Intelligence Theories and Methods

127 Comparison and Improvement of Health Misinformation Identification Methods in WeChat Official Account Articles Hot! Wang Lei, Song Shijie, Zhu Qinghua DOI: 10.3772/j.issn.1000-0135.2023.02.001 Recently, the proliferation of health misinformation in WeChat official account articles has impacted users’ access to health knowledge and decreased their ability to make informed health decisions. To suppress the dissemination of health misinformation, it is necessary to study methods of automatically identifying and detecting health misinformation. This study uses samples from two sources: health articles published by authority accounts (e.g., “Science China,” “Ding Xiang Doctor,” and other governmental accounts) and articles containing health misinformation that have been labeled. Health misinformation is identified through the steps of word segmentation, stop word removal, syntax feature extraction, and text classification. We selected the best classifier through the comparison of accuracy, precision, recall, training time, and other performance-related indicators. Moreover, to solve the problems of polysemy and synonyms in text classification, this paper used Latent Dirichlet Allocation (LDA) topic analysis to extract the semantic features of the text and then proposed a feature extraction method based on “syntax plus semantics.” The experiments suggest that our proposed new method had better performance over methods based on semantic feature extraction and other prior models. By proposing a novel method for identifying health misinformation in WeChat official account articles, this study may have practical implications for online health misinformation governance. 2023 Vol. 42 (2): 127-135 [Abstract] ( 315 ) HTML (132 KB)  PDF (1878 KB)  ( 586 )

136 Simulation Method: System Modeling of Complex Scenes in Library & Information Science in the Era of Big Data Hot! Huang Xiao, Wu Jiang, He Chaocheng, Ba Zhichao DOI: 10.3772/j.issn.1000-0135.2023.02.002 Simulation method can elucidate the mechanisms and scientific principles behind complex social problems by systemically modeling and developing computational experiments. In the big data era, the fields related to Library & Information Science are changing in terms of research objects, application scenarios, research paradigms, etc. Simulation methods will help the transformation of this discipline. Therefore, we describe the basic ideas of introducing the simulation method to Library & Information Science, to satisfy the system modeling requirements of the complex scenes in this discipline in the era of big data. First, we clarify the basic logic of the application of simulation methods, including the key problems that can be solved by simulation methods and implementation steps. Second, we summarize the application status and key difficulties of multi-agent simulation, system dynamics, complex network, and other methods in the fields related to this discipline, such as network public opinion, knowledge management, scientific cooperation and evaluation, and competitive intelligence. Third, we point out the applicability of simulation methods and the research in this discipline in the era of big data and propose that the key to matching simulation methods and research lies in the phenomenon recurrence, logical inference, strategy exercise, and scenario prediction of complex scenes. A data-driven system modeling solution is developed to address the aforementioned difficulties. Finally, we further explore the important role of simulation methods in promoting the transformation of this discipline into a data-intensive research paradigm and supporting the demand for the modernization of national governance in which this discipline serves intelligent decision-making. 2023 Vol. 42 (2): 136-149 [Abstract] ( 406 ) HTML (151 KB)  PDF (2153 KB)  ( 359 )

150 Study of Antiquarian Punctuation Recognition Methods Incorporating Semantic Enhancement with Structural Properties Hot! Li Peiqi, Wang Hao, Ren Qiutong, Fan Tao DOI: 10.3772/j.issn.1000-0135.2023.02.003 The concept of digital humanities has extended the connotation and extension of the automated processing of ancient texts and achieving a deeper understanding of the semantics of ancient texts has become a priority. Therefore, this article focuses on exploring semantic enhancement models in recognizing punctuation of ancient texts to improve the ability of mainstream BBiC models (BERT-BiLSTM-CRF) to characterize the semantics of ancient texts. This article fuses structural features to achieve a deeper representation of the semantics of ancient texts from both text and model dimensions, proposes a BBiC-EK (BBiC-external knowledge) model that introduces textual fine-grained textual knowledge and a BBiCC-EK model (BBiC-CNN-EK) that fuses the structural features of texts, and explores the structural perspective of the model to explore the relationship between CNN and the optimal connection between CNN and BiLSTM. The optimal location of external knowledge coding is also investigated from the perspective of model structuring. The experimental results show that the optimal external knowledge combination model in the BBiC-EK model can improve the sentence reading recognition accuracy by 0.83 percentage point compared with the baseline BBiC model, and the BBiCC-EK (Se) model can improve the recognition accuracy of the BBiC model by 1.36 percentage points by further fusing the CNN and exploring the optimal model structure. This article achieves the improvement of the punctuation recognition accuracy of ancient texts by fusing semantic enhancement techniques with structural features and provides new ideas for the automated semantic understanding of ancient texts. 2023 Vol. 42 (2): 150-163 [Abstract] ( 260 ) HTML (161 KB)  PDF (4091 KB)  ( 197 )

Intelligence Technology and Application

164 Evolution Path Identification and Visualization of Technological Innovation Based on SAO Hot! Liu Chunjiang, Liu Ziqiang, Fang Shu DOI: 10.3772/j.issn.1000-0135.2023.02.004 Using patent literature data to assess the development of a technical topic and analyze the development trend can help users to appropriately choose research and development directions and implementation paths; this is significant in both academia and industry when attempting technological innovation. In this study, Open IE 5.1 is used to extract the three tuples of Subject-Action-Object (SAO), the topics based on the Latent Dirichlet Allocation (LDA) model are identified, the technical topics are divided into four dimensions based on the semantic dictionary of action according to the TRIZ technology innovation idea, and the semantic association between the technical topics is evaluated by calculating the similarity between the three tuples of SAO. Subsequently, a visualization map of the evolution path of technology theme innovation is constructed and the evolution context and development trend of technological topics are analyzed. Based on an empirical study conducted in the field of supercapacitors, the innovation evolution path of the technology problem (problem to problem, P-P), technical function (solution to solution, S-S), solution (problem to solution, P-S), and technical effect (solution to problem, S-P) is interpreted and analyzed, thus verifying the feasibility and effectiveness of this method. 2023 Vol. 42 (2): 164-175 [Abstract] ( 182 ) HTML (130 KB)  PDF (4135 KB)  ( 573 )

176 A Research on Competitor Identification Model Based on Cross-domain and Multi-source Information Fusion in the Context of Big Data Hot! Song Xinping, Chen Mengmeng, Lyu Guodong, Shen Yan DOI: 10.3772/j.issn.1000-0135.2023.02.005 There have been significant changes in the pattern of competitor identification under the big data environment, engendering a new research paradigm of competitor identification. Guided by the new paradigm, this article modifies the traditional classic competitive analysis framework of Chen Ming-Jer, and then presents a new competitor identification index system framework consisting of market commonality and resource capability advantage, using the theory of corporate niche, the view of resources and ability, and the theory of customer value. The framework integrates cross-domain and multi-source information sources such as finance, patents, products, and customers from the perspective of the industry and market. Subsequently, the competitor identification model is built based on the fuzzy C-means clustering algorithm, and the new energy automobile industry is taken as an example to carry out simulation experiments. The results show that the model can effectively improve the accuracy and comprehensiveness of competitor identification. 2023 Vol. 42 (2): 176-188 [Abstract] ( 300 ) HTML (193 KB)  PDF (4637 KB)  ( 217 )

189 Study on Identification of Potential “Treasures” in Massive Papers Based on Machine Learning Models Hot! Hu Zewen, Ren Ping, Cui Jingjing DOI: 10.3772/j.issn.1000-0135.2023.02.006 Constructing a feature vector space of massive literature and using machine learning models to accurately and automatically identify and utilize potential “treasures” from a vast body of literature can enhance their scientific influence and facilitate advancements in science and technology. This study designs and implements machine learning models and the model framework of identifying potential “treasures” from consistent scientific and technological papers. As samples, we collected papers (and their citation data) published in international high-influencing journals and domestic journals from Web of Science and Library Information and Archives Management, respectively. Subsequently, we measured the bibliometric characteristics of all these papers and constructed a feature vector space of the literature. Thereafter, traditional machine learning models, such as support vector machine and naive Bayes model, and deep learning models, such as deep belief networks and multilayer perceptron, were used to identify potential “high-quality” papers. An receiver operating characteristic (ROC) curve and a confusion matrix were used to evaluate the recognition effect of the machine learning algorithms. The results show that deep learning models cannot efficiently identify the potential “treasures” from consistent papers, thus exhibiting a low recognition effect. However, the traditional machine learning models can efficiently identify the potential “treasures” from international high-influencing journals and domestic journals in library Information and Archives Management. While two types of machine learning models, including random forest and support vector machine, show the optimum recognition effect, relatively low recognition effect for the decision tree model and Naive Bayes model is identified. Moreover, the more influential a journal is, the higher the recognition effect. Irrespective of whether we considered international high-influencing journals from natural sciences or domestic journals from social sciences, all identified excellent papers exhibit a higher citation frequency, and extremely few review papers are found among them. Furthermore, by comparing the bibliometric features of all papers analyzed, we find that most identified excellent papers are multi-author articles supported by science foundation and present a shorter first-citation time, more references and keywords, higher citation frequency, and longer abstracts. The empirical results show that the machine learning model can accurately identify potential “high-quality” articles from massive scientific and technological literature and improve the automation scope of identifying potential “high-quality” articles. This can also provide theoretical reference and methodological support for automatic recognition, dissemination, and utilization of potential “high-quality” papers from massive literature. 2023 Vol. 42 (2): 189-202 [Abstract] ( 265 ) HTML (203 KB)  PDF (1784 KB)  ( 393 )

203 HanNER: A General Framework for the Automatic Extraction of Named Entities in Ancient Chinese Corpora Hot! Yan Chengxi, Tang Xuemei, Yang Hao, Su Qi, Wang Jun DOI: 10.3772/j.issn.1000-0135.2023.02.007 The digitization of ancient Chinese texts is fundamental for promoting the development of ancient Chinese book databases and utilizing relevant resources. As a critical technical aspect, the automatic extraction of named entities from ancient books has gained considerable attention from academia and industry worldwide. However, certain “bottle-neck” problems restricting the methodological development of such extraction have not been effectively handled; these problems mainly include few-shot learning, annotation cost management, and data quality control. This study presents a general framework called “HanNER” for the automatic extraction of named entities from ancient book resources. This approach can be regarded as a systematic solution that involves three steps: rule-based entity automatic annotation, iterative entity extraction based on deep active learning technology, and human-computer-interaction-based annotation decision. Experimental comparisons performed among multiple groups prove the feasibility and advantages of HanNER, including the advantages of a deep active learning algorithm known as “CNN-BiLSTM-CRF+margin,” functional positive effectiveness of proposed modules (entity query and entity recommendation), and efficiency of the proposed “ZenCrowd-II.” Finally, an automatic entity extraction system for ancient Chinese texts is developed based on the optimization of “BERT-CNN-BiLSTM-CRF.” The proposed “HanNER” method can not only further promote the technical and methodological development of the automatic entity extraction and other relevant tasks for ancient Chinese texts but also provide useful reference for product implementation from an engineering perspective. 2023 Vol. 42 (2): 203-216 [Abstract] ( 333 ) HTML (175 KB)  PDF (3146 KB)  ( 312 )

Intelligence Users and Behavior

217 Influencing Factors and Empirical Research on the Usage Behavior of Smart Library Online Chatbots Hot! Wang Xiwei, Luo Ran, Liu Yutong, Wuji Siguleng DOI: 10.3772/j.issn.1000-0135.2023.02.008 The smart library online chatbot is a novel medium for artificial intelligence to connect readers and smart libraries. Constructing a theoretical model for the usage behavior of a smart library online chatbot can play an important theoretical and practical role in the development of smart virtual reference services and smart libraries. Based on the stimulus-organism-response framework, combined with the information system success model and social response theory, from the two dimensions of functional and social characteristics, this study analyzes the influencing factors of the usage behavior of smart library online chatbots. The model determines how online chatbots affect users' organismal reaction and usage behavior in the smart library and provides a novel perspective for the study of online chatbot usage behaviors and a novel theoretical framework for behavioral analysis. The results are as follows. Information quality and empathy of smart library online chatbots have positive effects on satisfaction, and empathy and friendliness have positive effects on trust, while satisfaction and trust have positive effects on usage behavior. Users’ trust has the greatest influence on usage behavior, while the system quality of online chatbots has no influence on satisfaction. This research provides theoretical and practical significance for building new types of human-computer relationship in the construction of smart libraries, thereby realizing the equalization of public cultural services and promoting the transformation of conventional libraries into smart libraries. 2023 Vol. 42 (2): 217-230 [Abstract] ( 262 ) HTML (183 KB)  PDF (1223 KB)  ( 506 )

Intelligence Discipline Development and Construction

231 Analysis of the Joint Construction Path of Big Data Management and Application Specialty in Information Management Departments of Domestic Universities Hot! Ye Guanghui, Cao Gaohui, Xia Lixin DOI: 10.3772/j.issn.1000-0135.2023.02.009 The major of Big Data Management and Application (BDM&A) is a new major serving the national big data development strategy, as well as a new carrier and fulcrum to support the cultivation of library and information talents. However, the overall scale of the information management departments responsible for the BDM&A major construction is limited, and their construction characteristics are not prominent. This is because the major courses lack systematic top-level design and normative guidance, and the major construction quality standards need to be introduced urgently. Based on a comprehensive investigation of the existing research, this paper explores the joint construction path of the BDM&A major in information management departments based on four dimensions. First, the professional organization and standards dimension focus on the innovation of the professional joint construction organizational model and the introduction of professional certification standards. Second, the professional resources dimension highlights the joint construction and sharing of teaching, training, and discipline resources. Third, the professional construction effect dimension focuses on describing the quantitative analysis steps such as the design of evaluation indicators, index system construction, and grade description. Finally, the current implementation direction of BDM&A major construction is emphasized. This path will provide an effective reference for the training of high-quality BDM&A major talents in information management departments. 2023 Vol. 42 (2): 231-240 [Abstract] ( 306 ) HTML (87 KB)  PDF (1429 KB)  ( 267 )

241 Analysis of Intelligence Science Textbook Materials in China Hot! Liang Jiwen, Wang Wei, Yang Jianlin DOI: 10.3772/j.issn.1000-0135.2023.02.010 Textbook resources are the core element of subject education. This article provides a multi-dimensional analysis of the current situation of the design, creation, and use of intelligence science textbook resources in China and explores trends in the planning and layout of these resources while keeping in mind that this intelligence science content is driven by the national strategy. The article provides references for the long-term development of educational resources and discipline construction. In this study, comprehensive information was collected on the creation and use of textbook resources on intelligence science and related disciplines in China through literature research, network research, and other methods. Next, analysis was conducted considering different dimensions such as the publication time of the textbook, the subject content, and the quality of the textbook. The research results show that in recent years, as an applied discipline, the creation of textbook resources has shifted the focus of intelligence science due to the impact of related majors. Currently, there are problems such as missing information elements, uneven distribution of topics, fuzzy application levels, and incoherent content. On this basis, a corresponding improvement path for the design and creation of teaching material resources is proposed that involves improving the top-level design, standardizing the principles of writing, balancing various teaching materials, and promoting the application of teaching materials. 2023 Vol. 42 (2): 241-254 [Abstract] ( 177 ) HTML (142 KB)  PDF (2657 KB)  ( 291 )