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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ½ºÆÔ ÇÊÅ͸µÀ» À§ÇÑ Áö½Ä ±×·¡ÇÁ ±â¹ÝÀÇ ½ÅÁ¶¾î °¨Áö ¸ÅÄ¿´ÏÁò
¿µ¹®Á¦¸ñ(English Title) Knowledge Graph-based Korean New Words Detection Mechanism for Spam Filtering
ÀúÀÚ(Author) ±èÁöÇý   Á¤¿Á¶õ   Ji-hye Kim   Ok-ran Jeong  
¿ø¹®¼ö·Ïó(Citation) VOL 21 NO. 01 PP. 0079 ~ 0085 (2020. 02)
Çѱ۳»¿ë
(Korean Abstract)
¿À´Ã³¯ ½º¸¶Æ®Æù¿¡¼­ ½ºÆÔ ¹®ÀÚ¸¦ Â÷´ÜÇϱâ À§ÇØ ¹®ÀÚ ³»¿ë°ú ½ºÆÔ Å°¿öµåÀÇ ´Ü¼ø ¹®ÀÚ¿­ ºñ±³ ¶Ç´Â ½ºÆÔ ÀüÈ­¹øÈ£¸¦ Â÷´ÜÇÏ´Â ¹æ½ÄÀ» »ç¿ëÇÏ°í ÀÖ´Ù. ÀÌ¿¡ µû¶ó ½ºÆÔ ¹®ÀÚ°¡ ÀÚµ¿À¸·Î Â÷´ÜµÇ´Â °ÍÀ» ¹æÁöÇϱâ À§ÇØ Á¡Â÷ º¯È­µÈ ¹æ½ÄÀ¸·Î ½ºÆÔ ¹®ÀÚ¸¦ Àü¼ÛÇÑ´Ù. ƯÈ÷ ½ºÆÔ Å°¿öµå¿¡ Æ÷ÇԵǴ ´Ü¾îÀÇ °æ¿ì ´Ü¼ø ¹®ÀÚ¿­ ºñ±³·Î °Ë»öµÇÁö ¾Êµµ·Ï Ư¼ö¹®ÀÚ, ÇÑÀÚ, ¶ç¾î¾²±â µîÀ» ÀÌ¿ëÇÏ¿© ºñÁ¤»óÀûÀÎ ´Ü¾î·Î ½ºÆÔ ¹®ÀÚ¸¦ ¹ß¼ÛÇÑ´Ù. ±âÁ¸ ½ºÆÔ ÇÊÅ͸µ ¹æ½ÄÀÇ °æ¿ì ÀÌ·¯ÇÑ ½ºÆÔ ¹®ÀÚ¸¦ Â÷´ÜÇÒ ¼ö ¾ø´Ù´Â ÇÑ°è°¡ ÀÖ´Ù. µû¶ó¼­ º¯È­ÇÏ´Â ½ºÆÔ ¹®ÀÚ¿¡ ´ëÀÀÇÒ ¼ö ÀÖ´Â »õ·Î¿î ±â¼úÀÌ ÇÊ¿äÇÑ ½ÃÁ¡ÀÌ´Ù. º» ³í¹®¿¡¼­´Â ½ºÆÔ ¹®ÀÚ¿¡¼­ ÀÚÁÖ »ç¿ëµÇ´Â ½ÅÁ¶¾î¸¦ °ËÃâÇÏ¿© º¯È­ÇÏ´Â ½ºÆÔ ¹®ÀÚ¿¡ ´ëÀÀÇÒ ¼ö ÀÖ´Â Áö½Ä ±×·¡ÇÁ ±â¹ÝÀÇ ½ÅÁ¶¾î °¨Áö ¸ÅÄ¿´ÏÁòÀ» Á¦¾ÈÇÑ´Ù. ¶ÇÇÑ ±âº» Naive Bayes¿¡ °¨ÁöÇÑ ½ÅÁ¶¾î¸¦ Àû¿ëÇÏ¿© Á¦¾ÈÇÑ ¹æ¹ýÀÇ ¼º´É ½ÇÇè °á°ú¸¦ º¸¿©ÁØ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Today, to block spam texts on smartphone, a simple string comparison between text messages and spam keywords or a blocking spam phone numbers is used. As results, spam text is sent in a gradually hanged way to prevent if from being automatically blocked. In particular, for words included in spam keywords, spam texts are sent to abnormal words using special characters, Chinese characters, and whitespace to prevent them from being detected by simple string match. There is a limit that traditional spam filtering methods can¡¯t block these spam texts well. Therefore, new technologies are needed to respond to changing spam text messages. In this paper, we propose a knowledge graph-based new words detection mechanism that can detect new words frequently used in spam texts and respond to changing spam texts. Also, we show experimental results of the performance when detected Korean new words are applied to the Naive Bayes algorithm.
Å°¿öµå(Keyword) ½ºÆÔ ÇÊÅ͸µ   ½ºÆÔ Å½Áö   ½ÅÁ¶¾î °¨Áö   Áö½Ä±×·¡ÇÁ   ÄÁ¼Á³Ý   Spam Filtering   Spam Detection   New Words Detection   Knowledge Graph   ConceptNet  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå