Schematic diagram of the EQN structure.
<div><p>Textemotion detection constitutes a crucial foundation for advancing artificial intelligence from basic comprehension to the exploration of emotional reasoning. Most existing emotion detection datasets rely on manual annotations, which are associated with high costs, substantial...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852014872533925888 |
|---|---|
| author | Jingyi Zhou (3681790) |
| author2 | Senlin Luo (610842) Haofan Chen (18084565) |
| author2_role | author author |
| author_facet | Jingyi Zhou (3681790) Senlin Luo (610842) Haofan Chen (18084565) |
| author_role | author |
| dc.creator.none.fl_str_mv | Jingyi Zhou (3681790) Senlin Luo (610842) Haofan Chen (18084565) |
| dc.date.none.fl_str_mv | 2025-11-13T18:56:19Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0333930.g001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Schematic_diagram_of_the_EQN_structure_/30614579 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Medicine Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified thereby fully leveraging severe label imbalances providing strong support map label values expansion quantization network downstream task completion advancing artificial intelligence emotional intensity representation emotion quantization network rich emotions embedded interdependencies among labels energy intensity levels conducted comparative experiments emotion detection analysis achieve automatic micro eqn framework possesses emotion detection automatic detection emotional reasoning emotion annotation various models substantial subjectivity quantitative research particularly evident manual annotations machine models literature demonstrates level scores learning capabilities high costs high capability goemotions dataset eqn framework crucial foundation comprehensive comparison broad applicability basic comprehension adversely affect |
| dc.title.none.fl_str_mv | Schematic diagram of the EQN structure. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Textemotion detection constitutes a crucial foundation for advancing artificial intelligence from basic comprehension to the exploration of emotional reasoning. Most existing emotion detection datasets rely on manual annotations, which are associated with high costs, substantial subjectivity, and severe label imbalances. This is particularly evident in the inadequate annotation of micro-emotions and the absence of emotional intensity representation, which fail to capture the rich emotions embedded in sentences and adversely affect the quality of downstream task completion. By proposing an all-labels and training-set label regression method, we map label values to energy intensity levels, thereby fully leveraging the learning capabilities of machine models and the interdependencies among labels to uncover multiple emotions within samples. This led to the establishment of the Emotion Quantization Network (EQN) framework for micro-emotion detection and annotation. Using five commonly employed sentiment datasets, we conducted comparative experiments with various models, validating the broad applicability of our framework within NLP machine learning models. Based on the EQN framework, emotion detection and annotation are conducted on the GoEmotions dataset. A comprehensive comparison with the results from its literature demonstrates that the EQN framework possesses a high capability for automatic detection and annotation of micro-emotions. The EQN framework is the first to achieve automatic micro-emotion annotation with energy-level scores, providing strong support for further emotion detection analysis and the quantitative research of emotion computing.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_2d41e8aefca3cede2c6819971a382a8e |
| identifier_str_mv | 10.1371/journal.pone.0333930.g001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30614579 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Schematic diagram of the EQN structure.Jingyi Zhou (3681790)Senlin Luo (610842)Haofan Chen (18084565)MedicineSociologyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedthereby fully leveragingsevere label imbalancesproviding strong supportmap label valuesexpansion quantization networkdownstream task completionadvancing artificial intelligenceemotional intensity representationemotion quantization networkrich emotions embeddedinterdependencies among labelsenergy intensity levelsconducted comparative experimentsemotion detection analysisachieve automatic microeqn framework possessesemotion detectionautomatic detectionemotional reasoningemotion annotationvarious modelssubstantial subjectivityquantitative researchparticularly evidentmanual annotationsmachine modelsliterature demonstrateslevel scoreslearning capabilitieshigh costshigh capabilitygoemotions dataseteqn frameworkcrucial foundationcomprehensive comparisonbroad applicabilitybasic comprehensionadversely affect<div><p>Textemotion detection constitutes a crucial foundation for advancing artificial intelligence from basic comprehension to the exploration of emotional reasoning. Most existing emotion detection datasets rely on manual annotations, which are associated with high costs, substantial subjectivity, and severe label imbalances. This is particularly evident in the inadequate annotation of micro-emotions and the absence of emotional intensity representation, which fail to capture the rich emotions embedded in sentences and adversely affect the quality of downstream task completion. By proposing an all-labels and training-set label regression method, we map label values to energy intensity levels, thereby fully leveraging the learning capabilities of machine models and the interdependencies among labels to uncover multiple emotions within samples. This led to the establishment of the Emotion Quantization Network (EQN) framework for micro-emotion detection and annotation. Using five commonly employed sentiment datasets, we conducted comparative experiments with various models, validating the broad applicability of our framework within NLP machine learning models. Based on the EQN framework, emotion detection and annotation are conducted on the GoEmotions dataset. A comprehensive comparison with the results from its literature demonstrates that the EQN framework possesses a high capability for automatic detection and annotation of micro-emotions. The EQN framework is the first to achieve automatic micro-emotion annotation with energy-level scores, providing strong support for further emotion detection analysis and the quantitative research of emotion computing.</p></div>2025-11-13T18:56:19ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0333930.g001https://figshare.com/articles/figure/Schematic_diagram_of_the_EQN_structure_/30614579CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306145792025-11-13T18:56:19Z |
| spellingShingle | Schematic diagram of the EQN structure. Jingyi Zhou (3681790) Medicine Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified thereby fully leveraging severe label imbalances providing strong support map label values expansion quantization network downstream task completion advancing artificial intelligence emotional intensity representation emotion quantization network rich emotions embedded interdependencies among labels energy intensity levels conducted comparative experiments emotion detection analysis achieve automatic micro eqn framework possesses emotion detection automatic detection emotional reasoning emotion annotation various models substantial subjectivity quantitative research particularly evident manual annotations machine models literature demonstrates level scores learning capabilities high costs high capability goemotions dataset eqn framework crucial foundation comprehensive comparison broad applicability basic comprehension adversely affect |
| status_str | publishedVersion |
| title | Schematic diagram of the EQN structure. |
| title_full | Schematic diagram of the EQN structure. |
| title_fullStr | Schematic diagram of the EQN structure. |
| title_full_unstemmed | Schematic diagram of the EQN structure. |
| title_short | Schematic diagram of the EQN structure. |
| title_sort | Schematic diagram of the EQN structure. |
| topic | Medicine Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified thereby fully leveraging severe label imbalances providing strong support map label values expansion quantization network downstream task completion advancing artificial intelligence emotional intensity representation emotion quantization network rich emotions embedded interdependencies among labels energy intensity levels conducted comparative experiments emotion detection analysis achieve automatic micro eqn framework possesses emotion detection automatic detection emotional reasoning emotion annotation various models substantial subjectivity quantitative research particularly evident manual annotations machine models literature demonstrates level scores learning capabilities high costs high capability goemotions dataset eqn framework crucial foundation comprehensive comparison broad applicability basic comprehension adversely affect |