• 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 : 7 / 44 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ½º¸¶Æ®Æù ¾îÇø®ÄÉÀÌ¼Ç ¼³Ä¡ ¸ñ·ÏÀ» ÀÌ¿ëÇÑ »ç¿ëÀÚ Æ¯¼º Ãß·Ð
¿µ¹®Á¦¸ñ(English Title) Inferring User Traits from Applications Installed on a Smart Phone
ÀúÀÚ(Author) ±âÈ«µµ   ÀÌÀçÈ«   ¹ÚÈñ¿õ   ä¹®Á¤   ÃÖ»ó¿ì   ¹ÚÁ¾Çå   Hongdo Ki   Jaehong Lee   Heewoong Park   Moon-jung Chae   Sangwoo Choi   Jonghun Park  
¿ø¹®¼ö·Ïó(Citation) VOL 45 NO. 12 PP. 1240 ~ 1249 (2018. 12)
Çѱ۳»¿ë
(Korean Abstract)
½º¸¶Æ®ÆùÀÇ »ç¿ëÀÌ º¸ÆíÈ­µÊ¿¡ µû¶ó °³ÀÎÈ­ ¼­ºñ½º¿¡ ´ëÇÑ ¿ä±¸°¡ Áõ°¡ÇÏ°í ÀÖ´Ù. ÀÌ¿¡ µû¶ó °³ÀÎÈ­ ¼­ºñ½º¸¦ Á¦°øÇÒ ¶§ À¯¿ëÇÏ°Ô È°¿ëµÉ ¼ö ÀÖ´Â »ç¿ëÀÚ Æ¯¼ºÀ», µ¥ÀÌÅÍ ±â¹ÝÀ¸·Î Åë°è ÇнÀÀ» ÀÌ¿ëÇØ Ãß·ÐÇÏ´Â ¿¬±¸°¡ È°¹ßÈ÷ ÁøÇàµÇ°í ÀÖ´Ù. º» ¿¬±¸¿¡¼­´Â »ç¿ëÀÚÀÇ °ü½É»ç¿Í »ýÈ°½À°üÀ» ¹Ý¿µÇÏ°í ÀÖÀ» »Ó¸¸ ¾Æ´Ï¶ó, ÀûÀº ºñ¿ëÀ¸·Î ¼öÁýÇÒ ¼ö ÀÖ´Â ¾îÇø®ÄÉÀÌ¼Ç ¼³Ä¡ ¸ñ·ÏÀ¸·ÎºÎÅÍ ¿äÀÎ º¤Å͸¦ ÃßÃâÇÏ¿© »ç¿ëÀÚ Æ¯¼ºÀ» Ãß·ÐÇÑ´Ù. Ãß·Ð °úÁ¤¿¡¼­´Â ¼³Ä¡ ¸ñ·Ï°ú ´õºÒ¾î ¾îÇø®ÄÉÀÌ¼Ç ½ºÅä¾î¿¡¼­ ȹµæ °¡´ÉÇÑ ¸ÞŸÁ¤º¸ÀÎ Ä«Å×°í¸®¿Í ¼³¸í±ÛÀ» ÀÌ¿ëÇÏ¿© »ç¿ëÀÚ¸¦ Ç¥ÇöÇÏ´Â ³× °¡Áö ¿äÀÎ º¤Å͸¦ ¸¸µé¾î »ç¿ëÇÑ´Ù. ƯÈ÷, Àΰø ½Å°æ¸Á ±â¹ÝÀÇ ÅؽºÆ® ÀÓº£µù ±â¹ýÀÎ Doc2VecÀ» ¼³¸í±Û¿¡ Àû¿ëÇÑ ¿äÀÎ º¤Å͸¦ »ç¿ëÇÑ´Ù. ¶ÇÇÑ, ¿äÀÎ º¤ÅÍ ÃßÃâ¿¡ ÀÌ¿ëµÇ´Â ¾îÇø®ÄÉÀ̼ÇÀ» ¼±º°ÇÏ´Â ±âÁØÀ» Á¦½ÃÇÏ¿© Ãß·Ð ¼º´ÉÀ» ³ôÀÌ°íÀÚ ÇÏ¿´´Ù. ±¹³» ½º¸¶Æ®Æù »ç¿ëÀÚ 100¸íÀ¸·ÎºÎÅÍ µ¥ÀÌÅ͸¦ ¼öÁýÇÏ¿© ¼ºº°, ¿¬·É, ¿¬¾Ö »óÅÂ, °ÅÁÖÇüÅÂ, µ¿°Å ¿©ºÎ, ¼öÀÔ ¼öÁØ, ÁöÃâ ¼öÁØ, ½ÅÀå, üÁß, Á¾±³, À̼ö Çбâ, ´Ü°ú´ëÇÐÀ» Ãß·ÐÇÏ´Â ½ÇÇèÀ» ¼öÇàÇßÀ¸¸ç, Á¦¾È ±â¹ýÀÇ ¿ì¼ö¼ºÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Needs for customized services are increasing as a smart phone personalized device, has been used generally. Demographic information is beneficial for customized services, so inferring user traits based various data using statistical learning has been actively studied. This study conducted experiments of inferring user traits with a list of installed applications differed by users¡¯ interest and lifestyle, and may can be accessed easily as a snapshot without explicit permission. Four feature vectors are used for inferring user traits, including vectors using application category or description that can be collected from the application market. Especially, one of the feature vectors is generated by applying Doc2Vec, a text embedding method based on a neural network, to application description. The application selection method we proposed is also used to achieve better performances than could be achieved by using all applications on the list. Last, we collected 100 lists of installed applications for experiments of inferring gender, age, relationship status, residential type, living together or not, income, outcome, height, weight, religion, semester and college, and confirmed effectiveness of proposed feature vectors and the application selection method.
Å°¿öµå(Keyword) »ç¿ëÀÚ Æ¯¼º Ã߷Р  Àα¸Åë°èÇÐ Á¤º¸ Ã߷Р  »ç¿ëÀÚ ÇÁ·ÎÆÄÀϸµ   ½º¸¶Æ®Æù ¾îÇø®ÄÉÀÌ¼Ç ¼³Ä¡ ¸ñ·Ï   ½º¸¶Æ®Æù ¾îÇø®ÄÉÀÌ¼Ç ¸ÞŸÁ¤º¸   ÅؽºÆ® ÀÓº£µù   ¿äÀÎ ¼±Åà  user properties inference   demographic inference   user profiling   installed applications on smart phone   application meta-information   text embedding   feature selection  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå