Table 13: Processing accuracy of removal of noise words (Data consists of 1000 samples extracted randomly from web data using the Hot Pepper API from within Tokyo prefecture).

Number of samples 1000 　 Is it necessary to remove noise words from names, as determined by a manual check? Yes: 545 No: 455 　 Can we get the same result as manual processing using the FAW dictionary? Yes: 67 No: 478 　 　 　 Can we get the same result as manual processing using the dictionary of geographic names and station names? 　 Yes: 237 No: 241 　 　 　 Can we get the same result as manual processing after LFAW removal? 　 　 Yes:81 No:160 　 　 　 Do pure names remain after all noise word removal processing? 　 　 　 　 Yes: 409 No: 46 Sum total Number of data processed successfully 67 237 81 0 409 0 794 Processing accuracy (%) 　 79.40

“Hot Pepper” is a famous free coupon magazine in Japan, produced by Recruit Co., Ltd. Using the Hot Pepper API, we can collect information about many kinds of shops, companies, restaurants, and so forth.