653 Data Science and Its Implications on the Transformation of Information Science Ba Zhichao, Li Gang, Zhou Liqin, Mao Jin DOI: 10.3772/j.issn.1000-0135.2018.07.001 In the era of big data, the scientific community advocates the establishment of data sciences to form research paradigms and thought patterns that are differentiated and characterized by disciplines. Information science should positively absorb the theories, techniques, and methods of data science to seek the best paradigm for big data to promote the development of information science. On the basis of grasping the scientific nature, theoretical system, and research methods of data science, this paper constructs the inherent logical relationship between data, data science, and information science, and explores the significant influence of data science on the paradigm transformation of information science from the perspectives of technical methods, system construction, and practical application. Finally, the new topics that information science should pay attention to in the current development of big data and data science are pointed out. 2018 Vol. 37 (7): 653-667 [Abstract] ( 377 ) HTML (1 KB)  PDF (596 KB)  ( 1476 )

668 Review and Outlook on the Users’ Mental Model of Information Retrieval System Research Han Zhengbiao DOI: 10.3772/j.issn.1000-0135.2018.07.002 This paper aims to critically review users’ mental model literature. It also aims to propose an integrated research framework of the users’ mental model based on these reviewed literatures. Researchers have identified library and information science disciplinary exploring users’ mental model from seven aspects, which include its conception, feature, constituent, measurement, classification, individual difference factors, evolution factors, and effects. Our proposed integrated framework involves three innovative features. First, this integrated framework reveals the relationship among the users’ mental model, its influence factors, and its’ effection. Second, it recognizes the relationship among the conception, feature, constitution, measurement, and classification of users’ mental model. Third, it established a relation between the users’ mental model and searching as learning, which is information behavior research front. This research can provide a theoretical foundation for the further study of users’ mental model of an information retrieval system. 2018 Vol. 37 (7): 668-677 [Abstract] ( 368 ) HTML (1 KB)  PDF (380 KB)  ( 954 )

678 A Study of Information Symmetry from the Perspective of Domain Ontologies Li Yuxuan, Huang Qi, Chen Xue, Zheng Shuya, Zhang Ge DOI: 10.3772/j.issn.1000-0135.2018.07.003 This paper aims to examine information asymmetry in public life. It proposes a model that adopts domain ontologies in applications to solve this problem. The paper conducts an empirical study of how the model is applied to shopping and online medical consultation and improves the model according to the study results. The research indicates that, to some extent, this model can help counter information asymmetry by providing structural knowledge and visual rendering for both sellers and buyers. 2018 Vol. 37 (7): 678-685 [Abstract] ( 223 ) HTML (1 KB)  PDF (655 KB)  ( 762 )

686 Study on the Recognition Method of Frontier Topic in the Medical Field Fan Shaoping, An Xinying, Yan Guilai, Li Yong DOI: 10.3772/j.issn.1000-0135.2018.07.004 Frontier topic recognition has always been a key point in the field of Library and Information Science. With the emergence of the new paradigm of data intensive science, the importance and necessity of frontier topic recognition has increased. This paper focused on the features of medical literature and designed the calculation method of each feature: novelty, innovation, interdisciplinary, and high attention. In addition, we combined it with the medical thesaurus for the method of innovation that calculated semantic similarity beside topics. To determine the weight of each feature, we used the domain example. We tested the effectiveness of the proposed recognition method through experiments. The advanced topic recognition method in this paper has a certain reference value for identifying more meaningful research topics in the medical field. 2018 Vol. 37 (7): 686-694 [Abstract] ( 203 ) HTML (1 KB)  PDF (366 KB)  ( 808 )

695 Sentiment Classification of Micro-blog Public Opinion Based on Convolution Neural Network Zhang Haitao, Wang Dan, Xu Hailing, Sun Siyang DOI: 10.3772/j.issn.1000-0135.2018.07.005 In this paper, a sentiment classification model of micro-blog public sentiment is constructed based on convolution neural network. Micro-blog topic data is obtained by crawling and using word2vec to train word vectors. NLPIR/ICTCLAS 2016 tools were used for word segmentation and subsequently MATLAB programming model training and testing. The results show that the model can achieve an effective sentiment classification of micro-blog public sentiment, which is superior to traditional machine learning. 2018 Vol. 37 (7): 695-702 [Abstract] ( 265 ) HTML (1 KB)  PDF (677 KB)  ( 1259 )

703 Vital Node Detection and Evolution Analysis in Dynamic Networks Based on PageRank Wang Yu, Liu Dongsu DOI: 10.3772/j.issn.1000-0135.2018.07.006 The PageRank algorithm is widely used to detect vital nodes in static networks. Finding out a manner in which this algorithm can be extended to detect vital nodes in dynamic networks is a significant task. Two dynamic PageRank centrality definitions are separately proposed based on network reconstruction and random walk policy reconstruction. Then, a segmented least squares algorithm is presented to characterize the evolution process and predict the trends of nodes’ centrality. Dynamic co-author networks are constructed in the Library and Information fields to verify the effectiveness of our two dynamic centrality definitions. We compare the trends of author influence obtained by our methods with real-world trends. Our experiments demonstrate that using our definitions, we could characterize the evolution process and more accurately predict the trends of nodes’ centrality. 2018 Vol. 37 (7): 703-711 [Abstract] ( 203 ) HTML (1 KB)  PDF (617 KB)  ( 733 )

