An improved text similarity algorithm research for clinical decision support system

The paper presents an improved text similarity algorithm and applies to the Clinical Decision Support System. It can improve the efficiency of decision making. After analyzing the disadvantages of the conventional TF-IDF algorithm and Cosine Similarity calculation, we propose an improvement to the text similarity algorithm. The proposed algorithm takes into full consideration the impact of semantically-similar keywords and textually-similar keywords on text similarity, therefore achieves improved accuracy. The function of this Clinical Decision Support System is to search for relevant biomedical articles and locate solutions.

[1]  Xilin Chen,et al.  Text similarity computing based on sememe Vector Space , 2013, 2013 IEEE 4th International Conference on Software Engineering and Service Science.

[2]  Wael Hassan Gomaa,et al.  A Survey of Text Similarity Approaches , 2013 .

[3]  H. Mcdonald,et al.  Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review. , 2005, JAMA.

[4]  George Forman,et al.  BNS feature scaling: an improved representation over tf-idf for svm text classification , 2008, CIKM '08.

[5]  Andreas Handojo,et al.  Application of Topic Based Vector Space Model with WordNet , 2011, 2011 International Conference on Uncertainty Reasoning and Knowledge Engineering.

[6]  Kam-Fai Wong,et al.  Interpreting TF-IDF term weights as making relevance decisions , 2008, TOIS.

[7]  Edward Omiecinski,et al.  Alternative Interest Measures for Mining Associations in Databases , 2003, IEEE Trans. Knowl. Data Eng..

[8]  Hui Xiong,et al.  Hyperclique pattern discovery , 2006, Data Mining and Knowledge Discovery.

[9]  Xiaoping Xu,et al.  A Kind of Improved Vector Space Model , 2009, 2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing.