Most Read

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

An Exploration of the Data Assetization Paths for the Three Major Types of Data Ma Feicheng　Sun Yujiao　Xiong Siyue　Wang Wenhui Journal of Information Resources Management    2024, 14 (5): 4-13.   DOI: 10.13365/j.jirm.2024.05.004 Abstract （812）      PDF（pc） （6613KB）（1052）       Knowledge map    Save Data assetization is a key stage in grasping digital opportunities, realizing the value of data, and promoting the digital transformation of the economy and society. This paper argues that public data, enterprise data and personal data are the major subjects of data elements. However, current research on the realization path of data assetization for the three major types of data is insufficient, hindering the release of the value of data elements. In this paper, we systematically review the relevant concepts of data assets, and delve into the path of data assetization from the three major data subjects: public, enterprise and individual. The results shown that public data can serve internal government needs or be supplied to the society, generating social benefits or economic benefits through sharing and opening, and authorized operation, thus forming public data assets. Enterprises, depending on whether they hold data ownership, can carry out different degrees of processing and handling of data, so as to complete the deep excavation of data value and redistribution of data benefits, forming inventory, intangible assets and other types of data assets. The practice related to personal data assetization is limited, mainly relying on two paths: direct transaction between suppliers and demanders or entrusted transaction by data intermediaries to complete market circulation and form personal data assets. Through in-depth exploration of this topic, this study aims to provide theoretical guidance and practical reference for the value realization of data elements and the effective allocation of data resources. Related Articles | Metrics | Comments（0）

Select

A Review of Research on Elderly-oriented Digital Products: Demand Mining, Obstacle Analysis and Optimal Design Lin Yuqin　Zhao Yang　Liu Wanting　Wang Lin Journal of Information Resources Management    2024, 14 (4): 146-160.   DOI: 10.13365/j.jirm.2024.04.146 Abstract （749）      PDF（pc） （4159KB）（6744）       Knowledge map    Save The "digital divide" exacerbated by the simultaneous development of population aging and social digitization has become increasingly severe, prompting a focus on the research and design of elderly-oriented digital products within both industry and academia. Using a systematic review approach, this study analyzes 348 research articles on elderly-oriented digital product design indexed in CNKI and Web of Science from 2014 to 2023. It explores the research progress and developing trend of the demand mining, usage obstacles, and optimal design of digital products for elderly users. The findings reveal that research on elderly users' needs mainly focuses on the three levels of material, emotional and spiritual needs, with significant focus on sensory barriers, cognitive barriers, behavior barriers and psychological barriers in product usage. The study investigates elderly-oriented design through various lenses, including design standards, optimization countermeasures, and usability testing. Future research should further consider the evolving nature of digital products and demographic trends by enhancing the methods for sample collection, innovating research methodologies, and expanding the content of studies. The findings of this study provide valuable references for identifying research priorities in elderly-oriented digital product adaptation, spotlighting emerging areas, advancing theoretical frameworks, and also offer practical insights for the proactive development of an age-friendly digital society. Related Articles | Metrics | Comments（0）

Select

Reflections on Construction of Information Resources in University Libraries Serving National Strategies in the Era of Open Science Huang Ruhua　Shi Leyi Journal of Information Resources Management    2024, 14 (4): 16-28.   DOI: 10.13365/j.jirm.2024.04.016 Abstract （710）      PDF（pc） （907KB）（1008）       Knowledge map    Save The arrival of the open science era has changed the information environment and scholarly communication system, and has also brought new opportunities and challenges to the construction of information resources in university libraries. Based on the national strategies of becoming a leading country in education, science and technology, talent, culture and so on, construction of information resources in Chinese university libraries urgently needs to achieve high-quality development on the basis of serving multiple national strategies. This article proposes countermeasures in four aspects, including: constructing information resources that are consistent with a holistic approach to national security, constructing information resources system needed for the digitalization of Chinese higher education, consolidating the information resource foundation for great self-reliance and strength in science and technology, and strengthening information resource support needed for construction of philosophy and social sciences with Chinese characteristics. Related Articles | Metrics | Comments（0）

Select

Trends and Future Prospects in Sentiment Analysis of Financial Reviews Texts Wu Jiang　Duan Yiqi Journal of Information Resources Management    2025, 15 (1): 86-101.   DOI: 10.13365/j.jirm.2025.01.086 Abstract （649）      PDF（pc） （5622KB）（1515）       Knowledge map    Save This study surveys recent advancements in sentiment analysis of financial review texts, both domestically and internationally, to delineate the field’s developmental trajectory. Adopting dual perspectives of technology-driven and content-driven approaches, it scrutinizes prevailing research trends. Technologically, the evolution from lexicon-based methods, through traditional machine learning, to deep learning paradigms is summarized. Content-wise, BERTopic and LLaMA3 are employed for document clustering based on scholarly viewpoints, with dynamic topic modeling elucidating domain progress. Findings indicate a domestic transition from sentiment analysis methods to investigations of emotional impacts on financial market prediction. Meanwhile, international research continues progressing deep learning applications while revealing emerging interests in financial sentiment modeling. By integrating these observations, the paper proposes future directions including: (1)constructing high-quality datasets, (2)conducting granular sentiment analysis of financial discourse, and (3)improving the interpretability of analytical outcomes. These recommendations aim to establish methodological foundations for subsequent studies in this field. Related Articles | Metrics | Comments（0）

Select

Research on New Quality Productive Forces Driving High-Quality Development of Digital Economy Ma Feicheng　Sun Yujiao　Xiong Siyue Journal of Information Resources Management    2025, 15 (1): 4-12.   DOI: 10.13365/j.jirm.2025.01.004 Abstract （643）      PDF（pc） （1353KB）（515）       Knowledge map    Save New quality productive forces, emerging from a new wave of scientific and technological revolution and industrial transformation, align with China's domestic strategic blueprint and the practical needs arising from international competitive dynamics. With digital economy becoming a pivotal force in global economic and social transformation, promoting its high-quality development has become a strategic imperative for China's economic development in the new era. This research investigates how new quality productive forces drive the high-quality development of digital economy, which holds significant implications for advancing productivity theory, understanding digital era development patterns, and facilitating economic transformation. The study first explored the evolutionary context of new quality productive forces, systematically examined its theoretical underpinnings from three dimensions of "newness," dual implications of "quality," and intrinsic characteristics of "productive forces," and analyzed its practical features. Building upon this foundation, the research revealed from a theoretical perspective how new quality productive forces drive the high-quality development of digital economy, identifying three inherent mechanisms: new technology stimulated new growth drivers, new elements reshaped production relations, and new industries reconstructed competitive landscape. Finally, the research proposed five implementation paths: improving institutional supply, strengthening talent cultivation, unleashing element value, promoting coordinated regional development, and deepening opening up. This study aims to provide theoretical guidance and practical insights for promoting the high-quality development of digital economy. Related Articles | Metrics | Comments（0）

Select

Research on Large Language Model Evaluation for the Generation Task of Natural Language Processing in Classical Chinese Zhu Danhao　Zhao Zhixiao　Zhang Yiping　Sun GuangYao　Liu Chang　Hu Die　Wang Dongbo Journal of Information Resources Management    2024, 14 (5): 45-58.   DOI: 10.13365/j.jirm.2024.05.045 Abstract （598）      PDF（pc） （3124KB）（2426）       Knowledge map    Save The rapid development of large language models (LLMs) presents both opportunities and challenges for their evaluation. While evaluation systems for general-domain LLMs are becoming more refined, assessments in specialized fields remain in the early stages. This study evaluates LLMs in the domain of classical Chinese, designing a series of tasks based on two key dimensions: language and knowledge. Thirteen leading general-domain LLMs were selected for evaluation using major benchmarks. The results show that ERNIE-Bot excels in domain-specific knowledge, while GPT-4 demonstrates the strongest language capabilities. Among open-source models, the ChatGLM series exhibits the best overall performance. By developing tailored evaluation tasks and datasets, this study provides a set of standards for evaluating LLMs in the classical Chinese domain, offering valuable reference points for future assessments. The findings also provide a foundation for selecting base models in future domain-specific LLM training. Related Articles | Metrics | Comments（0）

Select

Research on Algorithm Embedding and Visibility Mechanism：A Platform Affordance Perspective Du Yan　Xie Xinzhou Journal of Information Resources Management    2024, 14 (5): 91-103.   DOI: 10.13365/j.jirm.2024.05.091 Abstract （576）      PDF（pc） （4260KB）（620）       Knowledge map    Save Given the increasing relevance of algorithms, how to implement the main responsibility of platforms has become a focal issue. Based on the perspective of affordance theory, the study analyzes the relationship between algorithms, the platform environment, and user perception through mixed research methods to clarify the role of platforms in the process and the problems that arise. The research results show that the algorithm reshapes the platform environment through specific encoding programs, multi-objective optimization, and billions of feature vector combinations. For ordinary users, the algorithm is invisible, uneditable and inaccessible. The platform initially constructs the visibility mechanism of the algorithm through interface cues, but the effect is limited. The research, combined with the embedding logic of the algorithm, provides policy recommendations to promote user algorithmic knowledge, which has certain theoretical and practical significance. Related Articles | Metrics | Comments（0）

Select

A Multinational Comparative Study of Regulatory Policies for Generative AI from the Perspective of “Tools-Structure” Deng Shengli　Ding Weiwei　Wang Fan　Wang Haowei Journal of Information Resources Management    2025, 15 (1): 54-68.   DOI: 10.13365/j.jirm.2025.01.054 Abstract （568）      PDF（pc） （4448KB）（1812）       Knowledge map    Save Based on the dual perspective of policy tools and structural characteristics, this study takes the regulatory policies of generative AI in different countries as the research object, aiming to explore the structural characteristics and internal connections of the policy elements of generative AI, in order to promote the healthy development of generative AI. A total of 14 effective policy texts were collected, and 327 relevant text units were coded and interpreted using bibliometrics, content analysis, and BERTopic. The structural characteristics were analyzed from three dimensions: policy issuance time, policy issuance subject, and policy theme characteristics. The role paths were discussed by dividing into three types of policy tools: environmental, demand-driven, and supply-driven. The findings show that the regulation of generative AI is still in its infancy, and there are significant differences in the overall characteristics of policies among different countries, with significant differences in the regulatory level. Overall, the role path of policy tools is mainly dominated by the indirect role of environmental policy tools, showing a structural imbalance and bias in the role path. Further comparison of the similarities and differences in regulatory policies among different countries is conducted, and corresponding countermeasures and suggestions are put forward to optimize the policy tool structure, balance the role path of policy tools, assessing the effectiveness of policy implementation, and promote the coordinated development of the generative AI regulatory system. Related Articles | Metrics | Comments（0）

Select

Research on the Copyright Dilemma and Solution Path of Generative Artificial Intelligence Using Previous Works Liu Zubing Journal of Information Resources Management    2024, 14 (5): 147-158.   DOI: 10.13365/j.jirm.2024.05.147 Abstract （564）      PDF（pc） （859KB）（725）       Knowledge map    Save The rapidly development and embedded applications of generative artificial intelligence pose challenges to the existing copyright system. Generative artificial intelligence normalizes the crawling of massive amounts of prior work data, inducing infringement risks. Long distance text semantic understanding ability is intended to cover up infringement traces, and open cross domain generalization reasoning ability provides technical convenience for infringement. In terms of data feeding in works, generative artificial intelligence may cross the boundaries of fair use systems or lead to the extreme of unprotected or overprotected rights in previous works; In terms of copyright-ability of generated content, generative artificial intelligence decouples copyright subjectivity with its high-quality and massive generation ability, meeting the "minimum creative standards" and originality requirements. Propose to establish an endorsement system for the use of prior works to address the problem of rational use of algorithms; Promote the horizontal transition from "author centrism" to "work centrism", and shift the author's rights law starting from personality rights to copyright law starting from property rights; Establish an interpretable generative artificial intelligence originality evaluation mechanism and reinterpret originality standards. Related Articles | Metrics | Comments（0）

Select

Evolutionary Characteristics of the Interdisciplinary Research in Scientific Breakthrough Topics Yang Junhao　Xu Haiyun　Wang Chao　Liu Chunjiang　Zhang Huiling　Tan Xiao Journal of Information Resources Management    2024, 14 (4): 70-85.   DOI: 10.13365/j.jirm.2024.04.070 Abstract （537）      PDF（pc） （12975KB）（99）       Knowledge map    Save The paper explores the impact of interdisciplinary collaboration on scientific breakthroughs at the granularity of research topics, advancing our understanding of the driving mechanisms behind scientific breakthroughs. By analyzing the dynamic characteristics of temporal data, it unveils the breakthrough potential of emerging research topics and their interdisciplinary features. Specifically this paper initially identifies scientific breakthrough topics based on emerging research topics and examines their interdisciplinary characteristics. Furthermore, the consistency in the increase and decrease evolutionary trends in the number of citations and the number of cross-disciplinary documents on scientific breakthrough topics and their knowledge base documents is analyzed. Finally, it measures the predictive causal relationship between the citation count of scientific breakthrough topics and their interdisciplinary quantity time series, thus investigating the association between the emergence of scientific breakthroughs and interdisciplinarity. Using stem cells research as a case study, this empirical research categorizes the interdisciplinary characteristics of scientific breakthrough topics into three categories. Results show that there is a great consistency between the scientific breakthrough topics and the knowledge base in the increase and decrease evolutionary trends in the number of citations and interdisciplinary quantity. However, the predictive causal relationship between the citation time series of most scientific breakthrough topics and the time series of interdisciplinary is not significant. Therefore, relying solely on the interdisciplinary quantity metric may not effectively identify or predict scientific breakthrough topics. The paper provides valuable insights to better understand the characteristics of scientific breakthrough research. Related Articles | Metrics | Comments（0）

Select

The Realization of Data Value in the Collaborative Development of Digital Industrialization and Industrial Digitization Ma Feicheng　Wang Wenhui　Sun Yujiao　Xiong Siyue Journal of Information Resources Management    2024, 14 (4): 4-15.   DOI: 10.13365/j.jirm.2024.04.004 Abstract （527）      PDF（pc） （1513KB）（602）       Knowledge map    Save The collaborative development of digital industrialization and industrial digitization is crucial for driving economic transformation and upgrading. However, existing research lacks in-depth exploration of the collaborative relationship between digital industrialization and industrial digitization. This study, based on the data value chain, elucidates four forms of data value: data resources, data assets, data commodities, and data capital. It further reveals the relevance of digital industrialization and industrial digitization for the two types of data, industrial data and government data. Additionally, it analyzes the evolution process of data element value and the value realization stages in the collaborative development of digital industrialization and industrial digitization. The study demonstrates that the collaborative development of the digital economy consists two value realization processes: the leap from data assets to data commodities and the evolution from data commodities to data capital. To promote the collaborative development of the digital economy, it is necessary to reshape and upgrade both digital and traditional industries by combining the transformation of data element value. Through in-depth analysis of the collaborative development of digital industrialization and industrial digitization, this study enhances the understanding of data element value realization and comprehension of the laws governing digital economic development, providing valuable insights for research in this field. Related Articles | Metrics | Comments（0）

Select

The Inherent Attributes of Artificial Intelligence Generated Content(AIGC) and Its Impact on the Discipline of Information Resources Management Zhu Yu　Chen Guanze　Ye Jiyuan Journal of Information Resources Management    2024, 14 (6): 60-72.   DOI: 10.13365/j.jirm.2024.06.060 Abstract （491）      PDF（pc） （1088KB）（608）       Knowledge map    Save The inherent attributes of the concept of Artificial Intelligence Generated Content(AIGC) remains a matter of contention within the field of library and information science/ information resources management(IRM). As the issue is closely related to the core research content of IRM research, delving into this problem is significant to understand the key research areas of the discipline, with a focus on AIGC research and a moderate expansion of the disciplinary scope. This study utilized both conceptual and comparative analysis methods to investigate the inherent attributes of AIGC and its related concepts, analyzing the information resources characteristics of AIGC from three perspectives, namely, knowledge philosophy, practical needs, and disciplinary construction, thus proving the necessity of incorporating AIGC into IRM research. Moreover, this study demonstrated the rationality through an analysis of AIGC’s source technology and an examination of the information chain, leading to a renewed understanding within the framework of IRM. Notably, this study clearly identified the inherent attribute of AIGC as the value of information resources, which is one of the core research content of IRM discipline. Additionally, it presented 6 pressing research topics on AIGC for the field of IRM to address. Related Articles | Metrics | Comments（0）

Select

Construction of the Whole Process Field of Data Element Circulation for the High-quality Development of Digital Economy Ma Haiqun　Liu Xinrui Journal of Information Resources Management    2024, 14 (4): 29-35.   DOI: 10.13365/j.jirm.2024.04.029 Abstract （449）      PDF（pc） （2351KB）（662）       Knowledge map    Save Based on the major strategic needs of the deepening development of the national digital economy, the construction of a full-process field for the circulation of data elements will help improve the overall efficiency of the release of the value of data elements and their transaction circulation, and accelerate the standardization of China's data element market. Related Articles | Metrics | Comments（0）

Select

Generation AI in Human-AI Interaction: Origins, Characteristics and Future Prospects Xu Hao　Cheng Qingxuan　Dong Jing　Wu Dan　Tian Li Journal of Information Resources Management    2025, 15 (1): 13-20.   DOI: 10.13365/j.jirm.2025.01.013 Abstract （448）      PDF（pc） （2333KB）（1467）       Knowledge map    Save The rapid development of artificial intelligence is driving society toward a new era of human-AI interaction (HAII) and reshaping a new generation of minors growing up with AI—Generation AI. This paper reviews the origins and evolution of human-computer interaction (HCI), examining the shift from HCI to HAII, and focuses on the unique traits of Generation AI in this context. By analyzing the interaction modes and characteristics of Generation AI, the study reveals their distinctive attributes in HAII scenarios, including intelligent perception, social contention, and digital embedding across all settings, timeframes, and environments. Finally, the paper envisions the future of human-AI synergy for Generation AI from three perspectives: human-centered design, multimodal interaction, and augmented collaboration, providing a theoretical foundation for building a smart and human-centered society. Related Articles | Metrics | Comments（0）

Select

Data Production: Concepts, Scenarios, Technologies and Reflections Hu Guangwei　Fan Zhaoyuan Journal of Information Resources Management    2024, 14 (5): 14-21.   DOI: 10.13365/j.jirm.2024.05.014 Abstract （437）      PDF（pc） （3318KB）（866）       Knowledge map    Save Digital transformation offers significant opportunities for the development of the economy and society while also presenting numerous challenges. Issues such as the source of data, continuous supply, cultivation of core data capabilities, and the urgent need to explore data production scenarios and technologies await discussion. By discussing the concept, structure, characteristics, scenarios, and technologies of data production, we hope to draw the attention of both the theoretical and practical sectors to the new business forms of data production, promote the development of new productive forces such as digitalization, intelligentization, and wisdomization, and serve the modernization of China’s digital transformation and governance capabilities. Related Articles | Metrics | Comments（0）

Select

Personal Information Protection Misconducts in the Era of Digital Intelligence: An AIGC-Assisted Grounded Theory Analysis Zhao Haiping　Liu Zhixin　Sun Yanchao　Jiang Na Journal of Information Resources Management    2024, 14 (4): 59-69.   DOI: 10.13365/j.jirm.2024.04.059 Abstract （427）      PDF（pc） （1491KB）（982）       Knowledge map    Save The extensive collection and deep utilization of personal information in the era of data intelligence highlight the significance of identifying misconducts in personal information protection. This study, guided by the current personal information protection laws and regulations, qualitatively analyzed 2100 cases of violations of laws. It aimed to identify common prevailing misconducts in safeguarding personal information during data processing activities. AIGC technology was introduced in the analytical process of Grounded Theory to categorize the identified misconducts. As a result, we identified eleven major categories and fifty-five subcategories of personal information protection conducts. We then particularly discussed key issues in personal information protection in the age of data intelligence. The findings of this study can not only offer a theoretical framework for future research in the field of personal information protection but also provide decision support for various organizations and government regulatory authorities. Related Articles | Metrics | Comments（0）

Select

Research on Online Public Opinion Guidance and Control of Major Emergencies from the Perspective of Actor Network：Analysis Based on the Hybrid Method of SD and fsQCA Li Ming　Hou Tiantian Journal of Information Resources Management    2024, 14 (5): 104-115.   DOI: 10.13365/j.jirm.2024.05.104 Abstract （424）      PDF（pc） （5326KB）（855）       Knowledge map    Save The occurrence of major emergencies often leads to a surge in online public opinion, making the effective guidance and control of such opinions a significant challenge in current public opinion management. From the perspective of actor-network theory, this study constructs an analysis framework for guiding and controlling online public opinion, which includes actors such as events, media, netizens, and government. A system dynamics model is employed to simulate the mechanism of online public opinion guidance and control for major emergencies. Through sensitivity analysis, the key influencing factors are identified. Based on this, the fuzzy set qualitative comparative analysis (fsQCA) method is applied to analyze the conditions configuration to explore effective pathways for online public opinion guidance and control in major emergencies. This study reveals that the severity of the event, the intensity of media coverage, the emotional intensity of netizens, and the level of government attention play crucial roles in guiding public opinion. It is essential to further strengthen the ability to analyze complex influencing factors, emphasize the roles of media and netizen actors, and enhance the organic linkage and effective collaboration between government attention and various actors to ultimately achieve effective guidance and control of online public opinion in major emergencies. Related Articles | Metrics | Comments（0）

Select

Information Reach: Influence of the Language Expression of Disaster Warning Message Wang Fang　Hu Qiandai　Ma Xin Journal of Information Resources Management    2024, 14 (4): 36-51.   DOI: 10.13365/j.jirm.2024.04.036 Abstract （424）      PDF（pc） （1739KB）（1745）       Knowledge map    Save In the context of natural disasters, as one of the key factors affecting the effectiveness of emergency management, the effective reach of emergency pre-warning messages is of significant value to enable the target audience to prepare in advance and mitigate disaster losses. To investigate the impact of information expression on the reach of emergency pre-warning messages, this study, based on prospect theory and reference point effect, employed an experimental research method to collect self-reported perception and behavioral data from the audience of pre-warning messages in the context of urban rainstorm disaster. The influences of the information expressions including different reference points on the effectiveness of information arrival were examined. The results indicated that information expression designed based on different reference points has different effects on the reach of disaster pre-warning messages. Specific information reference points and social comparison reference points significantly affect the audience's perception of disaster severity and risk, while the negative impact reference point does not have a significant effect. Furthermore, cognitive load affects the reach of information that contains both comprehensive reference points and specific information reference points related to disaster prevention measures. This study advances the research on information reach theory and has significant implications for improving government information expression, enhancing the effectiveness of disaster pre-warning messages delivery. Related Articles | Metrics | Comments（0）

Select

Identifying Technology Opportunities from High-Value Patents in Universities: The Case of Generative Artificial Intelligence Ran Congjing　Li Wang　Huang Wenjun Journal of Information Resources Management    2024, 14 (4): 103-116.   DOI: 10.13365/j.jirm.2024.04.103 Abstract （407）      PDF（pc） （2703KB）（2359）       Knowledge map    Save This study proposes a method for identifying technological opportunities of high-value patents in colleges and universities, using theme modeling, mutation level method, machine learning and outlier detection algorithms to further identify technological themes and patented technologies with potential technological opportunities on the basis of evaluating high-value patents in colleges and universities. Taking the field of "Generative Artificial Intelligence" as an example for empirical evidence, the results show that the potential technology themes in the field of "Generative Artificial Intelligence" are centered on cutting-edge areas such as deep learning, neural networks and machine learning, and AI imaging and AI diagnosis and treatment are potential technological opportunities in this field, and the above technologies are vigorously supported by relevant national policies. This method can break through the core problems such as poor targeting of the identification results of a single technology opportunity identification method, low value of the identified patents, and a single form of the identification results, and the relevant identification results can provide decision-making support for the technology transfer, technology research and development, and technological innovation of universities. Related Articles | Metrics | Comments（0）

Select

Research and Design of General Knowledge Model of Ancient Books Chen Tao　Zhao Xiaofei　Yang Xin　Lin Lixin Journal of Information Resources Management    2025, 15 (1): 139-153.   DOI: 10.13365/j.jirm.2025.01.13 Abstract （401）      PDF（pc） （8021KB）（72）       Knowledge map    Save China boasts a vast collection of ancient books. While the traditional organization and management mode of ancient books has facilitated the transformation of ancient book resources from "collection" to "use", the "raw resources" are increasingly unable to meet the needs of ancient book utilization in the digital era. This paper investigates and analyzes the reusable ontology model for ancient book knowledge organization, reviews the perspectives and approaches to knowledge modeling of ancient books, and proposes a five-layer framework for a general knowledge model of ancient books based on the two dimensions of form and content characteristics. To verify the usability of the model, this paper takes the "Hu Zi Book" of the Yongle Encyclopedia as an example, constructs an associated dataset, explores the knowledge graph of ancient books by integrating associated data, and realizes the combination of knowledge association and data aggregation.This paper constructs a general knowledge organization model for ancient books, providing an alternative approach for the association and aggregation, inference and calculation, dissemination and sharing, and intelligent application of ancient book knowledge. Related Articles | Metrics | Comments（0）

Select

A Study on Automatic Categorization of the Siku Quanshu Based on a Large Language Model Zuo Liang　Zhao Zhixiao　Wang Dongbo Journal of Information Resources Management    2024, 14 (5): 23-35.   DOI: 10.13365/j.jirm.2024.05.023 Abstract （395）      PDF（pc） （2258KB）（979）       Knowledge map    Save The craze of ancient book research and the contemporary requirement of ancient book revitalisation have raised higher requirements for automatic classification of ancient books. This study explores the classification effect of Xunzi large language series models on the automatic classification of ancient books by combining the large language model along the current preface with the 25 categories of corpus from the history and scripture sections of the Siku Quanshu as the input corpus.Through the comparison experiments with its base model, the results show that Xunzi large language models for ancient books have obvious advantages in the automatic classification task of ancient books, among which the Xunzi-Baichuan2-7B large language model has the most significant advantage in the automatic classification task of ancient books, and the overall classification F1 value reaches 96.90%. In addition, the experiments of adjusting the training data size show that the Xunzi-Baichuan2-7B large language model is able to achieve comparable classification results with the base model with only a small amount of data. Therefore, the automatic classification model for ancient books based on Xunzi large language models for ancient books proposed in this study can achieve efficient fine-grained classification of ancient books and opens up a new way for the classification of ancient books in resource-constrained contexts. Related Articles | Metrics | Comments（0）

Select

Government Data Openness Level Measurement, Regional Difference Decomposition and Dynamic Evolution：Evidence from 21 Provinces Gao Fan　Xu Sijia　Li Yiheng Journal of Information Resources Management    2024, 14 (5): 59-74,90.   DOI: 10.13365/j.jirm.2024.05.059 Abstract （395）      PDF（pc） （5908KB）（305）       Knowledge map    Save This study delves into the overall differences, regional differences, and dynamic evolution trends of interprovincial government data openness in China, with the aim of narrowing these differences, promoting balanced development in government data openness, and accelerating the digital transformation of government. Based on the Chinese Government Data Openness Evaluation Reports, the study employs the panel entropy method to calculate the comprehensive index of government data openness and four sub-dimensional indices across 21 provinces. Additionally, the study utilizes the Dagum Gini coefficient and Kernel Density Estimation to analyze the regional differences and evolution trends of government data openness across different regions. The findings reveal that the level of government data openness in China is on the rise, with significant and gradually widening regional differences. The differences across the four sub-dimensions vary, and except for the western region, the absolute differences between the eastern and central regions are expanding. This study innovatively applies the Gini coefficient to the theme of government data openness and equilibrium and integrates the entropy method, Dagum Gini coefficient, and Kernel density estimation to provide a progressive and comprehensive analysis of the overall differences, regional disparities, and future evolution dynamics of government data openness. Related Articles | Metrics | Comments（0）

Select

The Theoretical Logic and Implementation Path of Digital Industrialization Ma Feicheng　Wang Chunyang Journal of Information Resources Management    2024, 14 (6): 4-16.   DOI: 10.13365/j.jirm.2024.06.004 Abstract （384）      PDF（pc） （1268KB）（707）       Knowledge map    Save Digital industrialization is the core foundation of the digital economy, exerting profound impacts on both the economy and society. This paper first reviews the concepts and measurement methods of digital industrialization and explores its logical development path. Technological innovation and application have transformed the structure and distribution of data, information, and knowledge, leading to the creation of distinctive products and services, which in turn foster the formation of digital industrial chains and clusters. Moreover, digital industrialization integrates with traditional industries, driving their transformation and upgrading. The emergence of new quality productive forces presents significant opportunities for the qualitative transformation of digital industrialization. Building on this foundation, the paper proposes implementation paths for advancing digital industrialization: leading the development of digital infrastructure through "new infrastructure" initiatives, strengthening core technology research and development through original and disruptive technologies, unlocking the potential of data resources through market-oriented reforms in data elements, ensuring a steady supply of digital talent through an improved talent cultivation and recruitment system, fostering digital industrial clusters led by strategic emerging industries, promoting the deep integration of digital industrialization with the real economy through the digital transformation of traditional industries, and unleashing new momentum for digital industrialization by constructing a comprehensive digital industrial ecosystem. This study offers insights into deepening the understanding of digital industrialization and advancing reforms in this critical field. Related Articles | Metrics | Comments（0）

Select

Study on Governance Strategies for Compound Disaster Rumors Xie Zilin　Song Yushan　Shen Kaixin　Weng Wenguo Journal of Information Resources Management    2024, 14 (4): 52-58.   DOI: 10.13365/j.jirm.2024.04.052 Abstract （384）      PDF（pc） （1408KB）（466）       Knowledge map    Save With the continuous development of the Internet and social media, the hazards posed by disasters at the informational level have become a critical concern, and disaster rumors epitomize these hazards. The emergence and spread of such rumors can incite panic among the public and destabilize society, making the control and management of disaster rumors a widely recognized necessity. However, the majority of attention has been directed at typical disaster rumors associated with single types of disasters within isolated hazard scenarios. Compound disaster rumors, which occur in multi-hazard scenarios and involve multiple types of disasters, have not yet received sufficient attention. This study aims to outline the characteristics of compound disaster rumors and propose governance strategies tailored to these complex scenarios. By doing so, it seeks to support and enhance disaster information governance in multi-hazard scenarios. Related Articles | Metrics | Comments（0）

Select

Research on Multi-granularity Knowledge Organization Method for Standard Documents from the Perspective of Knowledge Association Fan Hao　Wang Yifan Journal of Information Resources Management    2024, 14 (4): 133-145.   DOI: 10.13365/j.jirm.2024.04.133 Abstract （382）      PDF（pc） （10721KB）（96）       Knowledge map    Save Traditional document organization methods are inadequate to address the evolving trends of standard digitization. It is essential to uncover the multi-granularity knowledge units and their semantic associations within standard documents, to explore novel organizational methods that can efficiently utilize standard knowledge, and to provide references for optimizing standard provision. From the perspective of knowledge association, this study proposed a multi-granularity, semantically-rich, and universal knowledge organization method for standard documents. Firstly, based on the Knowledge Granularity Theory, knowledge partitioning and description at multiple granularities are carried out according to the knowledge content and requirement characteristics of standard documents. Secondly, the semantic association patterns and types among multi-granularity knowledge units are recognized and discovered from aspects such as knowledge hierarchy, document features, text logic, and spatiotemporal evolution. Finally, the method of ontology construction is employed to achieve multi-granularity knowledge organization of standard documents, and the ontology is validated and its value elaborated through the addition of knowledge instances. The multi-granularity knowledge association method for standard organization can comprehensively reveal the multi-granularity knowledge units within standard documents, forming extensive interconnected knowledge levels and associations. This approach facilitates the effective acquisition, sharing, and reuse of standard knowledge across various service scenarios. It not only advances the construction of standard resources to suit the era of digital intelligence but also enriches the mining and utilization of document content driven by multi-granularity knowledge. Related Articles | Metrics | Comments（0）