712 Research on Scenario Evolution of Food Safety Incidents Based on Knowledge Element and Bayesian Network Song Yinghua, Liu Hanxiao, Jiang Xinyu, Yang Lijiao DOI: 10.3772/j.issn.1000-0135.2018.07.007 The scenario evolution of food safety incidents has the characteristics of unclear path, complex developments, and various subjects. Therefore, it is difficult for decision makers to effectively respond during emergency rescue operations. In the current study, a knowledge element model was used to understand the composition of food safety incident scenarios, which was subdivided into three components: emergencies, exposure, and emergency management; this was done to explore the evolution mechanism of incident scenarios. In addition, Bayesian network technology was employed to further develop a comprehensive model for scenario evolution and quantify the most likely scenarios while Dempster-Shafer (DS) theory was applied to modify the probabilities. Finally, the efficacy and feasibility of the developed method were demonstrated through the Taiwan Plasticizer Pollution case study. Moreover, by better understanding evolution mechanism, this study helps government agencies improve the efficacy of food safety response and conduct more targeted control measures. 2018 Vol. 37 (7): 712-720 [Abstract] ( 361 ) HTML (1 KB)  PDF (618 KB)  ( 746 )

721 Collaborative Order Model of Social and Knowledge Systems in Online Knowledge Communities Qiu Jiangnan, Zhang Meihui, Yang Chang DOI: 10.3772/j.issn.1000-0135.2018.07.008 With the development Web2.0, online knowledge communities (OKCs) are becoming collaborative platforms for knowledge construction. On the one hand, in the social system, OKC users form social networks via interaction and collaboration; users construct their knowledge structure by learning from others. On the other hand, in the knowledge system, the objective knowledge system of an OKC is constructed by integration and link knowledge view from OKC users. The knowledge and social systems of OKCs are self-evolution and co-evolution and interaction with each other. As a result, this paper studies the co-evolution mechanism of knowledge and social systems. First, we analyze the mechanism of internalization, externalization, assimilation, and adaptation of the OKC platform knowledge. Consequently, based on self-organization theory, we established the co-evolution framework for OKCs, where the process and path of OKCs social and knowledge systems are discussed. Finally, we explain the mechanism of the synergy of social system and knowledge system in OKCs by setting the example of Wikipedia. 2018 Vol. 37 (7): 721-731 [Abstract] ( 209 ) HTML (1 KB)  PDF (1065 KB)  ( 744 )

732 Analysis of the Evolutionary Trend of Technical Topics in Patents Based on LDA and HMM: Taking Marine Diesel Engine Technology as an Example Chen Wei, Lin Chaoran, Li Jinqiu, Yang Zaoli DOI: 10.3772/j.issn.1000-0135.2018.07.009 Identifying potential research hotspots from a large number of patents is a crucial strategic issue for both enterprises and countries. In view of the problems in the current analysis of patents, such as the non-repeatability of manual classification and unrecognized specialized vocabulary in natural language processing, a combination method is proposed here as follows. First, we use the Viterbi algorithm to identify specialized terms in patent documents. Second, we introduce the LDA algorithm from machine learning to capture latent topic clusters in patent documents. Third, combining the hidden Markov model and double stochastic process, the distribution and evolution of existing technology topics are analyzed and future technical trends are predicted. Finally, this study uses marine diesel engine technology as an example of applying the above combination method to analyze the topic distribution, evolutionary pattern, and future trend of marine diesel engine technology. The experimental results prove that the proposed method shows better performance. 2018 Vol. 37 (7): 732-741 [Abstract] ( 235 ) HTML (1 KB)  PDF (1239 KB)  ( 1120 )

742 Patent Term Extraction Based on Generic Words and Term Components Yu Yan, Zhao Naixuan DOI: 10.3772/j.issn.1000-0135.2018.07.010 Aiming at the problems that some high-frequency non-term strings cannot be effectively filtered and that low-frequency terms cannot be correctly extracted in patent term extraction, this paper proposes a patent term extraction method based on generic words and term components. The proposed method first takes advantage of generic words to select candidate terms. Then, candidate terms with the same term component as the target candidate term are used to evaluate the target candidate term. Experimental results show that the proposed method can effectively improve the accuracy of patent term extraction, when compared with the traditional methods. 2018 Vol. 37 (7): 742-752 [Abstract] ( 206 ) HTML (1 KB)  PDF (879 KB)  ( 706 )