"Text Mining-based Formation of Dictionaries Expressing Opinions in Natural Languages" . . "2"^^ . "[CA8DAFF86CD3]" . . . "Automatic formation of dictionaries containing words significant for expressing different customers' opinions written in natural languages is demonstrated. The research used very large real-world data concerning the hotel accommodation booking via the Internet. The hotel companies could be interested in characteristic words expressing positive and negative opinions because it could help improve the offered service. The suggested method uses unstructured plain text reviews of many customers from different countries. The data is transformed into vectors using the bag-of-words procedure with the word representation by their frequencies in the reviews. Significant words are selected as relevant attributes for the classification to given categories using trained decision trees. Each tree branch leading to a leaf represents a subset of significant words for a category. The individual word importance is weighted by the word frequency in all the branches combined with their occurrence in branches leading to specific categories. As a result, the generated dictionaries contain only a fraction of the original huge vocabulary. The selected words express very well the positive and negative meaning, which is demonstrated for several different languages using the same processing procedure."@en . "302647900059" . . "natural languages; text mining; opinion analysis; significant words; machine learning; decision tree"@en . . . . "Automatic formation of dictionaries containing words significant for expressing different customers' opinions written in natural languages is demonstrated. The research used very large real-world data concerning the hotel accommodation booking via the Internet. The hotel companies could be interested in characteristic words expressing positive and negative opinions because it could help improve the offered service. The suggested method uses unstructured plain text reviews of many customers from different countries. The data is transformed into vectors using the bag-of-words procedure with the word representation by their frequencies in the reviews. Significant words are selected as relevant attributes for the classification to given categories using trained decision trees. Each tree branch leading to a leaf represents a subset of significant words for a category. The individual word importance is weighted by the word frequency in all the branches combined with their occurrence in branches leading to specific categories. As a result, the generated dictionaries contain only a fraction of the original huge vocabulary. The selected words express very well the positive and negative meaning, which is demonstrated for several different languages using the same processing procedure." . . "235026" . "Da\u0159ena, Franti\u0161ek" . "RIV/62156489:43110/11:00215946" . "8"^^ . . "Brno" . "Text Mining-based Formation of Dictionaries Expressing Opinions in Natural Languages"@en . . "Brno" . . "Mendel 2011: 17th International Conference on Soft Computing" . . . "978-80-214-4302-0" . "RIV/62156489:43110/11:00215946!RIV14-MSM-43110___" . . . . "43110" . . "Z(MSM6215648904)" . "\u017Di\u017Eka, Jan" . . . "2011-01-01+01:00"^^ . "Vysok\u00E9 u\u010Den\u00ED technick\u00E9 v Brn\u011B" . "Text Mining-based Formation of Dictionaries Expressing Opinions in Natural Languages"@en . . . "Text Mining-based Formation of Dictionaries Expressing Opinions in Natural Languages" . "2"^^ .