This paper proposes a method to construct conceptual semantic knowledge base of software engineering domain based on Wikipedia. First, it takes the concept of SWEBOK V3 as the standard to extract the interpretation of the concept from the Wikipedia, and extracts the keywords as the concept of semantic; Second, through the conceptual semantic knowledge base, it is formed by the relationship between the hierarchical relationship concept and the other text interpretation concept in the Wikipedia. Finally, the semantic similarity between concepts is calculated by the random walk algorithm for the construction of the conceptual semantic knowledge base. The semantic similarity of knowledge base constructed by this method can reach more than 84%, and the effectiveness of the proposed method is verified.
References
[1]
Wang, X.-C. and Ding, J.Y. (2013) Big Data Knowledgebase Map: Concepts, Characteristics, Application and Effect. Journal of Intelligence Science, 9, 10-14.
[2]
Su, X.K. (2010) Research on the Construction of Semantic Knowledge Base and Its Application in the Field of Text Categorization Based on Wikipedia. Central China Normal University, Wuhan.
[3]
Chen, Q., Guo, X. and Wang, S. (2015) Topic Structure Modeling of Multi-Granularity Text Flow. Journal of Chinese Information Processing, 29, 118-125.
[4]
Zhang, Q., Chen, Q. and Guo, X. (2013) Topic Detection Technology Based on Topic Ontology Tree. Microelectronics and Computer, 7, 60-63.
[5]
Wu, C.Z. (2012) Research and Implementation of Knowledge Search System Based on Wikipedia. South China University of Technology, Guangzhou.
[6]
Wan, Y. (2014) Research on the Modeling and Application of the Concept Map Based on Wikipedia. Central China Normal University, Wuhan.
[7]
Zhang, T., Liu, K. and Zhao, J. (2015) A Graph Model Based Method for Computing the Similarity of Wikipedia Concepts and Its Application in the Entity Linking System. Journal of Chinese Information Processing, 29, 58-67.
