摘要 |
<p><P>PROBLEM TO BE SOLVED: To provide a word score calculator for detecting a word associated with a specific characteristic among words in an electronic document by considering association with other words in the document. <P>SOLUTION: In a first electronic document aggregation determined to be associated with a defined characteristic, a second electronic document aggregation determined not to be associated with the characteristic, and a collection of words with a plurality of words included therein, the calculator calculates a difference between a first information quantity reference amount and a second information quantity reference amount as a sore showing a degree of association between the specific word and the defined characteristic wherein the first quantity assumes that there is a causal relationship among the number of first electronic documents including the specific word included in the collection in the first aggregation, the number of second electronic documents including the specific words in the second aggregation, the number of third electronic documents not including the specific words in the first aggregation, and the number of fourth electronic documents not including the specific words in the second aggregation, while the second quantity assumes that there is no causal relationship. <P>COPYRIGHT: (C)2010,JPO&INPIT</p> |