Select

Structural Characteristics and Optimization Paths of Data Element Market Policy Text from the Perspective of Policy Instruments Zhao Xuyao　Ji Xiangfei　Zhang Jieni Journal of Information Resources Management    2024, 14 (6): 73-84.   DOI: 10.13365/j.jirm.2024.06.073 Abstract （381）      PDF（pc） （2105KB）（268）       Knowledge map    Save This paper conducts an analysis of local government data element market policy texts in China, aiming to provide theoretical support for the design of China’s data infrastructure system at the policy aspect. The study utilizes policy instruments to construct a two-dimensional framework for analyzing data element market policies based on the four principles outlined in the "Data Twenty". A cross-analysis is performed on 116 locally published policy texts related to the data element market published from 2019 to 2024 in China, revealing their structural characteristics and proposing optimization paths. The research identifies that current data element market policies exhibit features such as excessive use of environmental policy instruments, imbalanced structure systems of policy instruments, uneven utilization of these instruments with respect to policy principles, lack of coordination among internal tool combinations, and inadequate supporting facilities. Consequently, recommendations are made to strengthen supply-push and demand-pull forces, emphasize data property rights and income distribution considerations, leverage precise guidance from policy principles, and enhance ecological system construction for effective application of these policies. Related Articles | Metrics | Comments（0）

Select

The Impact of Regional Technical Criticality and Genericness on Industrial Innovation Performance: A Case Study of the Fuel Cell Vehicle Industry Li Yue　Ma Yaxue　Sun Jianjun Journal of Information Resources Management    2024, 14 (4): 117-132.   DOI: 10.13365/j.jirm.2024.04.117 Abstract （366）      PDF（pc） （5542KB）（1505）       Knowledge map    Save This study investigated the effect of regional technical criticality and genericness on the industrial innovation performance. The findings offer valuable insights for guiding targeted industrial innovation, refining technological development strategies, and optimizing resource allocation. This study took the Chinese Fuel Cell Vehicle industry as the example and represented technical units using 4-digit IPC codes and constructed a multi-layer co-occurrence network that focuses on various segments of the industry chain. This framework enabled the development of metrics to measure technical criticality and genericness, capturing the intricacies of regional technical characteristics. Regional technical advancements were subsequently assessed both temporally and spatially using provincial panel data from China spanning 2010 to 2021. Related Articles | Metrics | Comments（0）

Select

Research on Intelligent Information Processing of Ancient Books under the Large Language Model: Constituent Elements, Framework System, and Practical Path Zhang Hai　Zhao Xue　Wang Dongbo Journal of Information Resources Management    2024, 14 (5): 36-44.   DOI: 10.13365/j.jirm.2024.05.036 Abstract （345）      PDF（pc） （919KB）（441）       Knowledge map    Save With the rapid advancement of large language models (LLMs), there is growing potential for their integration into the intelligent information processing of ancient books. This study seeks to bridge the gap between LLMs and the field of ancient books processing, enhancing the theoretical and technical foundations of the information resource management discipline. Drawing on a coding-based deconstruction method, this study analyzed interviews from 28 domain experts to identify the key factors necessary for effective integration. The analysis reveals a comprehensive framework that centers on four critical dimensions: policy, technology, ancient books, and users. Building on this framework, this study proposes a set of practical paths tailored to the unique demands of the discipline. The findings suggest that these four dimensions are essential to the successful application of LLMs in the domain. Finally, this study offers detailed strategies for implementation across theoretical, technical, and user service, providing a roadmap for future development in this emerging field. Related Articles | Metrics | Comments（0）

Select

Research on Theoretical Framework of Breakthrough Paper Identification Based on Citation Perspective Huang Heng　Wang Xuefeng　Chen Hongshu　Lei Ming Journal of Information Resources Management    2024, 14 (6): 31-44.   DOI: 10.13365/j.jirm.2024.06.031 Abstract （338）      PDF（pc） （4852KB）（930）       Knowledge map    Save No consensus has been reached on the characteristics of breakthrough papers and the theoretical models for their identification. The content analysis method is adopted to analyze the similarities and differences between the characteristics of breakthrough papers and breakthrough research. A conceptual model of breakthrough paper identification is constructed from citation perspective and reflects the impact of breakthrough paper on the citation network and mainstream theories. On this basis, a breakthrough paper generation model is proposed. The influence of knowledge recombination on the originality of breakthrough papers is discussed from backward citation perspective. On the other hand, a breakthrough paper diffusion model is proposed to sort out the different paths of scientific impact cross-domain diffusion of breakthrough papers from forward citation perspective. It is found that breakthrough papers may not necessarily have all the characteristics of breakthrough research. The core characteristics consist of a huge influence on scientific research, challenging mainstream theories and interdisciplinary. The study defines the core characteristics of breakthrough papers. The conceptual model, generation model and diffusion model of breakthrough papers identification are constructed to provide a theoretical basis for the subsequent breakthrough paper identification research. Related Articles | Metrics | Comments（0）

Select

Driving Factors and Mechanism of Online Reverse Social Emotion in Emergencies: A csQCA Analysis Based on 30 Cases Wang Zhongyou Journal of Information Resources Management    2024, 14 (5): 116-131.   DOI: 10.13365/j.jirm.2024.05.116 Abstract （331）      PDF（pc） （1347KB）（478）       Knowledge map    Save This study explores the driving factors and evolutionary mechanisms of online reverse social emotions during emergencies. Utilizing the Qualitative Comparative Analysis (QCA) method, this study applies the theoretical model of amplified propagation of online reverse social emotions to examine thirty emergency cases across three dimensions: netizens, media, and government. The findings indicate that there are eight configurations that exacerbate online reverse social emotions across these three dimensions. Five key factors, such as expression appeal, social equity, continuous reporting, government intervention, and concealment, play critical roles in the evolution of online reverse social emotions. The degree of emergency, mass conformity, opinion leaders, type of media, launch platform, quality of response, and level of government, when combined with key factors, can determine the direction of the evolution of online reverse social emotions. To mitigate online reverse social emotions, it is essential to ensure open channels for expressing appeal, protect the interests of netizens, strengthen media oversight to harness its value-driven role, and fulfill government emergency responsibilities to demonstrate social justice and fairness, thereby severing the pathway for online risks to translate into offline conflicts and preventing social unrest. Related Articles | Metrics | Comments（0）

Select

Construction of Chinese Classical-Modern Translation Model Based on Pre-trained Language Model Wu Mengcheng　Liu Chang　Meng Kai　Wang Dongbo Journal of Information Resources Management    2024, 14 (6): 143-155.   DOI: 10.13365/j.jirm.2024.06.143 Abstract （330）      PDF（pc） （1784KB）（2460）       Knowledge map    Save This study aims to construct and validate a Chinese ancient-modern translation model based on pre-trained language models, providing strong technical support for the research of ancient Chinese and the inheritance and dissemination of cultural heritage. The study selected a total of 300,000 pairs of meticulously processed parallel corpora from the "Twenty-Four Histories" as the experimental dataset and developed a new translation model—Siku-Trans. This model innovatively combines Siku-RoBERTa(as the encoder) and Siku-GPT(as the decoder), designed specifically for translating ancient Chinese, to build an efficient encoder-decoder architecture. To comprehensively evaluate the performance of the Siku-Trans model, the study introduced three models as control groups: OpenNMT, SikuGPT, and SikuBERT_UNILM. Through comparative analysis of the performance of each model in ancient Chinese translation tasks, we found that Siku-Trans exhibits significant advantages in terms of translation accuracy and fluency. These results not only highlight the effectiveness of combining Siku-RoBERTa with Siku-GPT as a training strategy but also provide important references and insights for in-depth research and practical applications in the field of ancient Chinese translation. Related Articles | Metrics | Comments（0）

Select

How does the Quality of Online Health Information Trigger Cyberchondria? Multiple Mediating Roles of Perceived Uncertainty and Health Anxiety Jin Yan　Zhang Xiaohan　Sun Zhuo　Bi Chongwu Journal of Information Resources Management    2024, 14 (6): 156-169.   DOI: 10.13365/j.jirm.2024.06.156 Abstract （319）      PDF（pc） （1601KB）（273）       Knowledge map    Save In the era of "digital health", there has been a significant increase in the public's behavior of "Internet self-diagnosis" based on online health information. The uncertainty in the quality of online health information has heightened health anxiety and led to the emergence of cyberchondria. Understanding the impact of online health information quality on cyberchondria can offer valuable insights for improving online health information governance. This study investigates the mechanisms through which argument quality and source credibility affect cyberchondria from the perspective of online health information quality. We collected 386 valid responses through a questionnaire survey and performed data analysis and model testing with SmartPLS software. The results indicate that both the argument quality and source credibility significantly enhance users' perceived uncertainty and health anxiety, which are common factors contributing to the cyberchondria. Additionally, perceived uncertainty and health anxiety mediate the relationship between argument quality, source reliability, and cyberchondria. Furthermore, health anxiety serves as a mediator in the relationship between perceived uncertainty and cyberchondria. Related Articles | Metrics | Comments（0）

Select

The Influence of Information Presentation on the Persuasive Effect of Health-related Rumor Debunking Information Zhang Min　Han Xiqing　Shao Jing　Yan Weiwei Journal of Information Resources Management    2024, 14 (5): 132-146.   DOI: 10.13365/j.jirm.2024.05.132 Abstract （317）      PDF（pc） （1201KB）（728）       Knowledge map    Save Health-related rumors in social media under the failure of traditional “gatekeeper” mechanism face the problem of “rumor debunking-reappearing". Focusing on the characteristics of health-related rumors with mixed truths and emotions to explore the persuasive effect of health debunking information, this research provides a better understanding of the debunking information designing and provides useful reference for optimizing rumor management strategies. This research focuses on information presentation, through a 2 (Presentation content: one-sided content vs. double-sided content) ×2 (Presentation form: serious vs. humorous) ×2 (Rumor type: fear vs. hope rumor) online control experiment to analyze their influence on the persuasive effect of health-related rumor debunking information. Presentation content has significant influence on the persuasive effect of health-related rumor debunking information. One-sided (vs. double-sided) debunking information is more persuasive. Rumor type moderates the interaction effect of presentation content and presentation form on the persuasive effect. For hope rumors, it is better to use double-sided and humorous information or one-sided and serious information. Related Articles | Metrics | Comments（0）

Select

Measuring Policy Responsiveness with Multi-dimensional Text Features：Evidence from Science and Technology Talent Evaluation Policies Lin Xi　Dong Yu Journal of Information Resources Management    2025, 15 (1): 69-85.   DOI: 10.13365/j.jirm.2025.01.069 Abstract （313）      PDF（pc） （12392KB）（75）       Knowledge map    Save Policy responsiveness reflects national governance capabilities and governance levels. This study applies political system theory as an analytical framework, integrating the subject, time, quantity, and hierarchical characteristics of opinion texts and policy texts. It extracts four indicators-response rate, response effectiveness, response enthusiasm, and response efficacy-and develops a policy responsiveness measurement model. The analysis calculates the policy responsiveness in the field of scientific and technological talent evaluation in China from 2002 to 2022. By examining themes, it identifies the development and changing characteristics of policy responsiveness and uses the theme of "How to Evaluate" as a case study to explore the specific content of policy responses. The findings demonstrate that the policy responsiveness measurement model quantifies policy responsiveness effectively and reveal a shift in China's evaluation of S&T talents from selective responsiveness to comprehensive responsiveness, and from delayed responsiveness to high-quality responsiveness. This study enriches the methods for measuring policy responsiveness, reduces the influence of subjective factors, and enhances both the theoretical depth and practical application of the research. Related Articles | Metrics | Comments（0）

Select

Journal of Information Resources Management    2025, 15 (1): 154-160.   DOI: 10.13365/j.jirm.2025.01.154 Abstract （309）      PDF（pc） （688KB）（122）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Scientific Paper Recommendations with User Dynamic Preferences: A Knowledge Graph Approach Based on Attention Embeddings Liu Ya　Mao Qian’ang　Yan Jiaqi　Chen Xi Journal of Information Resources Management    2025, 15 (1): 113-125.   DOI: 10.13365/j.jirm.2025.01.113 Abstract （290）      PDF（pc） （2167KB）（307）       Knowledge map    Save Scientific paper recommendation systems serve as an effective solution to the problem of information overload in academic databases. This study proposes a knowledge-graph-based method employing attention embeddings for the task of scientific paper recommendation to enhance the effectiveness of recommendations. This method initially constructs a collaborative knowledge graph to integrate user behavior with paper attribute information and optimizes node vector representations using the TransR approach. Subsequently, it introduces an attention sequence module that employs an attention propagation mechanism to learn node features and utilizes a sequence attention mechanism to capture the temporal preferences of users from their reading sequences. Finally, the model calculates match scores between researchers and candidate papers to generate personalized recommendation lists. Experiments conducted on a dataset provided by the "Blockchain Laboratory" have validated the effectiveness of the model. Experimental results indicate that the proposed model significantly improves recommendation recall rates, capturing the dynamic interests of researchers more accurately. This study not only enhances the performance of scientific paper recommendation systems but also provides new perspectives and tools for understanding and predicting the evolution of researcher interests. Related Articles | Metrics | Comments（0）

Select

The Influence of Recency and Time-span in the Scientific and Technological Knowledge Convergence Zhang Jiarui　Kang Lele　Sun Jianjun Journal of Information Resources Management    2024, 14 (4): 86-102.   DOI: 10.13365/j.jirm.2024.04.086 Abstract （286）      PDF（pc） （5911KB）（493）       Knowledge map    Save Investigating the temporal attributes of patent knowledge absorption and their impact on patent innovation outcomes can enhance the understanding of time effects in knowledge absorption. By employing patent citation delays, it quantifies the recency and time-span of knowledge absorbed in patents. The analysis covers 2,563,948 citing patents, 6,693,213 cited patents, and 3,978,556 cited papers from 1979 to 2013. It examines the distributions of recency and time-span in the scientific and technological knowledge incorporated into patents and explores how these temporal characteristics relate to the uncertainty of patent impact, as indicated by forward citations. Findings reveal that patents in the field of electrical engineering predominantly rely on recently acquired scientific and technological knowledge, whereas chemistry-related fields depend more on scientific knowledge absorbed over extended periods. Universities and government agencies, as opposed to firms, tend to utilize knowledge with greater recency and time-span. Results from generalized negative binomial regression indicate that higher recency in scientific and technological knowledge and greater time-span in technological knowledge significantly increase the uncertainty in patent influence, while a longer time-span in scientific knowledge decreases it. Related Articles | Metrics | Comments（0）

Select

A Study on the Correlation Factors of Psychological Resilience and Impact on AIGC Users’ Dropout Behavior Based on ISM-MICMAC Xie Jing　Zhang Hai　Shi Qin Journal of Information Resources Management    2025, 15 (1): 126-138.   DOI: 10.13365/j.jirm.2025.01.126 Abstract （284）      PDF（pc） （2456KB）（1875）       Knowledge map    Save In order to clarify the influencing factors of user dropout behavior in the context of AIGC, improve the user experience and willingness to continue using AIGC, and promote the high-quality development of domestic AIGC application platforms, this study drew on the grounded theory research paradigm and extracted causal factors of AIGC user dropout behavior through coding analysis of interview sample data. Based on the interpretative structural model, the intrinsic logic and correlation paths of causal factors of AIGC user dropout behavior were explored. Furthermore, the dependencies and driving forces between individual factors were studied using the cross-impact matrix multiplication method in order to identify the key factors influencing the dropout behavior of AIGC users.The research results show that psychological resilience, technological factors, perceived risk factors，and environmental factors are important factors affecting the dropout behavior of AIGC users. At the same time, it was found that psychological resilience can effectively alleviate the negative factors such as technological burden, technological risk, and information overload, and has important theoretical and practical significance for improving the sustained use behavior of AIGC users. At last, effective measures and suggestions have been proposed to resolve the dropout behavior of AIGC users and promote their continued use. Related Articles | Metrics | Comments（0）

Select

Measuring the Academic Value of Scientific Papers by Integrating Innovation and Recognition—A Case Study in the Field of Artificial Intelligence Wu Jiachun　Dong Ke　Chen Xingyuan　Chen Lifang　Sun Jiaming Journal of Information Resources Management    2024, 14 (6): 17-30.   DOI: 10.13365/j.jirm.2024.06.017 Abstract （282）      PDF（pc） （2994KB）（1513）       Knowledge map    Save The full text of papers and their citation relationships convey a significant amount of academic information, which helps characterize the connotation of academic value and improve the precision of value assessment. This study builds a new evaluation index of academic value based on the epistemology of value, integrating the factual knowledge based on the papers themselves with the contingent knowledge based on external citations, and selecting papers in the field of artificial intelligence from the Web of Science database from 1990 to 2021 as the experimental data. Compared with traditional metrics, the academic value measurement proposed in this study comprehensively considers the value of internal innovation(represented by innovativeness), external recognition value(based on citation sentiment, citation intensity, and citation similarity). The results showed that:(1) value of internal innovation was not correlated with either the number of citations or the number of mentions;(2) value of external recognition was positively correlated with the number of mentions but not significantly correlated with the number of citations;(3) and academic value was positively correlated with the number of mentions, value of internal innovation, and value of external recognition, although value of external recognition was not significantly correlated with value of internal innovation. The results revealed that the impact indicator based on the number of citations has a lag and is insufficient to reflect the paper’s innovation. Compared to citation counts, the number of mentions, incorporating citation preference, shows slight improvement in measuring value of external recognition. The academic value measure proposed in this study has certain advantages in integrating the internal and external values of the paper and reflecting comprehensive academic value. Related Articles | Metrics | Comments（0）

Select

Linking Allusion Words in Ancient Poetry from the Perspective of Knowledge Reorganization: A Method of Integrating the Fine-grained Co-citation Relationships and the Semantic Features Li Xiaomin　Wang Hao　Bu Wenru1　Zhou Shu Journal of Information Resources Management    2024, 14 (6): 131-142.   DOI: 10.13365/j.jirm.2024.06.131 Abstract （279）      PDF（pc） （4793KB）（576）       Knowledge map    Save Guided by theories and technologies related to knowledge reorganization, this study conducts semantic mining and organization of allusion cultural resources to promote the inheritance and utilization of allusion culture. A model is proposed that integrates fine-grained co-reference relations and semantic features to link allusion terms. First, a co-reference network is constructed based on the citation relationships between ancient poems and allusion terms, and fine-grained co-reference relations, including positional co-reference and emotional co-reference, are added to build a fine-grained co-reference network. Then, Doc2vec is employed to extract the semantic features of each allusion term, and these features are integrated to reconstruct the co-reference network. Finally, a link prediction algorithm is applied to traverse the fine-grained co-reference network, achieving semantic association and organization of allusion terms. The association results are further analyzed from a path-based perspective, uncovering some regular patterns in domain knowledge. The constructed co-reference network consists of 5,869 nodes and 27,032 edges. The proposed method, which incorporates positional and emotional co-references as well as semantic features, achieves an accuracy of 0.963 in the task of linking allusion terms. Moreover, the analysis reveals that the shortest path order is negatively correlated with both the number of allusion term pairs and their similarity. Related Articles | Metrics | Comments（0）