Intelligence Theories and Methods

511 Research on Scientific Topic Prediction from the Perspective of Knowledge Unit Reorganization Hot! Liang Jiwen, Yang Jianlin, Wang Wei DOI: 10.3772/j.issn.1000-0135.2023.05.001 Accurate scientific topic prediction can clarify the future development direction of a given discipline and provide a reference for the development planning and management decision-making in the field of scientific research. This paper focuses on the prediction of new scientific topics based on the perspective of knowledge unit reorganization, compares the representation relationship between the topic and feature words to the representation relationship between scientific concepts and knowledge units, and proposes a scientific topic prediction method. First, the LDA (latent Dirichlet allocation) topic model is used to obtain the global topic, feature words, and probability matrix and obtains the feature word vector by transposing the vector space; second, the vector adjustment coefficients are calculated based on the feature word frequencies predicted by the ARIMA (autoregressive integrated moving average model) model to obtain the feature word prediction vectors, the t-SNE (t-distributed stochastic neighbor embedding) algorithm is applied to reduce the dimensionality of the prediction vectors, and then the low-dimensional prediction vectors are clustered by the fuzzy C-mean algorithm to generate prediction topics to realize the reorganization of knowledge units. Finally, the prediction topic with a new interpretation is selected from the aggregation of several original topics, and this is regarded as the scientific topic prediction result. This paper takes the field of “knowledge management-knowledge organization-knowledge service” as an example for conducting empirical research. The results show that the proposed scientific topic prediction method in this paper can effectively predict new scientific topics from which the essential concepts and the corresponding research content of some words have not appeared at that time, such as digital humanities and knowledge payment. 2023 Vol. 42 (5): 511-524 [Abstract] ( 223 ) HTML (142 KB)  PDF (3306 KB)  ( 306 )

525 Research on the Relationship between Interdisciplinarity of References and Academic Influence Hot! Liu Jiaming, Sun Jianjun DOI: 10.3772/j.issn.1000-0135.2023.05.002 Exploring the relationship between the interdisciplinarity of references and the academic influence of papers can provide suggestions for discipline construction; it is of great significance to promote the development of science. Based on journal and conference papers in bionics from 2001-2020, this paper discusses the relationship between references’ interdisciplinarity and papers’ academic influence from disciplinary variety, balance, and disparity. It compares the differences in four cooperation patterns. The result shows that the Rao-Stirling index has harmed academic influence, and there are thresholds for the positive impact of disciplinary variety, balance, and disparity perspectives. Additionally, the relationship between interdisciplinarity and academic influence varies in cooperation patterns. When engaging in interdisciplinary scientific research activities, the principle of moderation should be followed in the aspects of disciplinary variety, balance, and disparity. Different cooperation strategies should be adopted according to the types of collaborators. Researchers should actively communicate and cooperate with high-level international institutions. Colleges and universities should strengthen interdisciplinary training and cultivate compound talents. 2023 Vol. 42 (5): 525-536 [Abstract] ( 190 ) HTML (191 KB)  PDF (900 KB)  ( 498 )

537 On Disinformation Research from the Perspective of Information Hot! Peng Zhihui DOI: 10.3772/j.issn.1000-0135.2023.05.003 Disinformation is becoming an important subject in the research of information theory. The premise and basis of the research is focused on how disinformation can enter the field of information; hence, it is necessary to provide a theoretical explanation. According to the characteristics, conditions, and elements of disinformation, this paper expounds the feasibility and basic paths of disinformation research from the perspectives of information science and intelligence studies. Disinformation is a special type of information. From the perspective of information science, it can be studied from three dimensions of “characteristics,” “quality,” and “governance.” From the perspective of intelligence studies, it is also an information activity, which can be studied from three dimensions of “information,” “agent,” and “recipient.” The research on disinformation from the perspective of information demonstrates that information studies is not confined to the original research framework, but can constantly expand its research objects and research fields, study novel phenomena, explore new problems, and put forward novel theories in the information environment. 2023 Vol. 42 (5): 537-547 [Abstract] ( 231 ) HTML (110 KB)  PDF (1223 KB)  ( 233 )

548 Effect-oriented Quality Framework of Information Disclosure of Sudden Major Natural Disasters Hot! Liu Bing, Long Chenxiang DOI: 10.3772/j.issn.1000-0135.2023.05.004 The role and value of information disclosure in risk prevention, emergency rescue, disaster relief, and emergency management of sudden major natural disasters are becoming increasingly prominent, gradually attracting the attention of government managers and researchers. Its quality directly impacts its role and value and has become a subject of research. This study considers the information disclosure quality of two rainstorm disasters in Zhengzhou in 2021 as the research object. On the basis of the information disclosure effect, this study employs the case study method to explore and establish the basic framework of information disclosure quality of major sudden natural disasters comprising time, information, and organization. This study also analyzes and reveals the connotation of “significance” and “synergy” of the information disclosure quality of major sudden natural disasters embodied in the framework, which embody and reflect the “publicity” essence of information disclosure in sudden major natural disasters. It expands the theory of information disclosure of major sudden natural disasters and lays a foundation for the theoretical construction of information disclosure quality of major emergencies. 2023 Vol. 42 (5): 548-561 [Abstract] ( 201 ) HTML (192 KB)  PDF (1104 KB)  ( 260 )

Intelligence Technology and Application

562 Identification and Utilization of Key Points of Scientific Papers Based on Peer Review Texts Hot! Chen Chong, Cheng Zijia, Wang Chuanqing, Li Lei DOI: 10.3772/j.issn.1000-0135.2023.05.005 Scientific researchers often aim at specific tasks when searching literatures, such as seeking topics, methods, and conclusions. However, distinguishing the numerous key points of scientific papers and judging their value is time consuming and laborious. The task also requires extensive professional knowledge. The peer review contains the disclosure of the paper’s key points and the authoritative evaluation of the reference value of the paper, which can effectively help in meeting the aforementioned needs. This study considers the peer review as the object, defines the key point types in the review on the basis of the typical elements in scientific research activities, and extracts the key points of the paper described in the peer review through supervised learning methods, which not only provide a structured summary of the key points of the paper, but can also be used to assist the literature retrieval. This research collected 549 papers published in Acta Psychologica Sinica between 2014 and 2020 and their corresponding reviews. Four types of key points are defined: general information, methods, results, and highlights. Then, four classification models are trained using SVM (support vector machine), FastText, TextCNN (convolutional neural networks), and BiLSTM (bi-directional long short-term memory) to compare the results. Experiments show that the BiLSTM method has the best efficacy in key points recognition, with an average recognition accuracy of 91% across five tests. The highlights in the key points are further categorized into four: topic selection, value, method, and writing, which is then subdivided by the SVM method, with an F1 value of 85%. Similar to the application of the research results, this study also uses the recognized key points to facilitate in-depth understanding of the scientific paper, classifies the search results on the basis of the highlights, and improves the organization and service form of paper retrieval. This study’s contributions are as follows: (1) introducing the research problems of mining the key points of a scientific paper from the peer review and constructing the framework and hierarchy of the key points; (2) transforming the key points recognition into a classification task and comparing various classification methods to determine the comprehensively optimal method; and (3) achieving the classification organization of retrieval results on the basis of key points and assisting users in understanding and judging the results. 2023 Vol. 42 (5): 562-574 [Abstract] ( 220 ) HTML (138 KB)  PDF (3250 KB)  ( 265 )

575 Integration Forecast of Journal h-index Hot! Song Yanhui, Fu Qiyuan, Qiu Junping DOI: 10.3772/j.issn.1000-0135.2023.05.006 The prediction of academic influence of journals has gradually attracted extensive attention in journal and academic circles. Hirsch pointed out that h-index has better predictive ability compared with other bibliometric indicators. Predicting the development of journal h-index is equivalent to predicting the evolution of journal impact. On the basis of the Chinese Social Science Citation Index (CSSCI) and 13 core journals of library and information science in China, the time series prediction models of Vector Autoregression (VAR), Vector Error Correction (VEC), and Long Short-Term Memory (LSTM) are established to dynamically predict the future h-index of journals. Then, on the basis of the integrated forecast method, the integrated forecast values of the above three models are formed, and the precision of each model and method is compared. Empirical results show that the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) of the integrated forecast method are lower than those of the three single prediction models, thereby improving prediction stability. The journal h-index shows a steady growth trend in the future, and the academic influence of the journal in the field of library and information will develop positively. 2023 Vol. 42 (5): 575-584 [Abstract] ( 158 ) HTML (146 KB)  PDF (1374 KB)  ( 137 )

585 Topic Detection and Evolution in Social Media Platforms Based on a Temporal Co-word Network Hot! Yang Xinyi, Wang Wei, Zhu Hengmin DOI: 10.3772/j.issn.1000-0135.2023.05.007 Social media platforms are essential for netizens to express opinions and sentiments. Analyzing topic distribution and their evolution on social media platforms can reveal hot topics and their changes to provide important references for influencing public opinion. This study employs network community evolution discovery to detect topics and analyze their evolution on social media platforms. First, user-generated textual contents are divided into several slices to construct a temporal co-word network, and the backbones of co-word network in each time slice are extracted. Then, network communities are discovered through the Leiden algorithm to represent topics. To detect topic evolution, a method of detecting topic evolution events is proposed on the basis of the forward and backward transfer probabilities and community size. Therefore, events, such as continuing, growing, shrinking, merging, splitting, forming, and dissolving are identified. Considering the microblogs about COVID-19 in Sina Weibo as an example, a larger number of topics, with finer granularity are uncovered in backbones than in the original co-word networks. Topic evolution paths are also found, such as changes in users’ sentiment from negative to positive, professionalization of pandemic prevention and medical work, the global spread of the pandemic, and the growing economic impact of the pandemic. 2023 Vol. 42 (5): 585-597 [Abstract] ( 164 ) HTML (169 KB)  PDF (5195 KB)  ( 434 )

