Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
¿Â¶óÀÎ Ä¿¹Â´ÏƼ »ç¿ëÀÚÀÇ Çൿ ÆÐÅÏÀ» °í·ÁÇÑ µ¿ÀÏ »ç¿ëÀÚÀÇ ´Ð³×ÀÓ ½Äº° ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
A Method for Identifying Nicknames of a User based on User Behavior Patterns in an Online Community |
ÀúÀÚ(Author) |
¹Ú»óÇö
¹Ú¼®
Sang-Hyun Park
Seog Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 45 NO. 02 PP. 0165 ~ 0174 (2018. 02) |
Çѱ۳»¿ë (Korean Abstract) |
¿Â¶óÀÎ Ä¿¹Â´ÏƼ¶õ SNS¿Í ´Þ¸® »ç¿ëÀÚµéÀÌ ´Ð³×ÀÓÀ» ÅëÇØ À͸íÀ¸·Î °ü½É»ç¿Í Ãë¹Ì¸¦ °øÀ¯ÇÏ´Â °¡»ó ±×·ì ¼ºñ½ºÀÌ´Ù. ±×·±µ¥ ÀÌ·± ÀÍ¸í¼ºÀ» ¾ÇÀÇÀûÀ¸·Î È°¿ëÇÏ´Â »ç¿ëÀÚµéÀÌ Á¸ÀçÇÏ°í, ´Ð³×ÀÓÀÇ º¯°æÀ¸·Î ÀÎÇØ µ¿ÀÏ »ç¿ëÀÚÀÇ µ¥ÀÌÅÍ°¡ ¼·Î ´Ù¸¥ ´Ð³×ÀÓ¿¡ Á¸ÀçÇÏ´Â µ¥ÀÌÅÍ ÆÄÆíÈ ¹®Á¦°¡ ¹ß»ýÇÒ ¼ö ÀÖ´Ù. ¶ÇÇÑ ¿Â¶óÀÎ Ä¿¹Â´ÏƼ¿¡¼´Â ´Ð³×ÀÓÀ» º¯°æÇÏ´Â ÀÏÀÌ ºó¹øÇϹǷΠµ¿ÀÏ »ç¿ëÀÚ¸¦ ½Äº°Çϴµ¥ ¾î·Á¿òÀ» °Þ´Â´Ù. µû¶ó¼ º» ³í¹®¿¡¼´Â ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ ¿Â¶óÀÎ Ä¿¹Â´ÏƼ Ư¼ºÀ» °í·ÁÇÑ »ç¿ëÀÚÀÇ ÇൿÆÐÅÏ Æ¯Â¡ º¤Å͸¦ Á¦½ÃÇϸç, °ü°è ÆÐÅÏÀ̶ó´Â »õ·Î¿î ¾Ï½ÃÀû Çൿ ÆÐÅÏÀ» Á¦¾ÈÇÔ°ú µ¿½Ã¿¡ ·£´ý Æ÷·¹½ºÆ®ºÐ·ù±â¸¦ ÀÌ¿ëÇÑ µ¿ÀÏ »ç¿ëÀÚÀÇ ´Ð³×ÀÓÀ» ½Äº°ÇÏ´Â ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ¶ÇÇÑ ½ÇÁ¦ ¿Â¶óÀÎ Ä¿¹Â´ÏƼ µ¥ÀÌÅ͸¦ ¼öÁýÇØ Á¦¾ÈÇÑ ÇൿÆÐÅÏ°ú ºÐ·ù±â¸¦ ÀÌ¿ëÇØ µ¿ÀÏ »ç¿ëÀÚ¸¦ À¯ÀǹÌÇÑ ¼öÁØÀ¸·Î ½Äº°ÇÒ ¼ö ÀÖÀ½À» ½ÇÇèÀûÀ¸·Î º¸ÀδÙ.
|
¿µ¹®³»¿ë (English Abstract) |
An online community is a virtual group whose members share their interests and hobbies anonymously with nicknames unlike Social Network Services. However, there are malicious user problems such as users who write offensive contents and there may exist data fragmentation problems in which the data of the same user exists in different nicknames. In addition, nicknames are frequently changed in the online community, so it is difficult to identify them. Therefore, in this paper, to remedy these problems we propose a behavior pattern feature vectors for users considering online community characteristics, propose a new implicit behavior pattern called relationship pattern, and identify the nickname of the same user based on Random Forest classifier. Also, Experimental results with the collected real world online community data demonstrate that the proposed behavior pattern and classifier can identify the same users at a meaningful level.
|
Å°¿öµå(Keyword) |
¿Â¶óÀÎ Ä¿¹Â´ÏƼ
Çൿ ÆÐÅÏ
»ç¿ëÀÚ ½Äº°
¾ÇÀÇÀû »ç¿ëÀÚ
µ¥ÀÌÅÍ ÆÄÆíÈ
±â°èÇнÀ
online community
behavior pattern
user identification
malicious user
data fragmentation
machine learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|