Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
äÆà ´ëÈÀÇ ±¸¹®Àû Ư¼ºÀ» ÀÌ¿ëÇÑ Å©·Î½º-ÅؽºÆà ¹æÁö ½Ã½ºÅÛ |
¿µ¹®Á¦¸ñ(English Title) |
A Cross-Texting Prevention System Using Syntactic Characteristics of Chat Messages |
ÀúÀÚ(Author) |
ÀÌ´Ù¿µ
Á¶È¯±Ô
Da-Young Lee
Hwan-Gue Cho
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 48 NO. 06 PP. 0639 ~ 0648 (2021. 06) |
Çѱ۳»¿ë (Korean Abstract) |
Å©·Î½º-ÅؽºÆÃ(cross-texting)Àº ½Ç¼ö·Î ÀǵµÇÏÁö ¾ÊÀº »ó´ë¹æ¿¡°Ô ¸Þ½ÃÁö¸¦ À߸ø Àü¼ÛÇÏ´Â °ÍÀ» ¸»ÇÑ´Ù. ´Ù¼öÀÇ »ó´ë¹æ°ú µ¿½Ã¿¡ ´ëÈÇÒ ¶§ ºó¹øÇÏ°Ô ¹ß»ýÇÏ´Â ¹®Á¦·Î, ¸Þ½ÅÀú¿¡¼´Â ÁÖ·Î ¹ß¼Û Ãë¼Ò¶ó´Â ±â´ÉÀ» Á¦°øÇÏÁö¸¸ ÀÌ´Â »çÈÄ ÇØ°áÃ¥¿¡ ÇØ´çÇϸç, »ç¿ëÀÚ°¡ »çÀü¿¡ ½Ç¼ö¸¦ ¹æÁöÇϱâ´Â ¾î·Æ´Ù. º» ³í¹®¿¡¼´Â äÆà ¹®ÀåÀÇ Çü½ÄÀû Ư¡À» ºÐ¼®ÇÏ¿© Å©·Î½º-ÅؽºÆÃÀ» ŽÁöÇÏ´Â ¸ðµ¨À» Á¦¾ÈÇß´Ù. äÆà ¹®Àå¿¡¼ ³ôÀÓ¹ý, Ç¥ÃþÀû ¿Ï¼ºµµ ÀÚÁúÀ» ÃßÃâÇØ Æ¯Á¤ »ç¿ëÀÚÀÇ ÀÌÀü ´ëȸ¦ ¸ðµ¨¸µÇÏ°í, ÇöÀç ÁÖ¾îÁø ¹®ÀåÀÌ »ç¿ëÀÚ ´ëÈ ¸ðµ¨¿¡ ºÎÇÕÇÏ´ÂÁö ¿©ºÎ·Î Å©·Î½º-ÅؽºÆÃÀ» ŽÁöÇÑ´Ù. ÀÌ¿Í °°Àº ¹æ¹ýÀº »ç¿ëÀÚÀÇ Ã¤Æà ŵµÀÇ ÀÏ°ü¼ºÀ» ¸ðµ¨¸µÇÔÀ¸·Î½á ÀÇ¹Ì ºÐ¼®À» ÇÏÁö ¾Ê°í Çü½ÄÀû ÀÚÁú¸¸À¸·Î ¹®Á¦¸¦ ÇØ°áÇѵ¥ ÀÇÀÇ°¡ ÀÖ´Ù. º» ³í¹®¿¡¼ ±¸ÇöÇÑ ½Ã½ºÅÛÀ¸·Î ½ÇÁ¦ ¸Þ½ÅÀú ´ëÈ ¸»¹¶Ä¡¸¦ ÀÌ¿ëÇØ ÀÚµ¿À¸·Î »ý¼ºÇÑ µ¥ÀÌÅÍ¿¡¼ 85.5% Á¤È®µµ·Î Å©·Î½º-ÅؽºÆÃÀ» ŽÁöÇÒ ¼ö ÀÖÀ½À» È®ÀÎÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Cross-texting refers to accidentally sending a message to an unintended person. It occurs frequently when users chat with multiple counterparts at the same time. Messengers mainly provide a function of canceling sending, but it is only post solution, and users find it difficult to prevent mistakes in advance. In this paper, we proposed a cross-texting detection model by analyzing the syntactic characteristics of chat sentences. It modelizes the previous chat messages of a specific user by extracting the honorifics and completeness features from chat messages, and detects the cross-texting cases by determining whether the target sentences are in accordance with the user chat message model. This approach is significant as it solves the cross-texting detection problem only with syntactic characteristics without semantic analysis by modeling the consistency of the user's chat attitude. The proposed model detect cross-texting cases with an accuracy of 85.5% from automatically generated data using a real messenger dialogue corpus.
|
Å°¿öµå(Keyword) |
äÆà ¸Þ½ÃÁö
Å©·Î½º-ÅؽºÆÃ
³ôÀÓ¸» Ç¥Çö
¹®Àå ¿Ï¼ºµµ
¹®Àå º¤ÅÍ
chat message
cross-texting
honorifics
sentence completeness
sentence vector
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|