SUPPORTING INTERACTIVE TEXT MINING PROCESS WITH DIALOG IN NATURAL LANGUAGE

摘要

A mechanism is provided in a data processing system that has at least one processor and at least one working memory, the at least one working memory having instructions that are executed by the at least one processor to cause the at least one processor to execute a document analysis unit implement statistical analysis of documents in terms of one facet. An acceptance module accepts a sentence in natural language. An extraction module extracts a first facet from the sentence in natural language. A statistical analysis module performs a first statistical analysis of a group of documents related to the first facet and determines a value of the first facet based on a result of the first statistical analysis in response to information extracted from the natural language sentence, the information requiring a second statistical analysis. The statistical analysis module performs the second statistical analysis of the set of documents using the value of the first facet. A user interface represents a second facet that has been determined based on a result of the second statistical analysis.