GREY SENTIMENT ANALYSIS USING MULTIPLE LEXICONS
| Affiliation auteurs | !!!! Error affiliation !!!! |
| Titre | GREY SENTIMENT ANALYSIS USING MULTIPLE LEXICONS |
| Type de publication | Conference Paper |
| Year of Publication | 2016 |
| Auteurs | Cotfas L-A, Delcea C, Roxin I |
| Editor | Boja C, Doinea M, Ciurea C, Pocatilu P, Batagan L, Velicanu A, Popescu ME, Manafi I, Zamfiroiu A, Zurini M |
| Conference Name | INTERNATIONAL CONFERENCE ON INFORMATICS IN ECONOMY, IE 2016: EDUCATION, RESEARCH & BUSINESS TECHNOLOGIES |
| Publisher | Bucharest Univ Econ Studies; Dept Econ Informat & Cybernet; INFOREC Ass |
| Conference Location | 6, PIATA ROMA, 1ST DISTRICT, POSTAL OFFICE 22, BUCHAREST, 010374, ROMANIA |
| Mots-clés | grey systems, opinion mining, sentiment analysis, Social media analysis, twitter |
| Résumé | Polarity detection is one of the most important tasks in sentiment analysis, aiming to determine whether a text expresses a positive, negative or neutral perception. Existing approaches mainly rely on using lists of words with associated polarity scores, called sentiment lexicons. Building both comprehensive and accurate lexicons, while a key factor for sentiment analysis, has been shown to be a challenging task. The contributions of the present paper are two folded. From the theoretical point of view, the paper investigates how existing lexicons can be combined using grey system theory in order to improve sentiment analysis results. From the practical point of view, the paper includes a link towards the associated source code, thus allowing other researchers to easily test and expend upon the proposed approach. |