çªç¶Cã§ã³ã¼ããæ¸ããããªã£ãã®ã§ï¼ãªãã¡ãã£ã¦è»¢ç½®ã¤ã³ãã¯ã¹ãç¨ããæ¤ç´¢ããã°ã©ã ãæ¸ãã¦ã¿ãï¼ è»¢ç½®ã¤ã³ãã¯ã¹ã¨ã¯ï¼ç´¢å¼èªã¨å¼ã°ããåèªãåºç¾ããææ¸æ
å ± (å ´åã«ãã£ã¦ã¯ä½ç½®æ
å ±ã) ãä¿æãããã¼ã¿æ§é ã®ãã¨ã§ï¼ç´¢å¼èªã¨ï¼ããã«å¯¾å¿ãã転置ãªã¹ãã«ãã£ã¦æ§æãããï¼ # ç´¢å¼èª -> 転置ãªã¹ã hoge -> 5: 1,2,3,4,5 fuga -> 3: 1,4,5 piyo -> 2: 4,5ããã¯ï¼hogeã¨ããåèªãææ¸1,2,3,4,5ã«åºç¾ãï¼fugaã¨ããåèªãææ¸1,4,5ã«åºç¾ãï¼piyoã¨ããåèªãææ¸4,5ã«åºç¾ããæ
å ±ãä¿æãã¦ããï¼æåã®5,3,2ã¨ããæ°åã¯ããããç´¢å¼èªãããã¤ã®ææ¸ã«åºç¾ãããã¨ããææ¸é »åº¦ (document frequency; DF) ã表ãã¦ããï¼ æ¤ç´¢ã¯ã¨ãªhogeãå
¥åãããå ´åã«ã¯ï¼ææ¸1,2,3,4,5ãæ¤ç´¢çµæã¨ã
{{#tags}}- {{label}}
{{/tags}}