Special Topics

1379 Empowering High-level Self-reliance and Strength in Science and Technology with Scientific and Technological Information Hot! Zhao Zhiyun DOI: 10.3772/j.issn.1000-0135.2024.12.001 Self-reliance and strength in science and technology is the foundation for national prosperity and security, and it is the only way for building a world leader in science and technology. Since its birth, China's scientific and technological information has been closely related to the country's scientific and technological advancement. This study analyzes the new demands and challenges faced by China's scientific and technological information causes, combining the backgrounds of high-level self-reliance and strength in science and technology. This paper proposes a new perspective and scientific connotation for using the theory of new quality productive forces to create a new situation for scientific and technological information causes. Specifically, it proposes an efficiency-oriented research paradigm for scientific and technological information and highlights the key issues and measures that China's scientific and technological information institutions must address to empower high-level self-reliance and strength in science and technology. These issues include accelerating the construction of a high-quality scientific and technological information resource system, creating a new intelligent analysis engine for scientific and technological innovation services, strengthening the systematic construction of scientific and technological information, and building a scientific and technological information talent system. 2024 Vol. 43 (12): 1379-1385 [Abstract] ( 25 ) HTML (46 KB)  PDF (963 KB)  ( 49 )

Intelligence Theories and Methods

1386 Research on the Relationship between the Interdisciplinarity of Papers and Scientific Breakthroughs Hot! Liu Jiaming, Sun Jianjun DOI: 10.3772/j.issn.1000-0135.2024.12.002 Interdisciplinary research is of great significance for realizing scientific innovation. Based on annual breakthroughs reported in Science magazine from 2001 to 2020, this study measures the interdisciplinarity of scientific breakthroughs through three dimensions of discipline diversity from the perspective of references. Furthermore, it discusses and compares the relationship between interdisciplinarity and scientific breakthroughs in different disciplines. The results reveal an inverted U-shaped relationship between the Rao-Stirling index and scientific breakthroughs. Disciplinary variety and the number of discipline groups negatively affect scientific breakthroughs, and disciplinary disparity positively affects scientific breakthroughs. The relationship between interdisciplinarity and scientific breakthroughs differs depending on discipline groups. Therefore, we suggest that interdisciplinary research activities should be conducted in a few disciplines with large differences. Basic sciences should avoid being combined with too many disciplines, and applied sciences should absorb knowledge from various disciplines in a balanced and extensive manner. Furthermore, governments and research institutions should actively build cross-innovation platforms. 2024 Vol. 43 (12): 1386-1398 [Abstract] ( 23 ) HTML (195 KB)  PDF (2195 KB)  ( 51 )

1399 A Quantitative Evaluation of the US Science and Technology Competition Policy toward China Hot! Zhao Yiming, Sun Shaoju, Zhang Jianian DOI: 10.3772/j.issn.1000-0135.2024.12.003 Science and technology competition is a core area of the “game” between China and the US in this new era. Furthermore, science and technology policy is a bellwether of the government’s science and technology behavior. Therefore, this study explores the internal connections of the US science and technology competition policy toward China, which has become a normalcy according to the evaluation and analysis of relevant US policies undertaken, so asto help China take the initiative in the new round of this competition. Using the policy modeling consistency (PMC) index model, text mining, and policy sample analyses, we collected policy documents from sources such as the US President’s Project, US legislative information website, and various US government administrative department websites. Subsequently, we conducted word frequency analysis. Based on the results of this analysis, we constructed a PMC evaluation system for the US science and technology competition policy toward China. A stratified sampling method was employed to extract policy samples, followed by text mining and analyses to derive the PMC index for the samples. Finally, in conjunction with the PMC surface plot, we conducted an evaluative analysis of the policy samples, which clarified the Boyd cycle-like strategic operating system used in the US-China science and technology competition. This study provides strategic recommendations for China to address the new era of this competition, focusing on three aspects: awareness and early warning systems for technological competition dynamics, mechanisms of the rapid response to technological competition incidents, and the dynamic assessment system for technological competition situations. 2024 Vol. 43 (12): 1399-1413 [Abstract] ( 22 ) HTML (205 KB)  PDF (2604 KB)  ( 79 )

1414 Automatic Identification Method of Policy Irony Comments Based on Large Language Models Hot! Huo Chaoguang, Yin Zhuo, Yang Yuan, Yang Wancheng, Ru Runyu, Huo Fanfan DOI: 10.3772/j.issn.1000-0135.2024.12.004 Policy irony comments are extreme and sharp expressions whereby the public voices their opinions on public policies. Automatic and accurate identification is crucial for monitoring policy opinions. Given the scarcity of research on automatic identification methods for policy irony comments and the multiple difficulties involved, this paper proposes a method for automatically identifying policy irony comments based on large language model frameworks. Specifically, using the ChpoBERT, LLaMA-2, GPT-2, and StructBERT frameworks, models for the automatic identification of policy irony comments were constructed and compared. Based on a dataset of 111,628 valid policy comments collected from Sina Weibo, the first dataset of policy irony comments was manually annotated. Additionally, based on the presence or absence of topic labels, the data were further divided into two datasets—one with and one without topic labels—for model training and evaluation. We found that the model built on ChpoBERT achieved the best performance in terms of accuracy, recall, and F1 score, followed by the model built on LLaMA-2. After fine-tuning, the models demonstrated certain performance guarantees. The models constructed in this study establish clear and comparable baseline models for research on the accurate identification of policy irony comments, providing methodological support for policy sentiment monitoring. 2024 Vol. 43 (12): 1414-1424 [Abstract] ( 21 ) HTML (106 KB)  PDF (1838 KB)  ( 43 )

Intelligence Technology and Application

1425 Group Detection in Interest-Based Learning Communities Enhanced by Hypergraph from a Social Engagement Perspective Hot! Li He, Liu Jiayu, Shen Wang, Shi Qianru, Xie Mengfan DOI: 10.3772/j.issn.1000-0135.2024.12.005 Online learning group detection in the context of the new technological revolution empowering educational innovation, is a key approach for optimizing the stratified allocation of educational resources based on the personalized characteristics of learners. Existing detection methods for interest-based learning community online learning groups primarily rely on direct behavioral data and interaction metrics of learners, focusing less on the potential level of social engagement and community structure. To cultivate a culture of autonomous learning enhanced by learner profiles in a smart digital environment, we propose a group-detection method for interest-based learning communities enhanced by a hypergraph from a social engagement perspective. Initially, a feature set representing the learner’s level of social engagement is constructed based on factors influencing users’ social engagement. Subsequently, a hypergraph convolutional network (HyperGCN)-enhanced graph clustering algorithm is proposed to overcome the issue of ineffective capture of multivariate interactions and higher-order structures of learner groups previously encountered with bipartite graph detection. Data were collected from a real-life interest-based learning community to validate the effectiveness of the proposed method. Compared with the baseline, the proposed method achieved improvements of 16.16, 9.77, 16.01, and 22.14 percentage points in accuracy (Acc), F1, normalized mutual information (NMI), and adjusted Rand index (ARI), respectively. These results not only prove the effectiveness of HyperGCN in capturing the structure of learner groups for online learning group detection tasks but also provide methodological and theoretical support for formulating and adjusting personalized education configuration strategies from the perspective of social engagement. 2024 Vol. 43 (12): 1425-1439 [Abstract] ( 22 ) HTML (162 KB)  PDF (2510 KB)  ( 67 )

1440 A Study on the Stability of Semantic Representation of Entities in the Technology Domain-Comparison of Multiple Word Embedding Models Hot! Chen Guo, Xu Zan, Hong Siqi, Wu Jiahuan, Xiao Lu DOI: 10.3772/j.issn.1000-0135.2024.12.006 Lexical semantic analysis is crucial in the science and technology literature intelligence analysis field. Distributed word embedding techniques (e.g., fastText, GloVe, and Word2Vec), which can effectively represent lexical semantics and conveniently characterize the semantic similarity of lexical words, have recently become the mainstream technology for technological lexical semantic analysis. The use of word embedding techniques for lexical semantic analysis is highly dependent on computing the nearest semantic neighbors of words based on word vectors. However, because of random initialization of the word embedding model, even if the nearest semantic neighbors generated by repeated training on the exact same data are not identical, the randomly perturbed nearest semantic neighbors introduce untrue information. To minimize the impact of random initialization, enhance reproducibility, and obtain more reliable and effective semantic analysis results, this study comprehensively examined the influence of dataset size, model type, training algorithm, keyword frequency, vector dimension, and context window size and designed a quantitative stability assessment index and corresponding experimental scheme. The present study investigated the Microsoft Academic Graph (MAG) paper corpus in four distinct fields: artificial intelligence, immunology, monetary policy, and quantum entanglement. Specifically, we trained word embedding models on a corpus of MAG papers, performed word vector semantic representations for the keywords of the papers, and calculated evaluation metrics to ascertain the stability of semantic representations in conjunction with quantitative results. The results on the four domains demonstrate that the larger the dataset, the more stable the semantic representation. However, this is not the case for GloVe. Different models and training algorithms must be targeted when considering structural grammatical information, such as lexical composition, character similarity, and keyword frequency. Furthermore, setting the vector dimension to 300 and the context window to 5 is a more appropriate choice. This empirical study offers a point of reference for intelligence workers engaged in the semantic analysis of scientific and technological vocabulary. 2024 Vol. 43 (12): 1440-1452 [Abstract] ( 23 ) HTML (112 KB)  PDF (3302 KB)  ( 58 )

