中文    English
Current Issue
05 December 2023, Volume 35 Issue 12
Research Advances in Resource Management Technology of Smart Recommendation Enabled by Big Data in China | Open Access
SUN Yusheng, FAN Ying, ZHU Bo
2023, 35(12):  4-17.  DOI: 10.13998/j.cnki.issn1002-1248.24-0044
Asbtract ( 106 )   PDF (1141KB) ( 75 )  
References | Related Articles | Metrics
[Purpose/Significance] Data empowerment for collaborative transformation of the entire industrial chain has become a national strategy. In the context of multi-source and heterogeneous big data, we face higher demands on the diversity and real-time of recommendation services, as well as the standardization and comprehensiveness of user and item information management, in order to turn data into resources, support the diversification of smart recommendation services, and enhance the user interaction experience. To this end, we should systematically sort out and analyze the research results of user interest modeling and item information management technologies in China's big data empowerment, elaborate the technical system for standardized management of user and item information in intelligent recommendation. [Method/Process] The article summarizes the content of 507 documents using literature review methods, and summarizes and analyzes the domestic big data empowerment resource management technology for smart recommendation from two aspects: user interest modeling and item information management. User interest modeling technology includes model representation, model initialization and model evolution, the item information management technology shows the goals, implementation methods, implementation techniques, and methods of item information management, including data collection, data mining, data storage, data updating, and data interpretation. [Results/Conclusions] First, the user interest modeling technology of big data empowerment mainly studies the following issues. 1) The method of model representation is to accurately formalize the user's needs. 2) The model is initialized to collect user information in an implicit or explicit way and select tools and technologies according to data types to pre-process user data according to a fixed process, and select measurement methods to quantify user interest. 3) Model evolution aims to apply methods and technologies to evolve user interest models offline and online. Second, the item information management technology of big data empowerment mainly studies the following issues. 1) The online technology and offline equipment are used to synchronously collect item data across the whole domain, integrate domain knowledge, and use algorithm libraries and data analysis methods to mine item data. 2) The distributed storage is used such as databases and file systems to store item data. 3) Data collection, mining, and storage technologies are the main techniques, item data are updated through offline and online methods, and visualization technology is used to intuitively interpret ietm data. Finally, existing research needs to strengthen the design and practical research of user-driven and data-driven smart recommendation solutions, as well as strengthen research on data security.
Influencing Factors of Network Social Mentality in Public Emergencies: A Meta-Synthesis | Open Access
HU Yuan, GAO Wei, CHEN Guodong
2023, 35(12):  18-32.  DOI: 10.13998/j.cnki.issn1002-1248.23-0738
Asbtract ( 66 )   PDF (1997KB) ( 62 )  
References | Related Articles | Metrics
[Purpose/Significance] When emergencies occur, the information environment becomes complex, users' emotions are strongly affected, and the social mentality fluctuates. This situation also poses new requirements for the management of network public opinion. It is urgent to actively and correctly manage the current social mentality. The research on the current social mentality mainly focuses on the macro level, while the micro-user emotion and the macro-network social mentality need to be further explored. Therefore, it is necessary to explore the fine-grained influencing factors of the network social mentality in public emergencies, so as to promote the effective response to public emergencies in China and manage social mentality. [Method/Process] The meta-synthesis method is used to formulate a reasonable retrieval strategy. Based on the mainstream databases at home and abroad, the literature is screened by topic, and the quality of related topic literature is evaluated to obtain effective literature and use it as the original data. Through the form of three-level coding, the included literature was interpreted, translated and aggregated to test the reliability and validity of the research results and confirm the validity of the results. This paper summarizes the key variables and implicit relations of the existing research results, and constructs a comprehensive and micro-theoretical framework of the influencing factors of network social mentality in public emergencies. The relationship between the dimensions and the main categories in the model was analyzed. [Results/Conclusions] The study finally obtained 90 initial concepts, 31 categories and 13 main categories, which were summarized into a model of influencing factors composed of four dimensions: user, event, government and social environment. As the main body and direct cause of the change of network social mentality, users and events are the core objects of network social mentality management. As the external environment for the change of network social mentality, society and government play an important role in the management and standardization of network social mentality. The theoretical model framework can provide some guidance and reference for promoting public emergency response and social mentality management. It is also of great significance for the study of network social mentality and user emotion. There are still some shortcomings in the article. The research object of this paper has not yet been more official and unified. The definition is a self-summary based on literature reading. In addition, due to the specificity of the research object, there may be a problem of incomplete literature search. In the future research, the management model will be further explored in combination with the development of practice, and the model framework will be revised and expanded.
