Presentation 2006-03-06
Mining Algorithms for Frequent Weighted Sequential Patterns
Tomoyuki SHIBATA, Tomofumi NAKANO, Nobuhiro INUZUKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The frequent sequence pattern mining from sequence databases is interesting for many applications. For applying to English sentence analysis words, part-of-speech, and other attributes may become items being consisted sequences of. Then the items should be added some weights. Also for importance of words from educational viewpoints weights must to be treated. Therefore we study algorithms for frequent weighted sequence mining. First PrefixSpan, which explore patterns from shorter ones by extending to the right, is extended a simple extension of Paper shows that it is correct only when the weight of sequence are given by the minimum weight of items. In order to overcome this restriction we give an algorithm which extends patterns without the extension direction. The correctness is proved. We also give experiments with English corpus for efficiency evaluation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) datamining / text mining / language analysis / algorithms
Paper # AI2005-42
Date of Issue

Conference Information
Committee AI
Conference Date 2006/2/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Mining Algorithms for Frequent Weighted Sequential Patterns
Sub Title (in English)
Keyword(1) datamining
Keyword(2) text mining
Keyword(3) language analysis
Keyword(4) algorithms
1st Author's Name Tomoyuki SHIBATA
1st Author's Affiliation Department of Computer Science and Engineering Craduate School of Engineering, Nagoya Institute of Technology()
2nd Author's Name Tomofumi NAKANO
2nd Author's Affiliation Center for Information and Media Studies, Nagoya Institute of Technology
3rd Author's Name Nobuhiro INUZUKA
3rd Author's Affiliation Department of Computer Science and Engineering Craduate School of Engineering, Nagoya Institute of Technology
Date 2006-03-06
Paper # AI2005-42
Volume (vol) vol.105
Number (no) 639
Page pp.pp.-
#Pages 6
Date of Issue