1453 Construction and Application of Event Knowledge Graph for Major Emergency Response Management Hot! Zhou Honglei, Zhang Haitao, Liu Weili, Liu Yanhui DOI: 10.3772/j.issn.1000-0135.2024.12.007 To explore knowledge modeling and applications in emergencies and associate emergency management knowledge with events, this study aims to help relevant departments scientifically understand the occurrence and evolution of emergencies and improve emergency management capabilities. Based on a knowledge-driven perspective of event evolution and property association, this study proposes a process and methodology for constructing an event-knowledge graph. First, the schema layer of the event-knowledge graph is designed through event knowledge modeling, associating knowledge of emergencies, disaster-bearing events, and response management events. Second, the data layer of the event-knowledge graph is constructed through steps including event knowledge extraction, fusion, and memory. Finally, the study develops an example of an event-knowledge graph for heavy rainfall-related natural disasters and proposes applicable emergency management service scenarios. An example validation of a natural storm disaster emergency was conducted. The results demonstrate that the event-knowledge graph not only describes the type and intensity of emergencies and their spatiotemporal evolution trends but also illustrates their impact on disaster-bearing carriers and their practical utility in emergency management. This provides support for a scientific response to emergencies. 2024 Vol. 43 (12): 1453-1466 [Abstract] ( 22 ) HTML (109 KB)  PDF (6864 KB)  ( 40 )

1467 An Approval Time Prediction Method Based on Patent Characteristics Hot! Xiang Shuxuan, Li Rui DOI: 10.3772/j.issn.1000-0135.2024.12.008 Predicting the approval speed of their competitors’ or their own patents is a crucial part of competitive intelligence analysis for innovation subjects. The examination time included the validity period of a patent. Some examiners took eight or even 12 years to approve a patent. This greatly reduces the validity period of a patent for up to 20 years from the date of application and has a considerable impact on its value. This study aimed to construct an information science method by mining a series of features of patent literature to form a prediction model, which can be used to predict whether a patent will be granted and the speed of approval. The research consisted of two logical parts: approval and speed prediction. First, correlation analysis and the Cox proportional risk regression model were applied to examine the selected characteristics. A patent approval time prediction model (MACP) based on the relation of examination decision and pendency was then constructed using the method of auxiliary learning, including the characteristics of technology internal capacity, technology structure, technology function, technology concept clarity, applicant, and inventor. Experimental results show that the MACP based on the combination of auxiliary tasks outperformed the existing baseline model. Because the MACP model can effectively learn and use more knowledge of the patent examination process, it can reduce the dependence on the amount of data and achieve a better prediction effect. 2024 Vol. 43 (12): 1467-1482 [Abstract] ( 21 ) HTML (312 KB)  PDF (3614 KB)  ( 32 )

Intelligence Users and Behavior

1483 Irrational Information Behavior from a Cognitive Perspective: Application of the Mental Accounting Theory Hot! Shen Yutian, Lu Quan, Chen Jing DOI: 10.3772/j.issn.1000-0135.2024.12.009 Revealing the decision-making processes and mechanisms of information users from a cognitive perspective is an essential part of information behavior research. However, theoretical models based on rational assumptions cannot explain the irrational or limited rationality information behavior in complex information environments. This study introduces the mental accounting theory to the field of information behavior, providing a new perspective for studying information users’ cognitive processes and decision-making psychology given complex effects. In this study, we review the current status of user information behavior research from a cognitive perspective, conceptualize irrational information behavior, analyze the shortcomings of existing theoretical models and methodological perspectives, and clarify the importance and necessity of cognitive perspectives and biases. Subsequently, we introduce the mental accounting theory and summarize its theoretical connotations, core concept content, development, application, and research paradigm. We explain how to apply the ideas of multi-account classification and gain-and-loss analyses in mental accounting theory to explain and intervene in typical irrational phenomena, such as the non-substitution, sunk cost, and reference point effects in information behavior. Furthermore, we construct a research framework for irrational user information behavior based on the mental accounting theory. This article reveals how mental accounting affects individuals’ information decisions and behaviors in terms of different behavioral topics and stages. Our study findings enrich the methodology and theoretical system of information behavior research and promote the development of research on information behavior from rational to irrational assumptions and the transformation of research on irrational information behavior from scattered, descriptive research that summarizes rules to systematic, interventional research that reveals decision-making mechanisms. 2024 Vol. 43 (12): 1483-1494 [Abstract] ( 25 ) HTML (151 KB)  PDF (1652 KB)  ( 68 )