The present invention enables analysis of customer needs with a high level of precision, not by indicating whether the customer opinions are positive or negative, but by quantitatively indicating their levels of importance. An information processor storing customer opinion information containing document data expressing opinions of customers in natural language, includes: a morphological analysis unit which parses document data into individual words, correlates each individual word to a grammatical part of speech, and outputs resultant data; a syntactic analysis unit which uses the data outputted from the morphological analysis unit to analyze content of the document; a clustering unit which uses the processing results from the syntactic analysis unit to categorize and output the customer opinion information according to predetermined customer needs; an evaluative word definition unit which receives, from a user, a setting of a keyword for evaluating the customer needs and an evaluation value for the keyword; and a tally processing unit which calculates a score indicating level of importance of the customer need, by using the customer opinion information categorized by the customer needs, along with the keyword and evaluation value set for the keyword.