Stemming Versus Light Stemming as Feature Selection Techniques for Arabic Text Categorization

QSpace/Manakin Repository

Stemming Versus Light Stemming as Feature Selection Techniques for Arabic Text Categorization

Show simple item record


dc.contributor.author Duwairi, Rehab
dc.contributor.author Al-Refai, Mohammad
dc.contributor.author Khasawneh, Natheer
dc.date.accessioned 2009-12-28T05:33:38Z
dc.date.available 2009-12-28T05:33:38Z
dc.date.issued 2007-11-18
dc.identifier.uri http://dx.doi.org/10.1109/IIT.2007.4430403
dc.identifier.uri http://hdl.handle.net/10576/10501
dc.description.abstract This paper compares and contrasts two feature selection techniques when applied to Arabic corpus; in particular; stemming, and light stemming were employed. With stemming, words are reduced to their stems. With light stemming, words are reduced to their light stems. Stemming is aggressive in the sense that it reduces words to their 3-letters roots. This affects the semantics as several words with different meanings might have the same root. Light stemming, by comparison, removes frequently used prefixes and suffixes in Arabic words. Light stemming doesn't produce the root and therefore doesn't affect the semantics of words; it maps several words, which have the same meaning to a common syntactical form. The effectiveness of above two feature selection techniques was assessed in a text categorization exercise for Arabic corpus. This corpus consists of 15000 documents that fall into three categories. The K-nearest neighbors (KNN) classifier was used in this work. Several experiments were carried out using two different representations of the same corpus; the first version uses stem- vectors; and the second uses light stem-vectors as representatives of documents. These two representations were assessed in terms of size, time and accuracy. The light stem representation was superior in terms of classifier accuracy when compared with stemming. en_US
dc.language.iso en en_US
dc.subject Arabic language en_US
dc.subject K-nearest neighbors classifier en_US
dc.subject feature selection en_US
dc.subject light-stemming en_US
dc.subject stemming en_US
dc.subject text categorization en_US
dc.title Stemming Versus Light Stemming as Feature Selection Techniques for Arabic Text Categorization en_US
dc.type Article en_US

Files in this item

Files Size Format View Description
Stemming Versus Light Stemming.pdf 2.971Mb PDF View/Open Stemming Versus Light Stemming as Feature Selection Techniques for Arabic Text Categorization

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account