Unsupervised detection and categorization of word clusters in text data

摘要

Categorizing data sets obtained from a number of sources includes determining the frequency of appearance of symbols in a first collection of data sets and the frequency of appearance of symbols in a second collection of data sets, determining the most significant symbols for the second collection based on the frequency of appearance in the first collection and the frequency of appearance in the second collection, grouping the most significant symbols into groups according to their appearance in the same data set and ranking the data sets in relation to the symbol groups according to a ranking scheme. Related methods, devices, and/or computer program products are described.