A New Feature Selection Scheme for Emotion Recognition from Text
This paper presents a new scheme for term selection in the field of emotion recognition from text. The proposed framework is based on utilizing moderately frequent terms during term selection. More specifically, all terms are evaluated by considering their relevance scores, based on the idea that mo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/15/5351 |
| _version_ | 1797560422463700992 |
|---|---|
| author | Zafer Erenel Oluwatayomi Rereloluwa Adegboye Huseyin Kusetogullari |
| author_facet | Zafer Erenel Oluwatayomi Rereloluwa Adegboye Huseyin Kusetogullari |
| author_sort | Zafer Erenel |
| collection | DOAJ |
| description | This paper presents a new scheme for term selection in the field of emotion recognition from text. The proposed framework is based on utilizing moderately frequent terms during term selection. More specifically, all terms are evaluated by considering their relevance scores, based on the idea that moderately frequent terms may carry valuable information for discrimination as well. The proposed feature selection scheme performs better than conventional filter-based feature selection measures Chi-Square and Gini-Text in numerous cases. The bag-of-words approach is used to construct the vectors for document representation where each selected term is assigned the weight 1 if it exists or assigned the weight 0 if it does not exist in the document. The proposed scheme includes the terms that are not selected by Chi-Square and Gini-Text. Experiments conducted on a benchmark dataset show that moderately frequent terms boost the representation power of the term subsets as noticeable improvements are observed in terms of Accuracies. |
| first_indexed | 2024-03-10T18:00:18Z |
| format | Article |
| id | doaj.art-b76d3b3707694df592762f3b8a2ddec0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:00:18Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b76d3b3707694df592762f3b8a2ddec02023-11-20T08:57:53ZengMDPI AGApplied Sciences2076-34172020-08-011015535110.3390/app10155351A New Feature Selection Scheme for Emotion Recognition from TextZafer Erenel0Oluwatayomi Rereloluwa Adegboye1Huseyin Kusetogullari2Department of Computer Engineering, European University of Lefke, Lefke, 99728 Northern Cyprus, TR-10 Mersin, TurkeyDepartment of Computer Engineering, European University of Lefke, Lefke, 99728 Northern Cyprus, TR-10 Mersin, TurkeyDepartment of Computer Science, Blekinge Institute of Technology, 37141 Karlskrona, SwedenThis paper presents a new scheme for term selection in the field of emotion recognition from text. The proposed framework is based on utilizing moderately frequent terms during term selection. More specifically, all terms are evaluated by considering their relevance scores, based on the idea that moderately frequent terms may carry valuable information for discrimination as well. The proposed feature selection scheme performs better than conventional filter-based feature selection measures Chi-Square and Gini-Text in numerous cases. The bag-of-words approach is used to construct the vectors for document representation where each selected term is assigned the weight 1 if it exists or assigned the weight 0 if it does not exist in the document. The proposed scheme includes the terms that are not selected by Chi-Square and Gini-Text. Experiments conducted on a benchmark dataset show that moderately frequent terms boost the representation power of the term subsets as noticeable improvements are observed in terms of Accuracies.https://www.mdpi.com/2076-3417/10/15/5351text categorizationemotion recognitionterm weightingfeature selectionmachine learning |
| spellingShingle | Zafer Erenel Oluwatayomi Rereloluwa Adegboye Huseyin Kusetogullari A New Feature Selection Scheme for Emotion Recognition from Text Applied Sciences text categorization emotion recognition term weighting feature selection machine learning |
| title | A New Feature Selection Scheme for Emotion Recognition from Text |
| title_full | A New Feature Selection Scheme for Emotion Recognition from Text |
| title_fullStr | A New Feature Selection Scheme for Emotion Recognition from Text |
| title_full_unstemmed | A New Feature Selection Scheme for Emotion Recognition from Text |
| title_short | A New Feature Selection Scheme for Emotion Recognition from Text |
| title_sort | new feature selection scheme for emotion recognition from text |
| topic | text categorization emotion recognition term weighting feature selection machine learning |
| url | https://www.mdpi.com/2076-3417/10/15/5351 |
| work_keys_str_mv | AT zafererenel anewfeatureselectionschemeforemotionrecognitionfromtext AT oluwatayomirereloluwaadegboye anewfeatureselectionschemeforemotionrecognitionfromtext AT huseyinkusetogullari anewfeatureselectionschemeforemotionrecognitionfromtext AT zafererenel newfeatureselectionschemeforemotionrecognitionfromtext AT oluwatayomirereloluwaadegboye newfeatureselectionschemeforemotionrecognitionfromtext AT huseyinkusetogullari newfeatureselectionschemeforemotionrecognitionfromtext |