Current Issue
    , Volume 29 Issue 12 Previous Issue    Next Issue
    For Selected: View Abstracts Toggle Thumbnails
    Construction of Subject Knowledge Base——Taking the Domain of Chinese Cuisine Culture as an Example
    Xu Xin, Guo Jinlong
    2013, (12): 2-9.  DOI: 10.11925/infotech.1003-3513.2013.12.02
    This paper proposes a new Ontology-based subject knowledge base model. This model uses Ontology as guidance to construct domain knowledge framework and uses Ontology-based semantic annotation technique to realize the mapping between domain document and domain concept. Taking the domain of Chinese Cuisine Culture as an example, the flow of constructing the knowledge base is detailed including the two key techniques, Ontology modeling and semantic annotation. Finally, a prototype system for Chinese Cuisine Culture knowledge retrieval is developed with detailed introduction to Ontology manipulation using Jena, which verifies the advantages of the Ontology-based subject knowledge base model in the aspect of knowledge retrieval and semantic retrieval.
    References | Related Articles | Metrics
    Construction and Application of Ontology in the Domain of Chinese Cuisine Culture
    Guo Jinlong, Hong Yunjia, Xu Xin
    2013, (12): 10-18.  DOI: 10.11925/infotech.1003-3513.2013.12.03
    This paper mainly introduces the construction of Chinese Cuisine Culture Ontology and document semantic annotation based on that Ontology. In the part of Ontology construction, the authors use a combined method for Ontology population including manual editing, automatic import and manual semantic annotation. In the part of semantic annotation, the authors detail the techniques of semantic annotation using OntoGazetteer provided by GATE, a famous natural language processing tool. Finally, based on the results of the semantic annotation, semantic retrieval upon the domain documents is displayed so as to verify the function of Ontology, which is one of the advantages of the proposed model for Ontology-based subject knowledge base construction, that is improving the performance of document retrieval.
    References | Related Articles | Metrics
    Study on Multi-level Text Clustering for Knowledge Base Based on Domain Ontology——Taking Knowledge Base of Chinese Cuisine Culture as an Example
    Hong Yunjia, Xu Xin
    2013, (12): 19-26.  DOI: 10.11925/infotech.1003-3513.2013.12.04
    The paper puts forward a kind of multi-level text clustering method for the tree structure of knowledge base. In this method, the words are mapped as concepts by the domain Ontology. First the texts are represented by the top-level concepts to realize the big-size clustering, identify the different subjects of texts and formulate the main classification framework. Then the texts are represented by all concepts and non-concept feature words to further realize the small-size clustering and reveal the subjects of the texts with different depth. Finally, this method realizes the multi-level text clustering from big size to small size.
    References | Related Articles | Metrics
    Research on Using Domain Ontology to Optimize the Document Retrieval——Design and Implementation on the KIM Platform
    Jin Biyi, Guo Jinlong, Xu Xin
    2013, (12): 27-33.  DOI: 10.11925/infotech.1003-3513.2013.12.05
    This paper proposes the strategy of entities label annotation based on Ontology. In order to verify the effectiveness of this strategy, by means of KIM platform, this paper uses Chinese cuisine culture domain Ontology as experimental data, mapping entities in document to the instances in Ontology knowledge base to achieve semantic annotation firstly, and then indexs the user query with instances to achieve the semantic retrieval. At last, the experimental results are evaluated. The study shows that the proposed strategy has a better performance on document retrieval.
    References | Related Articles | Metrics
    Cooking Recipe Recommendation System Based on CBR
    Wu Shanyan, Xu Xin
    2013, (12): 34-41.  DOI: 10.11925/infotech.1003-3513.2013.12.06
    The paper introduces CBR methodology to solve the information utilization and dissemination issue on basis of its knowledge characteristics. Referring to previous scholar's CBR model-CBR R5, the authors apply CBR to cooking recipe knowledge domain and build the recipe system structure including case representation, retrieval and revise such phase tasks in combination with other AI technology, and the system generates the recommendations with numeric value to offer the results directly. At last, myCBR is used to verify the feasibility and effectiveness of CBR in the domain of everyday life information even in the unstructured knowledge.
    References | Related Articles | Metrics
    Design and Application of the S&T Innovation Group and Environment Ontology
    Zhang Pengyi, Qu Yan, Huang Chen
    2013, (12): 42-47.  DOI: 10.11925/infotech.1003-3513.2013.12.07
    In order to help innovation researchers to study the complex and dynamic Innovation Eco-system,this paper introduces the design and application of the S&T innovation and environment Ontology. Ontology modeling methods are used to analyze the concept and product groups, individuals and organizations that play key roles in innovations' evolvement, and the dynamic interactions among innovations and the key actors. Results suggest that the Ontology is able to empower innovation research by supporting analysis of innovation researchers and policy makers including relationship analysis and trend analysis.
    References | Related Articles | Metrics
    Study on Semantic Closeness of User Tags in Folksonomy
    Teng Guangqing, Bi Datian, Ren Jing, Chen Xiaomei
    2013, (12): 48-54.  DOI: 10.11925/infotech.1003-3513.2013.12.08
    This article constructs user tags network based on the relationship between the user tags with technology of complex network analysis.By calculation and analysis of closeness centrality index in user tags network, the conclusion is derived that the degree of semantic closeness among user tags in folksonomy comes close to the free and loose characteristics of random network at the individual level, but higher degree of semantic closeness closes to the domain Ontology on the semantic relationship of whole network.
    Related Articles | Metrics
    Application of Topic Maps in Consumer Health Information Resources Organization——Illustrated by Diabetes Mellitus Information Resources
    Li Yingying, Wang Huilin
    2013, (12): 55-61.  DOI: 10.11925/infotech.1003-3513.2013.12.09
    Limited medical knowledge, and the gaps between special medical terminology and the vocabulary used by consumers (Consumer Health Vocabulary, CHV) may cause the problem that health consumers often have difficulty in understanding and searching these information. This paper proposes a method of organizing consumer health information resources using topic maps, and the topic maps tools designed by the Ontopia corporation are adopted to organize the consumer health information resources about diabetes mellitus as the experiment. Different expressions of the same concept can be collected and the complex relationship between medical information can be displayed, so that consumers can not only initiate a search and browse the medical knowledge structures using their familiar vocabulary(CHV), but also understand exactly the medical knowledge.
    References | Related Articles | Metrics
    Use of Author-Keyword Network for Detecting Author Similarity
    Liu Ping, Guo Yuepei, Guo Yiting
    2013, (12): 62-69.  DOI: 10.11925/infotech.1003-3513.2013.12.10
    Accurately measuring the authors similarities is the fundamental work of detecting disciplinary knowledge structure and mining potential cooperative relationships, it is one of important research issues in library and information science. Current approaches rely on direct associations between properties,and the indirect associations between properties are ignored. This paper proposes a new measurement of authors similarities based on author-keyword network. Firstly the relatedness of keywords are calculated based on Vector Space Model, and then structure similarity algorithm P-Rank is used to calculate the similarities between authors.The initial experiment demonstrates the effectiveness of the proposed approach. Compared with keyword-coupling method and Vector Space Model method, this approach obtains more meaningful results.
    References | Related Articles | Metrics
    Research on the Method of Extracting Features from Chinese Product Reviews on the Internet
    Wang Yong, Zhang Qin, Yang Xiaojie
    2013, (12): 70-73.  DOI: 10.11925/infotech.1003-3513.2013.12.11
    Aim for better solving the problem of extracting features from Chinese product reviews on the Internet, an approach using FP-growth algorithm is proposed to obtain the set of candidate product features. Then, the candidate product features are filtered according to the rules of p-support, non-features frequent nouns and PMI threshold filtering technology. Finally, the final product features set are obtained. Thus, the automatic mining of product features information from Chinese customer reviews on the Internet is achieved. The proposed method is tested with the cell phone reviews from Datatang and the results show that the presented method is valid and effective.
    References | Related Articles | Metrics
    The Topic Evolution Model of the Public Opinion in Micro-Blogging Network
    Li Qing, Zhu Hengmin, Yang Dongchao
    2013, (12): 74-80.  DOI: 10.11925/infotech.1003-3513.2013.12.12
    As the popular development of the micro-blog, which has gradually become the stage where the public opinion occurs and evolves. To analyze the mechanism of that, based on the traditional disease spreading dynamic model named SEIR, this paper proposes an evolution model with the immune function which can represent the characteristic of the micro-blog's fission spreading pattern. In this model, whether a micro-blog's user would re-tweet the message is mainly influenced by his/her impact and the interest's degree to the public opinion. And the authors simulate the parameters in this model to analyze and verify the model presented in this paper. The results show that user's interest to the public opinion is the key factor to affect the spreading extent.
    References | Related Articles | Metrics
    A User’s Acceptance Model of Academic Blog and Its Empirical Study
    Chen Minghong, Qi Xianjun
    2013, (12): 81-87.  DOI: 10.11925/infotech.1003-3513.2013.12.13
    To explore key influencing factors of academic blog acceptance, this study builds a user's acceptance model of academic blog based on the Theory of Planned Behavior and Technology Acceptance Model. And the model is validated by PLS method through online questionnaire and paper questionnaire of 191valid responses from universities and scientific research institutions. The results indicate that perceived usefulness, perceived behavioral control and subject norm affect users' acceptance intentions to use academic blog, perceived ease of use is not significantly related to users' acceptance intentions to use academic blog.
    References | Related Articles | Metrics
    A Research on Selecting Partners of Knowledge Collaboration in Virtual Community Based on Tag
    Deng Weihua, Yi Ming
    2013, (12): 88-93.  DOI: 10.11925/infotech.1003-3513.2013.12.14
    This paper explores a new method of selecting partner of knowledge collaboration in virtual community based on Tag. It differentiates virtual community domain by tag clustering firstly, then projects and constructs new relational diagram of users and strengthens simply user knowledge relation based on the two branch of graph theory, and applies the network analysis method to determine the candidate partners set and to finish the candidate partner evaluation and selection. The experiment validates the conclusion of this paper.
    References | Related Articles | Metrics
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn