• 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¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¾îÈÖ °ü°è ¹× ¹®¸Æ Á¤º¸ ±â¹ÝÀÇ µµ¸ÞÀÎ °¨¼º»çÀü ÀÚµ¿ ±¸Ãà ¹æ¾È ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study on the Method for Automatically Constructing a Domain Specific Sentiment Lexicon Based Lexical Relation and Contextual Information
ÀúÀÚ(Author) ¹Ú»ó¹Î   ¿Âº´¿ø   Sangmin Park   Byung-Won On  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 10 PP. 0926 ~ 0941 (2020. 10)
Çѱ۳»¿ë
(Korean Abstract)
°¨¼º»çÀüÀº °¨¼º ¾îÈֵ鿡 ´ëÇÑ ÁýÇÕÀ¸·Î °¢ ¾îÈֵ鿡 ´ëÇÑ °¨¼ºÀÇ ±Ø¼ºÀÌ ºÎ¿©µÇ¾î ÀÖÀ¸¸ç, °¨¼º ºÐ¼®(Sentiment Analysis)À» À§ÇÑ ±âÃÊ ÀÚ·á·Î È°¿ëµÈ´Ù. ÇÏÁö¸¸ ÀÌ¿Í °°Àº °¨¼º ¾îÈÖµéÀº ƯÁ¤ µµ¸ÞÀο¡ µû¶ó ±Ø¼ºÀÌ ¿ªÀüµÇ°Å³ª À¯½ÇµÉ ¼öµµ ÀÖÀ¸¸ç ÀÇÁ¸ÀûÀÎ °¨¼º ¾îÈÖ°¡ Á¸ÀçÇÒ ¼ö ÀÖ´Ù. ¿¹¸¦ µé¸é, ÀϹÝÀûÀ¸·Î ¡®Àß Àä´Ù¡¯¶ó´Â ´Ü¾î´Â ±àÁ¤ÀÇ ±Ø¼ºÀ» º¸ÀÌÁö¸¸, ¿µÈ­ µµ¸ÞÀο¡¼­´Â ±× Àǹ̰¡ ºÎÁ¤À¸·Î ¾²ÀδÙ. ±×·¸±â ¶§¹®¿¡ °¨¼º»çÀüÀº ºÐ¼®ÇÏ°íÀÚ ÇÏ´Â µµ¸ÞÀÎÀÇ Æ¯Â¡ÀÌ ¹Ý¿µµÇ¾î ÀÖ¾î¾ß ÇÏ¸ç µµ¸ÞÀο¡ µû¶ó ¾Ë¸ÂÀº °¨¼º»çÀüÀÌ ±¸ÃàµÇ°í È°¿ëµÇ¾î¾ß ÇÑ´Ù. ÀÌ¿Í °°Àº ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ ÇöÀç µµ¸ÞÀÎ °¨¼º»çÀüÀ» ÀÚµ¿À¸·Î ±¸ÃàÇÏ´Â ´Ù¾çÇÑ ¿¬±¸µéÀÌ ³ª¿ÔÁö¸¸, Àΰ£ÀÇ °³ÀÔ, ¹®¸ÆÀû ¿ä¼Ò ¹Ì°í·Á, Áö¿ªÀûÀÎ Á¤º¸ ¹Ý¿µ µîÀ̶ó´Â ¹®Á¦Á¡À» Áö´Ï°í ÀÖ´Ù. º» ¿¬±¸¿¡¼­´Â ÀÌ¿Í °°Àº ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ Çѱ¹¾î ¹ü¿ë °¨¼º»çÀüÀÎ ¡®KNU Çѱ¹¾î °¨¼º»çÀü¡¯°ú ±Û·Îºê º¤ÅÍ ±×¸®°í Á¢¼Ó»ç °ü°è¸¦ È°¿ëÇÏ¿©, ƯÁ¤ µµ¸ÞÀÎÀÇ Àü¿ªÀûÀÎ °¨¼º Á¤º¸¿Í ¹®¸ÆÀû Ư¡À» ÃæºÐÈ÷ ¹Ý¿µÇÑ µµ¸ÞÀÎ °¨¼º»çÀü ±¸Ãà ¹æ¾ÈÀ» Á¦¾ÈÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
A sentiment lexicon is a set of sentiment words, each of which has its sentiment polarity, and is used as a basic method for sentiment analysis. However, the meaning of some words can be different or even the original meaning can disappear across domains. As such, many sentiment words are likely to depend on a specific domain. For example, the verb phrase ¡°slept well¡± usually has a negative meaning, while it has a positive meaning in movie domains. Thus, given a particular domain such as hotel, the sentiment lexicon should be constructed so that many of the domain-dependent words reflect the meaning of the domain. Using the domain-dependent sentiment lexicon will render more accurate results than using existing sentiment lexicons that do not consider domain-dependent words in the sentiment analysis. To build the domain-dependent sentiment lexicons, various studies have been presented, but there are many limitations including the human intervention and the use of local information rather than contextual information. In this paper, we propose a novel method of automatically constructing a domain-dependent sentiment lexicon based on the global and contextual information and an existing sentiment lexicon (i.e., KNU sentiment lexicon, Glove vector, Conjunction relation).
Å°¿öµå(Keyword) °¨¼º»çÀü   µµ¸ÞÀÎ °¨¼º»çÀü   ¹ÝÁöµµ ÇнÀ   °¨¼º ¾îÈÖ   ¾ð¾î Ç¥»ó   domain specific sentiment lexicon   semi-supervised learning   sentiment words   KNU sentiment lexicon   lexical relation   contextual information  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå