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

Value Creation of Data Elements: Review and Research Prospects Zhao Caijing Journal of Information Resources Management    2024, 14 (2): 41-53.   DOI: 10.13365/j.jirm.2024.02.041 Abstract （1484）      PDF（pc） （985KB）（4070）       Knowledge map    Save Data has become a key production factor in China’s economic and societal development, with the circulation and value realization of data elements progressively becoming a crucial means for the high-quality development of the digital economy. This paper reviews the literatures and practices concerning the value creation of data elements, examining aspects such as the connotation, mechanisms, driving factors, obstacles and development paths. Based on this, this paper identifies gaps in the existing literatures on the value creation of data elements, advocating for a future research agenda that emphasizes interdisciplinary integration. It also proposes to explore future research directions and methodologies from perspectives including the conceptualization and measurement of data element value, determinants, and mechanisms of influence. Related Articles | Metrics | Comments（0）

Select

The Evolution and Contemporary Perspectives on the Empowerment of Intelligence by Artificial Intelligence Technology Li Guangjian　Pan Jiali Journal of Information Resources Management    2024, 14 (2): 4-20.   DOI: 10.13365/j.jirm.2024.02.004 Abstract （1378）      PDF（pc） （1976KB）（4241）       Knowledge map    Save This paper systematically explores the evolution and application of artificial intelligence (AI) technology in intelligence work, revealing its new developments in ideology, characteristics, technical methods, and practical scenarios. Transitioning from a rule-based paradigm to the era of foundation model approaches, AI presents significant opportunities for the intelligence field’ s enhancement in intelligence processing. However, it also introduces novel challenges related to ethics, legal considerations, and privacy concerns. The paper identifies issues and challenges that should be addressed by the intelligence community in the new era of intelligence. Furthermore, the paper proposes forward-thinking strategies to address these issues and challenges, providing valuable insights for the stable development of intelligence field. Related Articles | Metrics | Comments（0）

Select

Impact of Data Classified and Graded Rights Confirmation on the Realization of the Value of Data Elements Ma Feicheng　Xiong Siyue　Sun Yujiao　Wang Wenhui Journal of Information Resources Management    2024, 14 (1): 4-12.   DOI: 10.13365/j.jirm.2024.01.004 Abstract （1087）      PDF（pc） （1559KB）（1701）       Knowledge map    Save Data rights confirmation is essential for realizing the value of data elements and sustaining the normal operation and continuous development of data elements market. This study delves into concepts related to data rights confirmation and explores the path of how to establish a property right system to realize data rights confirmation. Furthermore, this study shows methods for the data classified and graded rights confirmation, analyzing their impact across the data value chain. Results show that in the data collection stage, the data classified and graded rights confirmation mechanism can motivate data supply, improve data quality, and stimulate market vitality. In the data organization stage, it can break down technical work, protect private data, and explore potential value. In the data circulation stage, it can regulate negative externalities, reduce transaction costs, and optimize the allocation of resources. And in the data utilization stage, it plays a key role in data compliance regulation and data value redevelopment. Related Articles | Metrics | Comments（0）

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 （970）      PDF（pc） （6613KB）（1498）       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

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 （887）      PDF（pc） （5622KB）（3005）       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

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 （886）      PDF（pc） （4159KB）（9097）       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

Exploring the Antecedents of Health Information Credibility at Social Media Platforms: The Moderating Role of Prior Knowledge Wang Xiaopan　Zhang Miao　Wu Yi　Zhang Xiaofei Journal of Information Resources Management    2024, 14 (1): 55-67.   DOI: 10.13365/j.jirm.2024.01.055 Abstract （845）      PDF（pc） （4210KB）（1657）       Knowledge map    Save Based on the elaboration likelihood model, the current study takes fact-checking interruption as the research object, and explores the impact of two fact-checking mechanisms, source rating and content rating, on users' perceived information credibility and subsequent information participation behavior. The moderating effect of prior knowledge is also investigated. Through an online scenario-based experiment involving 202 subjects, the present study found that both source and content rating mechanisms positively affect perceived credibility. Subsequently, perceived credibility has a positive impact on reading, liking, posting supportive comments and forwarding information, but has had no significant impact on posting rebutted comments. Prior knowledge has a negative moderating effect on the relationship between content rating and perceived credibility, but has no significant moderating effect on the relationship between source rating and perceived credibility. The present study enriches the literature and theories related to the credibility of health information in social media and offers managerial insights for the development of a social media information intervention mechanism. Related Articles | Metrics | Comments（0）

Select

Two Modes and Ecological System Construction of Data Element Market Circulation in China Zhang Huiping　Zhao Qin　Ma Taiping　Zhang Yaoyao　Zhang Jingran Journal of Information Resources Management    2023, 13 (6): 29-42.   DOI: 10.13365/j.jirm.2023.06.029 Abstract （805）      PDF（pc） （2368KB）（236）       Knowledge map    Save Market circulation of data elements is a key link to activate the economic and social value of all kinds of data and build a data resource system, which directly affects the effectiveness of the construction of digital China. Government data authorization operation and data trading platform are two main modes of market circulation of data elements. In this study, eight market-based circulation platforms with data elements were selected to carry out comparative analysis from six dimensions, including the composition of working capital, platform participants, platform data sources, product and service types, data rights confirmation paths and technical solution applications. Based on the analysis results and the information ecology theory, this findings show that the data element market ecosystem is composed of data products and services, data subject, data platform and data environment. The ecosystem needs the support of the cooperation mechanism of data community, the linkage mechanism of the two modes and the interaction mechanism between inner and outer circles. This study has significant implications for future development: It is necessary to enrich and innovate application scenarios to drive the integrated development of data elements, establish income distribution mechanism to crack the conflicts of interest among data subjects, and promote the safe and reliable market circulation of digital technology, so as to promote the construction of market circulation ecosystem of data elements. Related Articles | Metrics | Comments（0）

Select

The Developing Directions of Information Resources Management Discipline in the Era of Artificial General Intelligence Yan Hui Journal of Information Resources Management    2024, 14 (2): 21-28,53.   DOI: 10.13365/j.jirm.2024.02.021 Abstract （788）      PDF（pc） （765KB）（2507）       Knowledge map    Save This paper reviews the seventy-year developing history of Artificial Intelligence and Artificial General Intelligence(AGI), reflects on the fifty-year history of information resources management, analyzes the profound and multifaceted impacts of AGI on the knowledge system, education system, and career system of information resources management, and proposes three suggestions for the developing direction of information resources management discipline in the AGI era. 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 （780）      PDF（pc） （1353KB）（683）       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

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 （777）      PDF（pc） （907KB）（1790）       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

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 （738）      PDF（pc） （3124KB）（3536）       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

Institute of Information Science, Shanghai Academy of Social Sciences, Shanghai, 200235 Zhang Zhun Journal of Information Resources Management    2024, 14 (2): 54-67.   DOI: 10.13365/j.jirm.2024.02.054 Abstract （736）      PDF（pc） （1104KB）（2267）       Knowledge map    Save The guideline, which includes twenty key measures to build basic systems for data released in December 2022 (referred to as the "Twenty Data Measures"), proposes a structural separation system for data property rights, with "incentivizing data circulation" as its core focus. The rational allocation of the right to hold data resources affects the initial distribution of data benefits, serving as the foundation for achieving the strategic goal of "common use and shared benefits" of data. Under the traditional exclusive property rights mindset, the allocation patterns of the right to hold data resources may exacerbate conflicts of interest among data co-producers. This article suggests allocating the right to hold data resources among data co-producers in a "1+N" model, which means "prior hold data right for a specific data producer + access rights for N other data producers". With the support of tools such as technical governance and transparency governance, it explores a new, fair, and efficient data property rights system that aligns with the developing laws of the data economy. Related Articles | Metrics | Comments（0）

Select

Research on Multilateral Platform for Data Element Transactions: Current Status, Approaches, and Framework Wu Jiang　Yuan Yiming　He Chaocheng　Qian Long　Du Le　Miao Jiarui Journal of Information Resources Management    2024, 14 (3): 4-20.   DOI: 10.13365/j.jirm.2024.03.004 Abstract （736）      PDF（pc） （4171KB）（1226）       Knowledge map    Save In response to the national policies aiming to establish a unified and comprehensive market for the circulation and transaction of data elements, it is imperative to systematically analyze the current processes involved in the circulation and transaction of data elements. Such analysis is crucial for the construction of data element platforms and holds strategic importance in advancing the market-driven distribution of data elements and fostering the growth of the digital economy within China. Through case studies and literature reviews, this study examines the entities within the multilateral data trading market and their interrelationships. It also identifies the primary challenges within the current market and proposes breakthrough pathways and a research framework for the development of a multilateral data element trading platform. This framework is grounded in value chain theory and socio-technical system theory, aiming to serve as a guide for the construction of a market conducive to the circulation and transaction of data elements. Related Articles | Metrics | Comments（0）

Select

The Dilemma and Practical Approach of Data Factor Value Creation in Chinese Enterprises from the Collaborative Perspective Qian Jinlin　Xia Yikun Journal of Information Resources Management    2023, 13 (6): 5-16.   DOI: 10.13365/j.jirm.2023.06.005 Abstract （734）      PDF（pc） （1867KB）（1427）       Knowledge map    Save Mining and releasing enterprise data factor value is of great significance to cultivate enterprise core competitiveness and to promote social economic growth. Based on literature research, comparative analysis and other methods, this paper comprehensively uses synergy theory and data value chain theory to analyze the connotation mechanism of data factor value creation, and then based on the coupling of data chain and value chain, this paper builds the analysis framework of the collaborative work scene within the enterprise and the collaborative co-governance scene outside the enterprise. The results suggest that: (1)Chinese enterprises lack the analytical ability of data value system, fail to set up data resource management system, and cannot achieve the collaborative development of data utilization and business scenarios; (2)It is difficult to form a value co-creation network with data sharing and exchange as the core because the data sharing channels between enterprises are not smooth, the data relationship is not harmonious, and the interest balance mechanism is not perfect; (3)The two-way data flow sharing mechanism between enterprises and the government is not perfect, and the government-enterprise data coordination supervision and cultivation system is not complete; (4)It is difficult to balance the protection of data rights and the pursuit of data interests between enterprises and individuals. Therefore, this paper puts forward the practical approach of data factor value creation in China from two perspectives: (1)improving the collaborative research ability of data factor value creation within enterprises, and (2)establishing a multi-agent collaborative and co-governing data ecology outside enterprises. Related Articles | Metrics | Comments（0）

Select

Exploring the Generation Mechanism of Affective Responses of User Danmaku Commenting Behavior in Reaction Videos Ye Xujie　Zhao Yuxiang　Zhang Yan　Li Jinhao　Preben Hansen Journal of Information Resources Management    2024, 14 (2): 104-120.   DOI: 10.13365/j.jirm.2024.02.104 Abstract （729）      PDF（pc） （3042KB）（2592）       Knowledge map    Save Investigating the generation mechanism of affective response of danmaku commenting behavior in reaction videos can provide valuable insights into the reasons for affective generations and the process of affective change. This paper takes reaction videos of the Bilibili video website as examples. We conduct coding using the directed content analysis method by selecting the danmaku resources, video content, and reactor responses of 11 popular videos in different camps as samples. Based on the Affective Response Model (ARM), this paper builds a theoretical framework of the generation mechanism of affective responses of user danmaku commenting behavior in reaction videos. The results suggest that affective responses of user danmaku commenting behavior in reaction videos generally follows the path of "information cues-affective response", that is, information cues can arouse emotions or particular affective responses autonomously, and they can also affect the generation of emotions or learned affective responses by arousing particular affective responses. The proposed framework helps to improve the contextualized exploration of ARM theory in computer-mediated communication and will also provide practical implications for optimizing user-information interaction in social media. Related Articles | Metrics | Comments（0）

Select

Effects of Negative Emotions on User Intermittent Discontinuance Behavior of Social Networking Services: Empirical Evidence from a Mixed Study Gan Chunmei　Xiao Chen　Chen Shuyi　Lin Jingjing　Qiu Zhiyan Journal of Information Resources Management    2023, 13 (6): 125-132.   DOI: 10.13365/j.jirm.2023.06.125 Abstract （723）      PDF（pc） （1357KB）（1647）       Knowledge map    Save Taking WeChat as the research sample, this study explores the negative emotions emerging in the social networking services (SNS) use and their configurations effects on SNS intermittent discontinuance behavior through a mixed study. Employing interviews and content analysis, the qualitative research of Study 1 found that, a variety of negative emotions, such as fatigue, anxiety, envy, frustration, disappointment, depression, worry and anger, are generated from SNS intermittent discontinuance behavior. And these emotions play separate or interactive roles. Furthermore, using 300 online questionnaires and fuzzy set qualitative comparative analysis (fsQCA), the empirical research of Study 2 revealed that, three configurations of conditions lead to SNS intermittent discontinuance behavior, i.e., users with envy, users with fatigue, and users with both envy and fatigue. They exert different levels of configuration effects on generating SNS intermittent discontinuance behavior. This study further enriches studies on negative emotions and social media user behavior, and confirms the complexity of emotions during social media use. In addition, this study provides theoretical references for service providers to retain users and for users to use SNS rationally. Related Articles | Metrics | Comments（0）

Select

The Impact of Work Unpredictability on Work-family Conflict in a Remote Work Context——A Moderated Mediation Model Xie Xinzhou　Jin Guangyao Journal of Information Resources Management    2024, 14 (3): 136-148.   DOI: 10.13365/j.jirm.2024.03.136 Abstract （703）      PDF（pc） （1230KB）（1031）       Knowledge map    Save Remote work has become the norm in digital work practices, and the study of the negative effects associated with work and family life in the use of digital technologies is receiving increasing scholarly attention in the field of information systems. Using a theoretical model of work-home resources, this paper explores the new types of work stress perceived by employees in the process of adapting to digital technologies in a remote work context and experiencing a shift in the form and manner of work, and explains the specific paths by which this stress undermines employees' prosperity in the family sphere. The results indicate that the work unpredictability in the context of intensive use of digital technologies leads to a reduction in coping resources for employees' psychological resilience, resulting in work-family conflict. Self-esteem, on the other hand, can be effective in helping employees relieve work stress and restore personal resources. The empirical results provide new insights and implications for how telecommuting affects employees' work experiences and work-home relationships. 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 （698）      PDF（pc） （4448KB）（2448）       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 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 （658）      PDF（pc） （4260KB）（1143）       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 Qualitative Study on the Impact Mechanisms of User Satisfaction of Comprehensive Government Service APPs Based on User Reviews Zhao Ying　Deng Huili　Li Guangyao　Chen Cheng Journal of Information Resources Management    2024, 14 (3): 121-135.   DOI: 10.13365/j.jirm.2024.03.121 Abstract （644）      PDF（pc） （1873KB）（561）       Knowledge map    Save Comprehensive Government Service Apps are critical for delivering "one-stop" solutions for high-frequency government transactions and are essential for the development of efficient, collaborative digital governance. This study explores the determinants of user satisfaction and their mechanisms to inform targeted enhancements in app functionality and service processes, ultimately aiming to improve digital governance standards. Utilizing the Service Encounter Triad and the Service Encounter Satisfaction Model as theoretical frameworks, this study analyzed user reviews from 29 apps through Grounded Theory, identifying seven key factors within product quality and usage contexts. This study developed a triadic subject model and a process model to describe these dynamics and revealed that higher product quality and usage scenarios aligned with user needs lead to greater satisfaction. Institutional pressures in app promotion negatively influence satisfaction prior to use, whereas during usage, product quality positively impacts user satisfaction. After use, perceived empathy within the usage context enhances satisfaction. Additionally, institutional pressures negatively moderate the positive relationship between product quality and satisfaction. This study not only elucidates the complex mechanisms affecting user satisfaction but also enriches the management information systems literature by extending the applicability of established theories. The insights provided offer a theoretical basis for further quantitative studies on satisfaction dimensions and the regulatory effects of institutional pressures. Recommendations derived from this study could optimize digital governance services, promoting high-quality development and advancing digital transformation in China. Related Articles | Metrics | Comments（0）

Select

Predicting Highly-value Patents and Analyzing its Determinants Based on BP Neural Network and MIV Algorithm Hu Zewen　Zhou Xiji Journal of Information Resources Management    2023, 13 (6): 144-155.   DOI: 10.13365/j.jirm.2023.06.144 Abstract （638）      PDF（pc） （3920KB）（1076）       Knowledge map    Save This paper designed multi-dimensional evaluation indicators of patent value and recognized high-value patents as the prediction target vector to construct the training set and the test set. Then the BP neural network model was used to predict and identify potential high-value patents. At the same time, the MIV algorithm was used to analyze the contribution and influence of various dimension indicators of patent value to the result of the high-value patents prediction. The experimental results show that: (1) The prediction performance of the BP neural network model is relatively good, and the prediction accuracy rate is all over 89%. The BP neural network model that takes the recognized high-value patents through "patent family size" as the predictive target vector has the best performance, while the BP neural network model with the predictive target vector composed of the recognized high-value patents through the combination indicator of "patent family size" and "patent citation frequency" performs relatively poorly. (2) The MIV absolute value can effectively reflect the influence and contribution degree of various patent value indicators on the result of the predication model. The indicator of technical value has the most significant influence on the result of the highly-value patent prediction based on the BP neural network model. From the perspective of the MIV absolute value and the total proportion of every single indicator, the four indicators including the number of patent IPC4 classification, the speed of first citation, the number of claims, and the frequency of patent citations have a more significant influence on the results of high-value patents prediction. 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 （626）      PDF（pc） （1088KB）（914）       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 and Application of Semantic Interoperability Concept System from the Perspective of Standardization: Taking Development of Smart Cities International Standards as an Example Huang Jie　An Xiaomi　Kuang Miaomiao　Wu Jing Journal of Information Resources Management    2024, 14 (3): 56-68，135.   DOI: 10.13365/j.jirm.2024.03.056 Abstract （624）      PDF（pc） （3928KB）（2000）       Knowledge map    Save This paper adopts ISO 704:2022 terminology work—principles and methods, regards the definitions of “semantic interoperability” in international standards as the research objects, and then identifies the core concepts, characteristic and their relationships of “semantic interoperability”. It constructs a concept system of “semantic interoperability” based on international standards, which reveals the capability characteristics and functional requirements of “semantic interoperability”. Then, this paper uses case analysis method to map the “semantic interoperability” characteristics of relevant international standards in the field of smart cities, to analyse gaps in the development of semantic interoperability standards and to provide guidance for selection and development of semantic interoperability standards in smart cities, which helps verify the practicality of this concept system. The research has shown that this system has significance for improving efficiency of data, information, and knowledge sharing and exchange in artificial intelligence scenarios, for promoting data, information, and knowledge association, fusion, and interpretability, and for promoting standardization collaboration on multi-dimensional, multi-scenario, and multi-dimensional semantic interoperability. 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 （616）      PDF（pc） （859KB）（1055）       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

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 （613）      PDF（pc） （2333KB）（2236）       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

International Standardization Consensus Building and Application on Concepts of “Smart” in Digital Domain from System of Systems Perspective An Xiaomi　Zhang Hongwei　Wei Wei　Huang Jie　Zhang Hui Journal of Information Resources Management    2024, 14 (3): 31-41.   DOI: 10.13365/j.jirm.2024.03.031 Abstract （607）      PDF（pc） （1506KB）（543）       Knowledge map    Save In the digital age, with the fast development and widespread application of big data and artificial intelligence technologies, “smart” designations are increasingly emerging. However, there is lack of research on international standardization consensus on “smart” concepts. This paper identifies the core concepts and essential characteristics of “smart” from definitions of relevant international standards in digital domain from system of systems perspective and employs principles and methods for concept building in ISO 704:2022. Based on cross-domain international standards experts virtual meetings and surveys conducted, cross-domain standardization consensus on generic concepts of “smart” is achieved. These concepts of “smart” have been used to map and guide the development of a Chinese national standard in smart city domain. The study has important strategic significance for promoting the compatibility between national and international standards. Related Articles | Metrics | Comments（0）

Select

Assessment of Urban Data Element Market Readiness from the Perspective of Information Ecology Theory Gu Jie　Liu Yubo　Wang Zhen　Tang Qifeng Journal of Information Resources Management    2024, 14 (2): 82-94,135.   DOI: 10.13365/j.jirm.2024.02.082 Abstract （604）      PDF（pc） （2810KB）（1803）       Knowledge map    Save Building the data element market stands as a crucial foundation for the successful implementation of China's digital strategies and the development of the digital economy. China's data element market is still in its early development stage, though data resources are abundant. Recognizing the imbalanced development status is essential for both theory and practice. This paper proposes the concept of "data element market readiness" based on the nascent market characteristics. Following the "tripartite constitution" of information ecology theory, an indicator system is established to measure the market readiness of 298 Chinese cities. Spatial analysis is further conducted on inter-city balance and regional competitiveness. The results objectively reflect the current overall status, issues and regional features of China's data element market, providing implications for policy making to promote an integrated national market. 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 （597）      PDF（pc） （8021KB）（106）       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

Research on Core Concepts of Regulation and Their Relationships in the Context of Artificial Intelligence: From Perspectives of Standardization and Multidisciplinary Integration Kuang Miaomiao　An Xiaomi　Huang Jie Journal of Information Resources Management    2024, 14 (3): 69-79.   DOI: 10.13365/j.jirm.2024.03.069 Abstract （595）      PDF（pc） （3873KB）（1119）       Knowledge map    Save In order to understand the concept of regulation in the context of artificial intelligence, this study investigates and analyzes the regulatory definitions in the standard documents published by the three major international standardization organizations, ISO, IEC, and ITU, and deconstructs and reconstructs core concepts and the relationships in these definitions. Using the concept system “entity-tool-management scenario-activity-object-feature” identified from the regulatory definitions in international standards as an analytical framework, this study analyzes the representative literature related to regulation in the context of artificial intelligence using content analysis. From a multidisciplinary perspective, this study proposes the core concepts of regulation and their relationships in the context of artificial intelligence. This study provides reference for establishing a consensus on the regulatory concepts in the context of artificial intelligence and the standardized collaborative implementation path for general regulatory concepts in the context of artificial intelligence. Related Articles | Metrics | Comments（0）

Select

Research on the Match between Chinese Research Data Open Sharing Policy Supply and User Demand Fan Hao　Zheng Xiaochuan　Reziya Aihaiti Journal of Information Resources Management    2023, 13 (6): 156-165.   DOI: 10.13365/j.jirm.2023.06.156 Abstract （588）      PDF（pc） （1597KB）（730）       Knowledge map    Save Understanding the supply-demand matching of policy on openness and sharing of scientific research data is significant important for the optimization and adjustment of policies. On the basis of clarifying the supply and demand entities and their functional relationships, we constructed a matching indicator system consisting of 5 first level dimensions and 17 second level dimensions; The content analysis method is used to code 61 policy texts to obtain the matching order value of the supply side; The questionnaire survey method is used to conduct an empirical survey on user needs to obtain the matching order value of the demand side; Finally, the supply and demand matching is analyzed from two aspects of content matching and environment matching. At present, the overall supply and demand matching of China's open sharing policy for scientific research data is good, but the matching degree of data availability, hierarchical classification, infrastructure construction, platform service capacity, and evaluation mechanism is relatively low. Among them, the demand for data availability and platform service capacity is large but the supply is insufficient. The hierarchical classification, platform infrastructure construction, and evaluation mechanism all show a feature of oversupply, reflecting the imbalance between supply and demand, such as policy weaknesses and oversupply caused by insufficient understanding or weak motivation of research subjects. Related Articles | Metrics | Comments（0）

Select

Model, Current Situation and Countermeasures of Data Element Market Governance in China Ding Botao Journal of Information Resources Management    2024, 14 (2): 29-40.   DOI: 10.13365/j.jirm.2024.02.029 Abstract （584）      PDF（pc） （884KB）（1133）       Knowledge map    Save It is necessary to establish a scientific and efficient market governance mechanism to foster the high-quality development of the data element market. This paper examines the governance mechanisms of the data element market, proposing three governance models: market-oriented governance, vertical governance, and relational governance. It also compares their characteristics to analyze the current situation and challenges of market governance mechanisms. This paper emphasizes that China needs to adopt multiple governance models simultaneously, establishing a governance structure that primarily focuses on market-oriented governance, supplemented by vertical governance, and complemented by relational governance as a key addition. Furthermore, this paper offers specific countermeasures and suggestions for the further improvement of these three governance models. Related Articles | Metrics | Comments（0）

Select

The Concepts of "Transparency" in AI Scenarios:A Content Analysis of Definitions from International Standards Organizations An Xiaomi　Xu Mingyue Journal of Information Resources Management    2024, 14 (3): 42-55.   DOI: 10.13365/j.jirm.2024.03.042 Abstract （581）      PDF（pc） （3492KB）（1816）       Knowledge map    Save This paper aims to clarify the intension and extension of the concepts of “transparency” in the AI scenario and build consensus on the concept within the AI field. It analyzes 11 definitions of transparency from international standards organizations including ISO, IEC and ITU-T, identifying core concepts and their relationships. In combination with analysis of relevant international standards of AI, a concept system model of transparency in AI scenarios is proposed. Through the analysis of definitions in different SDOs, this paper proposes implications to artificial intelligence information governance from three aspects in terms of objects, stakeholders and characteristics. This paper offers new insights into standardization collaboration on information governance and information technology governance for AI from a transparent perspective, which has both theoretical value and practical value. 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 （577）      PDF（pc） （1513KB）（897）       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

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 （570）      PDF（pc） （12975KB）（114）       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

Application and Reflection of Full-text Bibliometric in the Era of Large Models ——A Review of the 2023 Academic Salon on Full-text Bibliometric Analysis Zhou Haichen　Zhang Chengzhi　Hu Zhigang　Xu Shuo　Mao Jin　Chen Liang Journal of Information Resources Management    2024, 14 (2): 162-168,封2.   DOI: 10.13365/j.jirm.2024.02.162 Abstract （566）      PDF（pc） （797KB）（1564）       Knowledge map    Save On September 14-16, 2023, the Sixth Chengdu Conference on Scientometrics & Evaluation was held, hosted by the National Science Library (Chengdu), Chinese Academy of Sciences and organized by the Sci-tech innovation Evaluation Research Center (SERC). The Fourth Academic Salon on Full-text Bibliometric analysis, initiated by Zhang Chengzhi and others, was an important event of the Chengdu Conference, receiving more than eighty experts and scholars' enthusiastic participation and in-depth communication. By combing and summarizing the speeches and discussions of the guests of the salon, this article summarizes the main contents of the salon into the aspects of large language model and full-text bibliometric analysis, the application scenario of full-text bibliometric analysis and so on, in order to reveal the research status and development trend of full-text bibliometric analysis. Related Articles | Metrics | Comments（0）

Select

Research on the Model of Public Data Entering the Data Element Market Fan Jiajia Journal of Information Resources Management    2024, 14 (2): 68-81.   DOI: 10.13365/j.jirm.2024.02.068 Abstract （559）      PDF（pc） （1208KB）（3186）       Knowledge map    Save Public data is an important component of the data marketplace, yet its modes of entry and participation categories have received limited attention in the current literature. This paper investigates the modes of public data participation in the data element market, both domestically and internationally, through sorting and comparative analysis. We identified two main categories and five modes for public data to enter the data element market, including: 1) the primary market (authorized operation) + secondary market (trading in the data exchange) mode, 2) the public data development and utilization + trading outside the data exchange mode, 3) the construction of a public data circulation market mode based on data platforms, 4) the trading mode using data brokers and data intermediaries, and 5) the participation in the data market mode through (public) data trusts. Building upon this categorization, the paper proposes an ideal mode for public data entry into the data element market, outlined in three phases: data acquisition, data product production, and data product trading. This paper offers insights for strategic selection regarding the entry of public data into the data element market in China. Related Articles | Metrics | Comments（0）

Select

From Epistemological Paradox to Cognitive Trap: Research on Security Issues of Generative Technology-Driven Information Ecosystem Bai Yun　Li Baiyang　Mao Jin　Li Gang Journal of Information Resources Management    2024, 14 (1): 13-21.   DOI: 10.13365/j.jirm.2024.01.009 Abstract （559）      PDF（pc） （907KB）（640）       Knowledge map    Save Generative technology-driven information system, with generative artificial intelligence as its core, supports and promotes the process of knowledge transmission and sharing, as well as cognitive flow, and diffusion in the entire information environment. However, it also poses challenges to epistemic security and cognitive security. This paper analyzes the characteristics, advantages, and risks of the generative technology-driven information ecosystem from the perspectives of epistemic and cognition environments. It explores how to fully realize the potential of generative artificial intelligence while adhering to human values and social ethics, to promote the construction of an efficient, secure, and sustainable generative technology-driven information ecosystem. Related Articles | Metrics | Comments（0）

Select

Exploring the Cognitive Factors of Healthcare Professionals’ Health Misinformation Correcting Intention on Social Media——Using SEM and fsQCA Yu Mei　Yu Shiya　Liu Rui Journal of Information Resources Management    2024, 14 (3): 104-120.   DOI: 10.13365/j.jirm.2024.03.104 Abstract （546）      PDF（pc） （1527KB）（953）       Knowledge map    Save This paper aimed to explore the factors of healthcare professionals’ health misinformation correcting intention on social media. The results of this study can be useful to reduce the spread of health misinformation. Based on Third-Person Effects (TPE), Protective Motivation Theory (PMT) and Heuristic System Model (HSM), this paper employed Structural Equation Model(SEM) and Fuzzy-Set Qualitative Comparative Analysis(fsQCA) to explore the influencing factors of healthcare professionals’ health misinformation correcting intention and its configurations. The path analyses showed that third-person effect, social media trust, self-efficacy, response efficacy and professional identity can positively affect health misinformation correcting intention; Information processing affected social media trust and the third-person effect; Social media trust positively affected self-efficacy and response efficacy, and these two variables had mediating effects between social media trust and health misinformation correcting intention. The fsQCA found that there were three configurations leading to health misinformation correcting intention. Third-person effect, self-efficacy, response efficacy, and professional identity were important antecedents. This study can call for and encourage more healthcare professionals to participate in the correction of health misinformation on social media, thus reducing the adverse effects of misinformation and safeguarding public health. Related Articles | Metrics | Comments（0）

Select

Multi-level Functional Structure Recognition of Scientific Literature Liu Haotan　Liu Jiawei　Zhang Fan　Lu Wei Journal of Information Resources Management    2024, 14 (3): 90-103.   DOI: 10.13365/j.jirm.2024.03.090 Abstract （545）      PDF（pc） （3730KB）（676）       Knowledge map    Save The automatic recognition of structure function helps improve the efficiency of tasks such as fine-grained information retrieval, keyword extraction, and citation analysis. In response to the current challenges faced by structure function recognition research, including weak expression of internal textual dependencies and insufficient model generalization and transferability, this paper utilizes graph convolution neural networks to capture inherent dependency information and topological structures among word nodes, enhancing the modeling and representation capabilities of scientific publications. Additionally, adversarial learning is introduced to improve the generalization ability of the structure-function recognition model. The ScienceDirect dataset is selected to examine the recognition effectiveness of various model approaches for structure function at three different granularities: Header, Section, and Paragraph. Furthermore, we tested the transferability of multiple models across domains on PubMED-20k, a medical abstract structure function recognition dataset. Experimental results demonstrate that BERT+GCN get the best performance at the Header level, with an value of 88%, which is a 3% improvement over baseline models. At the Section level, the combination of BERT and GAN achieves the best performance, which is also a 3% improvement over baseline models. At the section paragraph level, the score reaches 68%. BERT+GCN exhibits superior cross-domain transferability compared to other models, achieving an score of 90% on cross-domain data. Related Articles | Metrics | Comments（0）