Evaluation of potential features present in short texts in spanish in order to classify them by polarity
This work describes the identification and evaluation process of potential text markers for sentiment analysis. The evaluation of the markers and their use as part of the feature extraction process from plain text that is needed for sentiment analysis is presented. The evaluation of text markers obt...
| Main Authors: | , , |
|---|---|
| Format: | Online |
| Language: | spa |
| Published: |
Universidad de Costa Rica. Campus Rodrigo Facio. Sitio web: https://www.ucr.ac.cr/ Teléfono: (506) 2511-4000. Correo de soporte: revistas@ucr.ac.cr
2017
|
| Online Access: | https://revistas.ucr.ac.cr/index.php/kanina/article/view/30223 |
| id |
KANINA30223 |
|---|---|
| record_format |
ojs |
| spelling |
KANINA302232022-05-31T02:52:01Z Evaluation of potential features present in short texts in spanish in order to classify them by polarity Casasola Murillo, Édgar Leoni de León, Antonio Marín Raventós, Gabriela sentiment analysis information gain feature vectors polarity classification This work describes the identification and evaluation process of potential text markers for sentiment analysis. The evaluation of the markers and their use as part of the feature extraction process from plain text that is needed for sentiment analysis is presented. The evaluation of text markers obtained as a result of systematic analysis from a corpus over a second one allowed us to identify that emphasized positive words that tend to appear in positive text posts. The second corpus allowed us to evaluate the relation between the polarity of morphological text markers and the text they appear in. The evaluation of the markers for polarity detection task, in combination with a polarized dictionary, produced polarity classification average precision of 0.56 % using only three markers. These are promising results if we compared them to the top 0.69 % obtained using more features and specialized dictionaries for the same task. Universidad de Costa Rica. Campus Rodrigo Facio. Sitio web: https://www.ucr.ac.cr/ Teléfono: (506) 2511-4000. Correo de soporte: revistas@ucr.ac.cr 2017-08-16 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Article Article application/pdf https://revistas.ucr.ac.cr/index.php/kanina/article/view/30223 10.15517/rk.v40i4.30223 Káñina; Vol. 40 No. 4 (2016): Káñina número extraordinario; 21-32 Káñina; Vol. 40 Núm. 4 (2016): Káñina número extraordinario; 21-32 Káñina; Vol. 40 N.º 4 (2016): Káñina número extraordinario; 21-32 2215-2636 0378-0473 spa https://revistas.ucr.ac.cr/index.php/kanina/article/view/30223/30203 Derechos de autor 2017 Káñina |
| institution |
Universidad de Costa Rica |
| collection |
Káñina |
| language |
spa |
| format |
Online |
| author |
Casasola Murillo, Édgar Leoni de León, Antonio Marín Raventós, Gabriela |
| spellingShingle |
Casasola Murillo, Édgar Leoni de León, Antonio Marín Raventós, Gabriela Evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| author_facet |
Casasola Murillo, Édgar Leoni de León, Antonio Marín Raventós, Gabriela |
| author_sort |
Casasola Murillo, Édgar |
| description |
This work describes the identification and evaluation process of potential text markers for sentiment analysis. The evaluation of the markers and their use as part of the feature extraction process from plain text that is needed for sentiment analysis is presented. The evaluation of text markers obtained as a result of systematic analysis from a corpus over a second one allowed us to identify that emphasized positive words that tend to appear in positive text posts. The second corpus allowed us to evaluate the relation between the polarity of morphological text markers and the text they appear in. The evaluation of the markers for polarity detection task, in combination with a polarized dictionary, produced polarity classification average precision of 0.56 % using only three markers. These are promising results if we compared them to the top 0.69 % obtained using more features and specialized dictionaries for the same task. |
| title |
Evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| title_short |
Evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| title_full |
Evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| title_fullStr |
Evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| title_full_unstemmed |
Evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| title_sort |
evaluation of potential features present in short texts in spanish in order to classify them by polarity |
| publisher |
Universidad de Costa Rica. Campus Rodrigo Facio. Sitio web: https://www.ucr.ac.cr/ Teléfono: (506) 2511-4000. Correo de soporte: revistas@ucr.ac.cr |
| publishDate |
2017 |
| url |
https://revistas.ucr.ac.cr/index.php/kanina/article/view/30223 |
| work_keys_str_mv |
AT casasolamurilloedgar evaluationofpotentialfeaturespresentinshorttextsinspanishinordertoclassifythembypolarity AT leonideleonantonio evaluationofpotentialfeaturespresentinshorttextsinspanishinordertoclassifythembypolarity AT marinraventosgabriela evaluationofpotentialfeaturespresentinshorttextsinspanishinordertoclassifythembypolarity |
| _version_ |
1810112808905342976 |