• 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 C : ÄÄÇ»ÆÃÀÇ ½ÇÁ¦

Á¤º¸°úÇÐȸ ³í¹®Áö C : ÄÄÇ»ÆÃÀÇ ½ÇÁ¦

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) SNS¿¡¼­ ´Ü¾î °£ À¯»çµµ ±â¹Ý ´Ü¾îÀÇ Äè-ºÒÄè Áö¼ö ÃßÁ¤
¿µ¹®Á¦¸ñ(English Title) Estimating a Pleasure-Displeasure Index of Word based on Word Similarity in SNS
ÀúÀÚ(Author) ÀÌ°­º¹   ¹éÁ¾¹ü   À̼ö¿ø   Kangbok Lee   Jongbum Baik   Soowon Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 20 NO. 03 PP. 0159 ~ 0164 (2014. 03)
Çѱ۳»¿ë
(Korean Abstract)
°¨¼º ºÐ¼®Àº ÀÚ¿¬¾ð¾î ó¸® ±â¼ú ¹× ÅؽºÆ®¸¶ÀÌ´× ±â¼úÀ» È°¿ëÇÏ¿© ÅؽºÆ® µ¥ÀÌÅͷκÎÅÍ ÁÖ°üÀû Á¤º¸¸¦ ÀÎ½Ä ¹× ÃßÃâÇÏ´Â ±â¼ú·Î¼­, ºÐ¼®ÇÏ°íÀÚ ÇÏ´Â ¹®¼­¿¡ Æ÷ÇÔµÈ °¨¼º´Ü¾îÀÇ °¨¼º Áö¼ö¸¦ ÀÌ¿ëÇÏ¿© ¼öÇàµÈ´Ù. ´ë´Ù¼öÀÇ °¨¼º ºÐ¼® ¿¬±¸¿¡¼­´Â °¨¼º´Ü¾î¸¦ ±àÁ¤-ºÎÁ¤ÀÇ µÎ °¡Áö·Î ºÐ·ùÇÏ´Â ¿¬±¸¸¦ ¼öÇàÇÏ¿´°í, ÃÖ±Ù¿¡´Â ±â»Ý, ½½ÇÄ, È­³²°ú °°ÀÌ ´Ù¾çÇÑ °¨¼ºÀ¸·Î ºÐ·ùÇÏ´Â ¿¬±¸µé ¿ª½Ã È°¹ßÈ÷ ÁøÇà ÁßÀÌ´Ù. ¸¸¾à °¨¼º Á¤µµ¸¦ Á¤·®ÀûÀ¸·Î ³ªÅ¸³¾ ¼ö ÀÖ´Ù¸é º¸´Ù Á¤¹ÐÇÑ °¨¼º ºÐ¼®À» ¼öÇàÇÒ ¼ö ÀÖ°ÚÁö¸¸, ´Ü¾îÀÇ °¨¼º Á¤µµ¸¦ Á¤·®È­ÇÏ´Â ¿¬±¸´Â ã±â Èûµé´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â ´Ü¾î °£ À¯»çµµ¸¦ ±â¹ÝÀ¸·Î ½Å±Ô ´Ü¾îÀÇ Äè-ºÒÄè Áö¼ö¸¦ ÃßÁ¤ÇÏ´Â ¹æ¹ý·ÐÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ½Ã½ºÅÛÀº Àüó¸®, ÀÚÁú¾î ¼±ÅÃ, µ¿½Ã ÃâÇö ´Ü¾î¿ÍÀÇ ¿¬°ü¼º °è»ê, ´Ü¾î °£ À¯»çµµ °è»êÀÇ ´Ü°è¸¦ °ÅÃÄ ÃÖÁ¾ÀûÀ¸·Î Äè-ºÒÄè Áö¼ö ÀÚµ¿ ÃßÁ¤À» ¼öÇàÇÑ´Ù. ½ÇÇè °á°ú ±âÁ¸ ¹æ¹ýµé¿¡ ºñÇØ ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Sentiment analysis is a technology that extracts subjective information from text data by using natural language processing and text mining. In general, sentiment analysis is conducted based on sentiment of words in a document. Most researches have considered only positive/negative as sentiment classes, while recently many researches consider more diverse sentiments such as happy, sad and angry. However, a problem is how to estimate a sentiment index of a word. In this paper, we propose a method to estimate pleasure-displeasure index of words using similarities between words. In order to automatically estimate pleasure-displeasure index, we conducted our experiment based on following steps: 1) preprocessing 2) feature selection 3) cooccurrence-word-based association analysis 4) word similarity calculation. The experimental results show that the proposed method performs better comparing with existing methods.
Å°¿öµå(Keyword) °¨¼º ºÐ¼®   °¨¼º »çÀü   ´Ü¾î °£ À¯»çµµ   Äè-ºÒÄè Áö¼ö ÃßÁ¤   sentiment analysis   sentiment word dictionary   words similarity   pleasure-displeasure index estimation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå