<![CDATA[One of semantic approach in word or phrase separation for determining topic of a document is a concept-based mining model. This approach works based on frequency of occurrence of the word by heeding semantic aspects, so the results are more accurate than syntax analyzing. Concept-based mining model arises from the need for understanding and manipulating the text to get specific information from text document using computer technology, by considering the aspects of syntactic and semantic.Semantic role labeling that based on case grammar is used to obtain semantic role of each word or phrase in a document, whereas the label itself are taken from PropBank. Concept-weighting in this research used two concept-based methods, the graphical concept-based where each concept is represented in a graph rise with different values for each levels, and the statistical concept-based that analyze the concept statistically which based on the frequency of occurrence. The concept with the highest weight value will represent the topic of the document. The test results that acquired by using test data which is news article that used Bahasa, shows that the number of attributes that represent the document on conceptbased mining models approach are affecting system performance,but the given effects are different between classification and clustering. Identifying semantic roles provide the level of semantic analysis to solve human language processing problems. Further research is needed to get higher quality of concept.]]>
Copyrights © 2014