Construction Model of Digital Rural Areas in China from the Perspective of Structural Dynamics Based on Multiple Cases | Open Access
FENG Xian, LI Jin, CUI Kai, FAN Beibei
2023, 35(12):  33-48.  DOI: 10.13998/j.cnki.issn1002-1248.23-0842
Asbtract ( 85 )   PDF (1699KB) ( 104 )  
References | Related Articles | Metrics
[Purpose/Significance] Accelerating the construction of digital rural areas is a strategic direction for comprehensively promoting rural revitalization, which plays an important role in promoting the modern basic living conditions in rural areas, improving the quality and efficiency of farmers' production and living, and achieving the development of urban-rural integration. In recent years, the construction of digital rural areas has been actively promoted in various regions, and a number of typical models are being explored and practised which has brought more digital dividends to rural residents. However, the regular characteristics of various practices have not been summarized in related research, resulting in poor promotion of best experience models and a lack of directional indicators for digital rural construction in different regions. This paper has summarized the regular characteristics and application mechanisms of diversified digital rural construction practices in China. The relevant conclusions would provide theoretical reference for promoting the construction of digital rural areas in different regions through classification. [Method/Process] Based on the perspective of structural elements and dynamic effects, this paper investigated four typical county-level digital rural construction models as research objects, namely Deqing County, Pukou District, Cao County, and Dianjiang County, in the national or provincial-level digital rural pilot county. Then, it used a multi-case analysis method to explore the regulatory characteristics of different types of digital rural construction models. [Results/Conclusions] The construction of digital rural areas in China mainly involves the integration of urban and rural areas, the integration of industry and city, the integration of point, line, and area, and the promotion of construction throughout the county. Influenced by factors such as the main functions of the construction, the requirements of the construction content, and the resource endowment, location, and transportation of the construction area, the internal and external thrust mechanisms of different construction models also exhibit different characteristics. In promoting the construction of digital rural areas in the future, different regions should fully consider the strength of the main functions of the construction, choose different construction mechanisms and content, so that digital rural areas can benefit more farmers, and help promote the comprehensive revitalization of rural areas. However, there are some shortcomings in this paper, such as the lack of in-depth analysis on the role and functional positioning of farmers, different levels of government, and market subject as participants. More wisdom is needed to embed the operation and maintenance mechanism for the later stage of digital rural area construction in future research.
Online Social Spammer Detection Based on Deep Learning | Open Access
ZHANG Jiyang, ZHANG Peng, GONG Siyu, SONG Naipeng
2023, 35(12):  49-59.  DOI: 10.13998/j.cnki.issn1002-1248.23-0813
Asbtract ( 224 )   PDF (1249KB) ( 462 )  
References | Related Articles | Metrics
[Purpose/Significance] The development of the Internet has led to the rapid development of social networks, providing users with a convenient channel for the release, dissemination and acceptance of information. However, its low-threshold characteristics have also given rise to a group of the "Internet water army"--online social spammers, who are paid to post online comments with particular content and spread false information on purpose. They have become a major problem for the Internet ecology. It is of great significance to detect the Internet water army, prevent their malicious attacks, and combat and eliminate their negative effects on the security of the online public opinion. [Method/Process] First, we analyzed the development process and characteristics of the online social spammers, summarized the algorithms used in previous studies and the characteristics mentioned, and sorted out three research starting points: text features, interaction features and graph structure features. Then, an online social spammer detection method based on deep learning was proposed. Combined with the three aspects of user basic information, historical remarks and interaction behavior, six types of features were extracted from the basic information, recent remarks, social intimacy, interaction behavior, microblog number and membership level. Through feature depth extraction and vector splicing and fusion, the user feature vectors were formed with the same length. Finally, a convolutional neural network was used as a classifier to build an automatic, high-precision and high-efficiency spammer detection model. Two Chinese online spammer datasets collected from the Sina Weibo platform were selected for the experiment. The features of the datasets were spliced and aligned to form the Weibo Spammer 2023 dataset as the model training dataset, which prevented the data features of a single dataset from being too discrete and reducing modle generalization. Considering the overfitting problem in the model training process, we solved the problem by adding abandoned layers. [Results/Conclusions] The online spammer detection model constructed in this experiment has significantly improved in terms of metrics such as precision and accuracy. At the same time, the ablation experiment shows that the six features extracted in this experiment have a positive effect on the detection process. Through empirical analysis, the model constructed in this paper has a high detection accuracy and detection efficiency, which can provide certain technical support and theoretical guidance for online spammer identification. By using machine learning methods to actively identify online social spammer accounts, real-time monitoring and prevention of key spammer accounts can prevent the occurrence of malicious network events more timely and effectively and reduce the risk of illegal forces damaging the public opinion ecology.
Value, Current Situation, Difficulties, and Countermeasures of Reading Leader Service in Public Libraries under the High Quality Development of National Reading | Open Access
FAN Xinmei
2023, 35(12):  60-70.  DOI: 10.13998/j.cnki.issn1002-1248.23-0472
Asbtract ( 80 )   PDF (1164KB) ( 58 )  
References | Related Articles | Metrics
[Purpose/Significance] The report of the 20th National Congress of the Communist Party of China proposed the task of "deepening the activities of reading for all", pointing out that reading for all has entered a stage of high-quality development. As an important force to promote reading for all, library readers play an important role in promoting reading, improving cultural quality, and cultivating reading fashion. Improving the delivery ability and quality of reading services will be conducive to promoting the high-quality development of reading for all, helping the high-quality development of reading for all to deepen and consolidate the cultural foundation of Chinese path to modernization. This article aims to study the direction and strategies for improving reading services from different perspectives and dimensions and provide theoretical support and practical reference for the high-quality development of reading promotion. [Method/Process] This article elaborates on the core of high-quality development of reading for all, and analyzes the significance and value of improving library reader services. At the same time, a survey was conducted through online surveys, literature searches, and other methods to investigate the status of reading leader services provided by 32 libraries and cultural institutions nationwide. Based on the survey results, research was conducted on the current status of the reading leader services, with a focus on the obstacles in the development of the services, as well as issues such as a lack of coordination and sufficiency. The problems and difficulties in the services were pointed out. [Results/Conclusions] Current reading leaders lack the introduction of evaluation mechanisms and their own accumulation is insufficient. The reading service method is outdated and the content is homogeneous. The service neglects the essence of segmented reading and deviates from the heterogeneous needs of the audience. There is a lack of community reading linkage and inability to form resource synergy. Based on these findings, several solutions are proposed: establishing a system for reading leaders, improving reading standards and strategies, building a resource library for reading leader projects, creating a "think tank" for reading services, carrying out community reading linkage, building a synergy of reader resources, emphasizing graded reading services, accurately matching the internal needs of readers, establishing high-quality content IPs, building a brand power for reading services, accurately tracing reading portraits, and optimizing content side presentation and utilizing opinion leaders to expand communication influence. Undoubtedly, there are still issues with incomplete case studies in this article, and more in-depth research and analysis will be conducted in the future.
Model of Cooperation between University Libraries and Social Organizations for the Integration of Culture and Tourism Development | Open Access
XU Zhao, PENG Juyuan, DUAN Juanjuan
2023, 35(12):  71-83.  DOI: 10.13998/j.cnki.issn1002-1248.23-0769
Asbtract ( 73 )   PDF (1422KB) ( 63 )  
References | Related Articles | Metrics
[Purpose/Significance] The report of the 20th National Congress of the Communist Party of China pointed out that the in-depth integrated development of culture and tourism should follow the principle of shaping tourism with culture and highlighting culture with tourism. As an integral part of the public cultural service system, university libraries and social organizations cooperate with each other to form a common force that contributes to promoting the inheritance and innovation of excellent culture, enhancing cultural confidence, and promoting the high-quality development of culture and tourism integration. [Method/Process] This study elaborates on the necessity of jointly building and empowering the development of cultural and tourism integration between university libraries and social organizations. At the same time, it introduces a new model of cooperation between university libraries and social organizations based on the theory of full life-cycle project management, and systematically analyzes the characteristics and management mechanisms of project management under this model. Based on this, it takes the practice of strengthening culture and tourism integration through cooperation between Hainan Normal University Library and social organizations as an example, and summarizes the effectiveness and characteristics of their cooperation. [Results/Conclusions] Based on the characteristic literature resources, university libraries cooperate with social organizations to jointly promote the innovation practice of local cultural construction, which has strengthened the inheritance and innovation of local characteristic culture to a certain extent. However, due to the different cooperation projects, the specific practice process and effectiveness are also very different. It is necessary to standardize the management process and further refine the cooperation strategies for the characteristics of different social organizations. Therefore, in connection with the actual cooperation between the Shanghai Normal University Library and social organizations, starting from the project cooperation process, university libraries should pay attention to the following issues: clarifying service positioning, strengthening the selection of cooperation organizations; integrating advantageous resources and improving service project management; ensuring service effectiveness and optimizing the connotation of cooperation projects; innovating service forms and deepening the promotion of cooperation achievements..
AIGC Technology Enables Innovative Applications in Library Reading Promotion | Open Access
LI Peng, SONG Xigui
2023, 35(12):  84-93.  DOI: 10.13998/j.cnki.issn1002-1248.23-0831
Asbtract ( 205 )   PDF (4849KB) ( 301 )  
References | Related Articles | Metrics
[Purpose/Significance] Reading promotion has been a basic and normalized activity in libraries, and has been carried out for many years. Although it has achieved remarkable results in promoting the dissemination of knowledge and culture, it has reached a developmental bottleneck that urgently requires innovative breakthroughs. The introduction and application of artificial intelligence generated content (AIGC) technology can innovate the content and form of the library work, and promote the connotative development of library services. Currently, there is limited research on the application of AIGC in library reading promotion, with most studies focusing on theoretical discussions of work scenarios rather than practical applications. The aim of this article is to explore new technology applications in new scenarios to help solve common problems in the field. [Method/Process] Through literature research and case analysis, based on the characteristics of AIGC content, we look forward to AIGC empowering library reading promotion scenarios, including inspiring activity creativity, and enriching work forms; creating reading IP, and forming work brands; promoting in-depth and professional reading, and optimizing work content; strengthening service management, and promoting the construction of work evaluation standards. Taking the "New Book Recommendation" activity as an example, we analyze work application elements such as planning, promotion, organization, and evaluation, and construct a work model suitable for the scenario. [Results/Conclusions] Although AIGC has great potential and broad prospects for application in library reading promotion, it faces many application challenges, such as the need for a change in librarians' work mindset, issues of data privacy and ethics, and the quality and accuracy of generated content. This paper discusses the application paths of AIGC in library reading promotion, including strengthening skills training to comprehensively enhance librarians' new literacy in the AI era; exploiting the role of "AI prompter" to deepen reading services; building a rich database of event data corpora to ensure digital content generation; and improving rules for content review and quality control. Compared to other information resource management tasks, such as reference consulting and academic services, the impact of AIGC is relatively mild. AIGC is applied as a tool for reading promotion, with librarians remaining the primary actors, and the implementation of work elements is still carried out within the existing work framework. The discussion of AIGC applications in library reading promotion practice in this paper offers methodological insights for library reading promotion, with scenario elaboration, model construction, and path generation facilitating the realization and broad application of these related services. The limitation of this study, however, is the lack of concrete data on the effectiveness of the work discussed, which requires further research.
Security Strategy of Scientific and Technological Literature Resources in Western Regions of China | Open Access
WANG Yuefei, LU Yao, YUAN Xue, WANG Ting, LIU Hongbing
2023, 35(12):  94-103.  DOI: 10.13998/j.cnki.issn1002-1248.23-1020
Asbtract ( 62 )   PDF (1164KB) ( 30 )  
References | Related Articles | Metrics
[Purpose/Significance] As an important strategic information resource, scientific and technological (S&T) literature is increasingly valued by countries around the world. The construction of information resource security systems has become one of the important indicators for measuring national competitiveness. The National Science and Technology Literature Center (NSTL) is a model for the joint construction and sharing of S&T literature resources in China. In the current era of vigorously promoting the western development strategy, NSTL, as a strategic guarantee institution for national S&T literature resources, actively conducts research on resource security and joint construction and information sharing mechanisms in the western regions of China to support the social and economic development of the regions. It has formulated relevant action plans that are practical for the western regions, which is of positive significance and plays an important role in supporting the national western development strategy. [Method/Process] Taking the western provinces of Xinjiang, Qinghai, and Tibet as examples, this study has analyzed the publication situation based on the Dimension database, comprehensively surveyed and analyzed the types of S&T literature resource demands, potential demands, barriers to accessing S&T literature resources, and the current status of joint construction and resource sharing in the three western provinces. The paper output, discipline and field distribution of users in these western provinces were summarized. The study also analyzed the citation situation to summarize the discipline demand characteristics of users in the region, the distribution of publishers of demanded resources, and conducted research on the joint construction and information sharing status of publishing institutions and their resources. [Results/Conclusions] Based on the analysis of the situation of users in these western provinces, the demand for resources, and the current status of resource joint construction and information sharing, this study proposes the NSTL western region S&T literature resource security strategy, which includes proposals for joint construction of resources and information sharing. This includes focusing on securing much-needed discipline resources in the western provinces, selecting specific areas to pilot the opening of specific resources, establishing specialized resource repositories for the western provinces, and utilizing alliances or systems of NSTL member units to provide relevant resources to the western provinces of China.