Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis
This study investigates the relationship between the phonemic content of texts in English and the emotional valence they inspire. The sublexical content is presented in terms of biphones composed by one vowel and one consonant. The statistical analysis of a vast corpus of emotionally evaluated sente...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2020-06-01
|
| Series: | Cybernetics and Information Technologies |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/cait-2020-0012 |
| _version_ | 1811272242573606912 |
|---|---|
| author | Slavova Velina |
| author_facet | Slavova Velina |
| author_sort | Slavova Velina |
| collection | DOAJ |
| description | This study investigates the relationship between the phonemic content of texts in English and the emotional valence they inspire. The sublexical content is presented in terms of biphones composed by one vowel and one consonant. The statistical analysis of a vast corpus of emotionally evaluated sentences reveals a strong correlation between this sublexical presentation and the evaluations of valence provided by the readers. An initial test performed with other valence-rated prose texts makes believing that the feature observed within the corpus can be useful for the emotion classification of texts. |
| first_indexed | 2024-04-12T22:36:47Z |
| format | Article |
| id | doaj.art-0c0b9e874ada41adbfe59c636a1d99d6 |
| institution | Directory Open Access Journal |
| issn | 1314-4081 |
| language | English |
| last_indexed | 2024-04-12T22:36:47Z |
| publishDate | 2020-06-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Cybernetics and Information Technologies |
| spelling | doaj.art-0c0b9e874ada41adbfe59c636a1d99d62022-12-22T03:13:50ZengSciendoCybernetics and Information Technologies1314-40812020-06-0120232110.2478/cait-2020-0012Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus AnalysisSlavova Velina0New Bulgarian University, Department of Informatics, 21 Montevideo Str., Sofia, BulgariaThis study investigates the relationship between the phonemic content of texts in English and the emotional valence they inspire. The sublexical content is presented in terms of biphones composed by one vowel and one consonant. The statistical analysis of a vast corpus of emotionally evaluated sentences reveals a strong correlation between this sublexical presentation and the evaluations of valence provided by the readers. An initial test performed with other valence-rated prose texts makes believing that the feature observed within the corpus can be useful for the emotion classification of texts.https://doi.org/10.2478/cait-2020-0012natural language processingsound-symbolismcorpus linguisticstext emotion recognition |
| spellingShingle | Slavova Velina Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis Cybernetics and Information Technologies natural language processing sound-symbolism corpus linguistics text emotion recognition |
| title | Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis |
| title_full | Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis |
| title_fullStr | Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis |
| title_full_unstemmed | Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis |
| title_short | Emotional Valence Coded in the Phonemic Content – Statistical Evidence Based on Corpus Analysis |
| title_sort | emotional valence coded in the phonemic content statistical evidence based on corpus analysis |
| topic | natural language processing sound-symbolism corpus linguistics text emotion recognition |
| url | https://doi.org/10.2478/cait-2020-0012 |
| work_keys_str_mv | AT slavovavelina emotionalvalencecodedinthephonemiccontentstatisticalevidencebasedoncorpusanalysis |