Algorithm for Detection of Positive and Negative Text
MetadataZobrazit celý záznam
In the present, obtaining and sorting knowledge from data produced by various sources requires significant effort which is not ensured easily by a human, meaning machine processing is taking place. Purpose of this work was to create a system capable of positive and negative emotion detection from text along with evaluation of its performance. System allows training with use of large amount of data (known as Big Data), exploiting Spark library. Classificator model was created with use of Support Vector Machines. Highest achieved accuracy is 78,05% for Czech, 79,73% for German and 91,88% for English.
Typ dokumentuRecenzovaný dokument
Verze dokumentuxmlui.vut.verze.Publishers's version
Zdrojový dokumentProceedings of the 22nd Conference STUDENT EEICT 2016. s. 161-163. ISBN 978-80-214-5350-0
- Student EEICT 2016