Mining Hierarchical Research Interests Based on IEEE/ACM Taxonomy

• Main Authors: Kuan-Chin Huang, 黃冠智
• Other Authors: I-En Liao
• Format: Others
• Language: zh-TW
• Published: 2016
• Online Access: http://ndltd.ncl.edu.tw/handle/53858465384133188012

碩士 === 國立中興大學 === 資訊科學與工程學系 === 104 === In the data explosion era, new research issues and new solutions have arisen from the advanced technologies. To understand the research interests and research roadmap of a researcher, browsing the researcher’s publication lists is a time-consuming task. One way to solve the problem for researchers in computer science is to map the topics of their researches to the IEEE or ACM taxonomy and then construct their research interest ontology and roadmap. In this thesis, we proposed a method for mining research interests of computer scientists based on IEEE/ACM taxonomies. The proposed method analyzed data from the DBLP Computer Science Bibliography. It consists of data extraction module, data preprocessing module, research interest extraction module, and research hierarchy module. Our method can not only build research interest hierarchy but also find potential new research interests of a computer scientist. Using a small-size experiment, the results showed that the proposed method has about 87% of precision.