598 Information Avoidance Behavior of Intelligent Recommendation Users on Mobile Social Media from the Perspective of Privacy Concerns Hot! Wang Xue, Zha Xianjin, Mei Xiao, Yan Yalan DOI: 10.3772/j.issn.1000-0135.2023.05.008 Privacy concerns refer to the degree to which intelligent recommendation (IR) users on mobile social media perceive that their behaviors and tracks are observed and recorded against their wishes. Using the three-level coding of grounded theory, we explore new forms of privacy concerns and information avoidance behavior of IR users on mobile social media and develop a formation mechanism model of information avoidance behavior of IR users from the perspective of privacy concerns. These privacy concerns include information collection, unauthorized secondary use, a sense of being manipulated and spied on, and involuntary exposure, while information avoidance behaviors include ignoring, blocking, and denying information as well as diverting attention and clearing users’ tracks. Meanwhile, privacy concerns directly influence information avoidance intention and behavior and indirectly influence information avoidance intention and behavior through the mediating role of risk appraisal. Moreover, information narrowing can exacerbate privacy concerns. The results of this research provide useful references for developers and users of mobile social media intelligent recommender systems, with theoretical and practical implications. 2023 Vol. 42 (5): 598-610 [Abstract] ( 392 ) HTML (156 KB)  PDF (1174 KB)  ( 735 )

611 Multimodal Negative Sentiment Recognition in Online Public Opinion during Public Health Emergencies Based on Fusion Strategy Hot! Zeng Ziming, Sun Shouqiang, Li Qingqing DOI: 10.3772/j.issn.1000-0135.2023.05.009 Social media is used for the online mapping of the offline public opinion on public health emergencies, and multimodal information with image and text becomes the primary means of public sentiment expression. To fully use the correlation and complementarity among different modalities and improve the accuracy of the multimodal negative sentiment recognition in the online public opinion during public health emergencies, this study constructs a two-stage, hybrid fusion strategy-driven multimodal fine-grained negative sentiment recognition model (THFMFNSR) comprising four parts: multimodal feature representation, feature fusion, a classifier, and decision fusion. By collecting image-text data related to COVID-19 from Sina Weibo, this study verifies the effectiveness of the model and extracts the best sentiment decision fusion rules and classifier configurations. The results show that compared with the optimal recognition model with text, image, and image-text feature fusion, the precision of this model in sentiment recognition improved by 14.48%, 12.92%, and 2.24%, respectively, and in fine-grained negative sentiment recognition, the precision improved by 22.73%, 10.85%, and 3.34%, respectively. The multimodal fine-grained negative sentiment recognition model can sense public opinion situations and assist public health departments and public opinion control departments in decision making. 2023 Vol. 42 (5): 611-622 [Abstract] ( 330 ) HTML (152 KB)  PDF (1807 KB)  ( 591 )

Intelligence Users and Behavior

623 Fact or Opinion: Exploration of Context, Motivation, and Task Features when People Actively Seek Attitude-inconsistent Information Hot! Peng Hanqi, Wang Xinyue, Liu Chang DOI: 10.3772/j.issn.1000-0135.2023.05.010 During everyday life information seeking, people are often biased in favor of information that supports their attitudes, intensifying the information cocoon effect. To promote openness in information searching, information systems should provide diverse information, and people must actively contact and understand information that is inconsistent with their attitudes. This study examined situations and motivations when people actively search for attitude-inconsistent information, and it further defined this type of search tasks as “attitude-inconsistent task” based on related studies. We conducted semi-structured interviews with 13 people with experiences of actively seeking attitude-inconsistent information. The transcript data were coded for analysis based on the grounded theory. Finally, we developed a theoretical model to describe the situations and motivations of people actively searching for attitude-inconsistent information. The results demonstrated that context, user characteristics, and motivation are the main factors that lead users to actively seek attitude-inconsistent information. Furthermore, we enriched the connotation of “attitude-inconsistent task” and described it from multiple dimensions. This study explores the situations and motivations when people actively search for attitude-inconsistent information with their attitudes, and proposes attitude-inconsistent tasks to guide search systems to better support the tasks and promote the openness and diversification of information searching. 2023 Vol. 42 (5): 623-635 [Abstract] ( 248 ) HTML (124 KB)  PDF (1100 KB)  ( 224 )