• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Current Result Document : 2 / 5 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) °¨Á¤ ´Ü¾îÀÇ ÀǹÌÀû Ư¼ºÀ» ¹Ý¿µÇÑ Çѱ¹¾î ¹®¼­ °¨Á¤ºÐ·ù ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) A Korean Document Sentiment Classification System based on Semantic Properties of Sentiment Words
ÀúÀÚ(Author) ȲÀç¿ø   °í¿µÁß   Jaewon Hwang   Youngjoong Ko  
¿ø¹®¼ö·Ïó(Citation) VOL 37 NO. 04 PP. 0317 ~ 0322 (2010. 04)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº °¨Á¤´Ü¾î(Sentiment Word)ÀÇ ÀǹÌÀû Ư¼ºÀ» ¹Ý¿µÇÏ¿© Çѱ¹¾î ¹®¼­ °¨Á¤ºÐ·ù ½Ã½ºÅÛÀÇ ¼º´ÉÀ» Çâ»ó½Ãų ¼ö ÀÖ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. °¨Á¤´Ü¾î´Â °¨Á¤À» °¡Áö´Â ´Ü¾î¸¦ ÀǹÌÇϸç, °¨Á¤´Ü¾îµéÀÇ ÁýÇÕÀº °¨Á¤ÀÚÁú(Sentiment Feature)·Î½á °¨Á¤ºÐ·ù¸¦ À§ÇÑ Áß¿äÇÑ ¾îÈÖ ÀÚ¿øÀÌ´Ù. °¨Á¤ÀÚÁúÀº ÀϹÝÀûÀ¸·Î »ç¿ëµÉ ¶§¿Í ƯÁ¤ ¿µ¿ª(Domain)¿¡¼­ »ç¿ëµÉ ¶§¿¡ ±× °¨Á¤ Á¤µµÀÇ Â÷À̸¦ °¡Áø´Ù. °¨Á¤ÀÚÁúÀÌ ÀϹÝÀûÀ¸·Î »ç¿ëµÉ ¶§ ±× °¨Á¤ Á¤µµ´Â °Ë»ö ¿£ÁøÀ» ÅëÇØ ¾òÀ» ¼ö ÀÖ´Â ½º´ÏÇÍ(Snippet)À» ÅëÇØ ÃßÁ¤ÇÒ ¼ö ÀÖÀ¸¸ç, ƯÁ¤ ¿µ¿ª¿¡¼­ »ç¿ëµÉ ¶§ÀÇ °¨Á¤ Á¤µµ´Â ½ÇÇè ¸»¹¶Ä¡¸¦ ÀÌ¿ëÇÏ¿© ÃßÁ¤ÇÒ ¼ö ÀÖ´Ù. ÀÌ·¸°Ô ÃßÁ¤µÈ °¨Á¤ ÀÚÁúÀÇ °¨Á¤ Á¤µµ ¼öÄ¡¸¦ ÀǹÌÁöÇ⼺À̶ó°í Çϸç, ¹®¼­³»ÀÇ ¹®ÀåÀÇ °¨Á¤ °­µµ¸¦ ÃßÁ¤Çϱâ À§ÇØ ÀÌ¿ëµÈ´Ù. ¹®ÀåÀÇ °¨Á¤ °­µµ°¡ ÃßÁ¤µÇ¸é ¹®Àå °¨Á¤ °­µµ¸¦ °¨Á¤ÀÚÁúÀÇ °¡ÁßÄ¡¿¡ ¹Ý¿µÇÏ°Ô µÈ´Ù. º» ³í¹®Àº ÁöÁö º¤ÅÍ ±â°è(Support Vector Machine)¸¦ ÀÌ¿ëÇÏ¿© ÀϹÝÀû, ¿µ¿ª ÀÇÁ¸Àû, ÀϹÝÀû/¿µ¿ª ÀÇÁ¸Àû ÀǹÌÁöÇ⼺À» ¹Ý¿µÇÑ °æ¿ì¿¡ ´ëÇØ ¼º´ÉÀ» Æò°¡ÇÑ´Ù. Æò°¡ °á°ú, ¾ÕÀÇ 3°¡Áö °æ¿ì¿¡ ¸ðµÎ ¼º´É Çâ»óÀ» ¾ò¾úÀ¸¸ç ÀϹÝÀû/¿µ¿ª ÀÇÁ¸Àû ÀǹÌÁöÇ⼺À» ¹Ý¿µÇÑ °æ¿ì, ÀϹÝÀûÀÎ Á¤º¸ °Ë»ö¿¡¼­ »ç¿ëÇÏ´Â ³»¿ë¾î(Content Word) ±â¹ÝÀÇ ÀÚÁúÀ» »ç¿ëÇÑ °æ¿ìº¸´Ù 3.1%ÀÇ ¼º´É Çâ»óÀ» ¾òÀ» ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper proposes how to improve performance of the Korean document sentiment-classification system using semantic properties of the sentiment words. A sentiment word means a word with sentiment, and sentiment features are defined by a set of the sentiment words which are important lexical resource for the sentiment classification. Sentiment feature represents different sentiment intensity in general field and in specific domain. In general field, we can estimate the sentiment intensity using a snippet from a search engine, while in specific domain, training data can be used for this estimation. When the sentiment intensity of the sentiment features are estimated, it is called semantic orientation and is used to estimate the sentiment intensity of the sentences in the text documents. After estimating sentiment intensity of the sentences, we apply that to the weights of sentiment features. In this paper, we evaluate our system in three different cases such as general, domain-specific, and general/domain-specific semantic orientation using support vector machine. Our experimental results show the improved performance in all cases, and, especially in general/domain-specific semantic orientation, our proposed method performs 3.1% better than a baseline system indexed by only content words.
Å°¿öµå(Keyword) °¨Á¤´Ü¾î   °¨Á¤ÀÚÁú   °¨Á¤ºÐ·ù   ÀǹÌÁöÇ⼺   Sentiment word   Sentiment Feature   Sentiment Classification   Semantic Orientation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå