Title :
Descriminant Words for Problems in Scientific Articles
Author :
Sakai, Toshihiko ; Zeng, Jun ; Flanagan, Brendan ; Nakatoh, Tetsuya ; Hirokawa, Sachio
Author_Institution :
Grad. Sch. of Inf. Sci. & Electr. Eng., Kyushu Univ., Fukuoka, Japan
fDate :
May 30 2012-June 1 2012
Abstract :
Various viewpoints are required to make a survey and a trend analysis on related research. In order to find important problems, especially in unfamiliar field, simple search and clustering is not enough. We have to read most of the articles carefully. The work requires a lot of time and effort. This paper analyzes the sentences that describe the problem using SVM. It turned out the negative words are more effective in discernment than manually selected clue words or the positive words.
Keywords :
support vector machines; word processing; SVM; discriminant words; negative words; positive words; scientific articles; sentences; support vector machines; Abstracts; Data mining; Educational institutions; Feature extraction; Machine learning; Patents; Support vector machines; feature words; problem sentence of paper abstract; related work search; svm;
Conference_Titel :
Computer and Information Science (ICIS), 2012 IEEE/ACIS 11th International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4673-1536-4
DOI :
10.1109/ICIS.2012.42
