendation model integrating users’ dynamic interests and social relationships. [Method/Process] Firstly, using the periodical literature of different disciplines as the classified corpus, the discipline domain of scholars’ blog posts was distinguished based on the labeled LDA model. Then KNN algorithm was used to classify blogs by discipline. At the same time, the change rate of subject interests was used to improve the time factor, and the dynamic interest similarity of scholars was calculated. The PageRank of scholars was calculated by using the quantitative relationship of links between scholars, and the global trust level was calculated by combining the PageRank and time value of blogs sent by scholars. Time weight was introduced into scholars’ comments and recommendation interaction behaviors to calculate scholars’ interactive trust level. The dynamic social trust level of scholars was obtained by integrating the global trust level and interactive trust level. Finally, the similarity of interest and trust were combined to recommend scholars. [Result/Conclusion] The scholar recommendation model integrating users’ dynamic interests and social relationships in the virtual academic community can effectively improve the quality of scholar recommendation from the perspectives of dynamic interests and dynamic social relationships.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/Significance] Combined with domestic and foreign literature research and the characterization of college students' network information security literacy from the perspective of platform society, this study constructs the evaluation index system of college students' network information security literacy ability and makes empirical analysis, in order to provide references for the scientific evaluation of network information security literacy.[Method/Process] Combined with the previous research, this paper preliminarily constructed the evaluation index system of college students' network information security literacy facing the new environment and carried out network questionnaire investigation. Eight first-level indexes such as "network information security knowledge" and "basic skills for the safe use of the platform" were extracted by the exploratory factor analysis method based on data samples. At the same time, the coefficient of variation method was used to assign weight coefficients to all levels of indicators and the empirical results were analyzed.[Result/Conclusion] The empirical results show that college students perform relatively well in the indicators related to the basic awareness of network information security, while there is much room for improvement at the deep level of multiple cognition, specific knowledge and practical skills. At the same time, the study also finds that the index scores of college students in different grades, different majors and different types of universities do not show significant differences. Based on this, this paper puts forward some countermeasures and suggestions on improving college students' network information security literacy from the perspective of platform society around the three related subjects of "nation-university- individual student".
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】利用用户标签及关系网络, 为用户推荐潜在的相似用户。【方法】通过探究社会化标注系统中标 签、关系网络所表征的用户长短期兴趣特征, 综合用户标签及关注关系, 利用多维尺度法构建用户聚类模型, 根 据用户聚类结果进行相似用户推荐, 并以“微博”为例对模型进行实证。【结果】实验结果表明, 基于标签和关系 网络的用户聚类模型能够有效地结合用户长短期兴趣特征, 挖掘潜在相似用户, 聚类及推荐效果较好。【局限】 样本数据集具有局限性, 不能完全涵盖用户兴趣领域, 仅从一个领域验证了模型的准确性与有效性。【结论】通 过对用户标签及关系网络挖掘用户长短期兴趣, 构建的基于用户静态标签与动态关系网络的用户推荐模型, 对 个性化用户推荐效果有较好的提升。
Subjects: Library Science，Information Science >> Information Science submitted time 2017-11-30 Cooperative journals: 《数据分析与知识发现》
Abstract：【目的】利用用户标签及关系网络, 为用户推荐潜在的相似用户。【方法】通过探究社会化标注系统中标 签、关系网络所表征的用户长短期兴趣特征, 综合用户标签及关注关系, 利用多维尺度法构建用户聚类模型, 根 据用户聚类结果进行相似用户推荐, 并以“微博”为例对模型进行实证。【结果】实验结果表明, 基于标签和关系 网络的用户聚类模型能够有效地结合用户长短期兴趣特征, 挖掘潜在相似用户, 聚类及推荐效果较好。【局限】 样本数据集具有局限性, 不能完全涵盖用户兴趣领域, 仅从一个领域验证了模型的准确性与有效性。【结论】通 过对用户标签及关系网络挖掘用户长短期兴趣, 构建的基于用户静态标签与动态关系网络的用户推荐模型, 对 个性化用户推荐效果有较好的提升。
Hits
YES
Hits
Downloads
Comment