TY - JOUR
T1 - A fuzzy ontological knowledge document clustering methodology
AU - Trappey, Amy J.C.
AU - Trappey, Charles V.
AU - Hsu, Fu Chian
AU - Hsiao, David W.
PY - 2009
Y1 - 2009
N2 - This correspondence presents a novel hierarchical clustering approach for knowledge document self-organization, particularly for patent analysis. Current keyword-based methodologies for document content management tend to be inconsistent and ineffective when partial meanings of the technical content are used for cluster analysis. Thus, a new methodology to automatically interpret and cluster knowledge documents using an ontology schema is presented. Moreover, a fuzzy logic control approach is used to match suitable document cluster(s) for given patents based on their derived ontological semantic webs. Finally, three case studies are used to test the approach. The first test case analyzed and clustered 100 patents for chemical and mechanical polishing retrieved from the World Intellectual Property Organization (WIPO). The second test case analyzed and clustered 100 patent news articles retrieved from online Web sites. The third case analyzed and clustered 100 patents for radio-frequency identification retrieved from WIPO. The results show that the fuzzy ontology-based document clustering approach outperforms the K-means approach in precision, recall, F-measure, and Shannon's entropy.
AB - This correspondence presents a novel hierarchical clustering approach for knowledge document self-organization, particularly for patent analysis. Current keyword-based methodologies for document content management tend to be inconsistent and ineffective when partial meanings of the technical content are used for cluster analysis. Thus, a new methodology to automatically interpret and cluster knowledge documents using an ontology schema is presented. Moreover, a fuzzy logic control approach is used to match suitable document cluster(s) for given patents based on their derived ontological semantic webs. Finally, three case studies are used to test the approach. The first test case analyzed and clustered 100 patents for chemical and mechanical polishing retrieved from the World Intellectual Property Organization (WIPO). The second test case analyzed and clustered 100 patent news articles retrieved from online Web sites. The third case analyzed and clustered 100 patents for radio-frequency identification retrieved from WIPO. The results show that the fuzzy ontology-based document clustering approach outperforms the K-means approach in precision, recall, F-measure, and Shannon's entropy.
KW - Fuzzy inference control
KW - Hierarchical clustering
KW - Ontology schema
KW - Patent analysis
KW - Text mining
UR - http://www.scopus.com/inward/record.url?scp=67349126463&partnerID=8YFLogxK
U2 - 10.1109/TSMCB.2008.2009463
DO - 10.1109/TSMCB.2008.2009463
M3 - Article
C2 - 19336337
AN - SCOPUS:67349126463
SN - 1083-4419
VL - 39
SP - 806
EP - 814
JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IS - 3
ER -