Using Semantic Dependencies to Mine Depressive Symptoms from Consultation Records November/December 2005 (vol. 20 no. 6) pp. 50-58
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2005.115
Interactive psychiatric services aim to provide immediate consultation, assessment, and education for mental health care. The first step toward this goal is to know what kinds of depressive symptoms people are experiencing and the semantic relations between symptoms. In consultation records, depressive symptoms are embedded in a single sentence or a discourse segment. A framework integrating the semantic dependencies of a sentence (intrasentence) and the strength of lexical cohesion between sentences (intersentence) supports data-mining the symptoms in these records. In addition, a domain ontology helps to mine the semantic relations between extracted symptoms. Experimental results show that all the intrasentence dependency, intersentence dependency, and domain ontology are significant features in the mining task. This article is part of a special issue on data mining in bioinformatics.
Index Terms:
data mining, natural language processing, semantic dependency, lexical cohesion, domain ontology
Citation:
Chung-Hsien Wu, Liang-Chih Yu, Fong-Lin Jang, "Using Semantic Dependencies to Mine Depressive Symptoms from Consultation Records," IEEE Intelligent Systems, vol. 20, no. 6, pp. 50-58, Nov./Dec. 2005, doi:10.1109/MIS.2005.115 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb