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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Àå¼Ò ÃßõÀ» À§ÇÑ ¹æ¹® °£°Ý º¸Á¤
¿µ¹®Á¦¸ñ(English Title) Temporal Interval Refinement for Point-of-Interest Recommendation
ÀúÀÚ(Author) ±è¹Î¼®   ÀÌÀç±æ   Minseok Kim   Jae-Gil Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 34 NO. 03 PP. 0086 ~ 0098 (2018. 12)
Çѱ۳»¿ë
(Korean Abstract)
Àå¼ÒÃßõ½Ã½ºÅÛÀº ½Ã°£°ú Àå¼Ò°¡ ÁÖ¾îÁ³À» ¶§, »ç¿ëÀÚ¿¡°Ô °¡Àå Èï¹Ì·Î¿î Àå¼Ò¸¦ ÃßõÇØÁÖ´Â ½Ã½ºÅÛÀ» ¸»ÇÑ´Ù. ½º¸¶Æ®Æù°ú »ç¹°ÀÎÅͳÝ(IoT), Àå¼Ò±â¹Ý ¼Ò¼È³×Æ®¿öÅ©(LBSN)ÀÇ ¹ß´Þ¿¡ ÈûÀÔ¾î »ç¿ëÀÚµéÀÇ ¹æ´ëÇÑ ¾çÀÇ Àå¼Ò ¹æ¹® µ¥ÀÌÅ͸¦ ÃàÀûÇÏ°Ô µÇ¾ú°í, À̸¦ ÅëÇØ Æ¯Á¤ÇÑ ½ÃÁ¡¿¡ »ç¿ëÀÚµéÀÌ ¿øÇÏ´Â Àå¼Ò¸¦ ÀûÀýÈ÷ ÃßõÇØÁÙ ¼ö ÀÖ´Â Àå¼ÒÃßõ½Ã½ºÅÛÀÇ Á߿伺ÀÌ ºÎ°¢µÇ¾ú´Ù. Àå¼ÒÃßõ½Ã½ºÅÛÀº »ç¿ëÀÚÀÇ ¹æ¹®(Check-in) Ƚ¼ö¶ó´Â ¾Ï½ÃÀû Çǵå¹é(Implicit feedback) µ¥ÀÌÅÍ¿¡¼­ »ç¿ëÀÚÀÇ ½ÃÄö½º ¼±È£(Sequential preference)¸¦ À̲ø¾î³»¾î ³ôÀº ¼º´ÉÀ» ³»±â À§ÇÑ ¿¬±¸µéÀÌ Á¦¾ÈµÇ¾ú´Ù. ÇÏÁö¸¸ ½ÃÄö½º ¼±È£ Á¤º¸¸¦ È°¿ëÇÏ¿© ¸ðµ¨À» ±¸¼ºÇÏ´Â °æ¿ì, µ¥ÀÌÅÍÀÇ ¹Ðµµ°¡ ´õ¿í Èñ¹ÚÇØÁö°í ÀÌ¿¡ µû¶ó ÀûÀº ¼öÀÇ µ¥ÀÌÅÍ¿¡ ±â¹ÝÇÏ¿© ±¸ÃàµÇ´Â ¸ðµ¨ÀÇ ¼º´ÉÀÌ ¿Ö°îµÉ °¡´É¼ºÀÌ Á¸ÀçÇÑ´Ù. º» ¿¬±¸¿¡¼­´Â ½Å·Úµµ(Confidence)¿¡ ±â¹ÝÇÏ¿© ¹æ¹® Áֱ⸦ º¸Á¤ÇÏ´Â ¹æ¹ý·ÐÀ» Á¦¾ÈÇÑ´Ù. »ç¿ëÀÚÀÇ ½ÃÄö½º ¼±È£ Á¤º¸·ÎºÎÅÍ µµÃâµÈ Àå¼Ò °£ ¹æ¹® ½Ã°£ÀüÀÌ°£°Ý(temporal transition interval)À» È°¿ëÇÏ¿© Ãßõ½Ã½ºÅÛÀ» ±¸¼ºÇÒ ¶§, ÇØ´ç ¹æ¹ý·ÐÀ» ÅëÇÏ¿© µ¥ÀÌÅÍÀÇ ¿Ö°îÀ» º¸Á¤ÇÔÀ¸·Î½á Ãßõ½Ã½ºÅÛÀÇ ¼º´ÉÀ» Çâ»óÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ È¿°ú¸¦ °ËÁõÇϱâ À§ÇÏ¿©, Foursquare¿Í GowallaÀÇ µ¥ÀÌÅͼÂÀ» ÀÌ¿ëÇÑ ºñ±³½ÇÇèÀ» ÅëÇØ Á¦¾ÈÇÏ´Â ¹æ¹ý·ÐÀÇ ¿ì¼ö¼ºÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Point-of-Interest(POI) recommendation systems suggest the most interesting POIs to users considering the current location and time. With the rapid development of smartphones, internet-of-things, and location-based social networks, it has become feasible to accumulate huge amounts of user POI visits. Therefore, instant recommendation of interesting POIs at a given time is being widely recognized as important. To increase the performance of POI recommendation systems, several studies extracting users¡¯ POI sequential preference from POI check-in data, which is intended for implicit feedback, have been suggested. However, when constructing a model utilizing sequential preference, the model encounters possibility of data distortion because of a low number of observed check-ins which is attributed to intensified data sparsity. This paper suggests refinement of temporal intervals based on data confidence. When building a POI recommendation system using temporal intervals to model the POI sequential preference of users, our methodology reduces potential data distortion in the dataset and thus increases the performance of the recommendation system. We verify our model¡¯s effectiveness through the evaluation with the Foursquare and Gowalla dataset.
Å°¿öµå(Keyword) Ãßõ½Ã½ºÅÛ   ½Å·Úµµ   Àå¼ÒÃßõ½Ã½ºÅÛ   µ¥ÀÌÅ͸¶ÀÌ´×   ½ÃÄö½º ¼±È£   º¸Á¤   µ¥ÀÌÅÍ Èñ¹Ú¼º   Recommendation system   Confidence   POI-Recommendation system   Data Mining   Sequential Preference   Refinement   Data Sparsity  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå