Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic
Social media is a widely used platform that provides a huge amount of user-generated content that can be processed to extract information about users’ emotions. This has numerous benefits, such as understanding how individuals feel about certain news or events. It can be challenging to ca...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10138896/ |
| _version_ | 1797804075327160320 |
|---|---|
| author | Iqra Ameer Necva Bolucu Grigori Sidorov Burcu Can |
| author_facet | Iqra Ameer Necva Bolucu Grigori Sidorov Burcu Can |
| author_sort | Iqra Ameer |
| collection | DOAJ |
| description | Social media is a widely used platform that provides a huge amount of user-generated content that can be processed to extract information about users’ emotions. This has numerous benefits, such as understanding how individuals feel about certain news or events. It can be challenging to categorize emotions from text created on social media, especially when trying to identify several different emotions from a short text length, as in a multi-label classification problem. Most previous work on emotion classification has focused on deep neural networks such as Convolutional Neural Networks and Recurrent Neural Networks. However, none of these networks have used semantic and syntactic knowledge to classify multiple emotions from a text. In this study, semantic and syntactic aware graph attention networks were proposed to classify emotions from a text with multiple labels. We integrated semantic information in the graph attention network in the form of Universal Conceptual Cognitive Annotation and syntactic information in the form of dependency trees. Our extensive experimental results showed that our two models, UCCA-GAT (accuracy = 71.2) and Dep-GAT (accuracy = 68.7), were able to outperform the state-of-the-art performance on both the challenging SemEval-2018 E-c: Detecting Emotions (multi-label classification) English dataset (accuracy = 58.8) and GoEmotions dataset (accuracy = 65.9). |
| first_indexed | 2024-03-13T05:30:41Z |
| format | Article |
| id | doaj.art-9c8b1304ac354c0e9af4e76d7d100d40 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T05:30:41Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9c8b1304ac354c0e9af4e76d7d100d402023-06-14T23:00:21ZengIEEEIEEE Access2169-35362023-01-0111569215693410.1109/ACCESS.2023.328154410138896Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than SyntacticIqra Ameer0https://orcid.org/0000-0002-1134-9713Necva Bolucu1Grigori Sidorov2https://orcid.org/0000-0003-3901-3522Burcu Can3Computer Science Program, Division of Science and Engineering, Pennsylvania State University at Abington, Abington, PA, USADepartment of Computer Engineering, Hacettepe University, Ankara, TurkeyInstituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City, MexicoDepartment of Computing Science and Mathematics, University of Stirling, Stirling, U.KSocial media is a widely used platform that provides a huge amount of user-generated content that can be processed to extract information about users’ emotions. This has numerous benefits, such as understanding how individuals feel about certain news or events. It can be challenging to categorize emotions from text created on social media, especially when trying to identify several different emotions from a short text length, as in a multi-label classification problem. Most previous work on emotion classification has focused on deep neural networks such as Convolutional Neural Networks and Recurrent Neural Networks. However, none of these networks have used semantic and syntactic knowledge to classify multiple emotions from a text. In this study, semantic and syntactic aware graph attention networks were proposed to classify emotions from a text with multiple labels. We integrated semantic information in the graph attention network in the form of Universal Conceptual Cognitive Annotation and syntactic information in the form of dependency trees. Our extensive experimental results showed that our two models, UCCA-GAT (accuracy = 71.2) and Dep-GAT (accuracy = 68.7), were able to outperform the state-of-the-art performance on both the challenging SemEval-2018 E-c: Detecting Emotions (multi-label classification) English dataset (accuracy = 58.8) and GoEmotions dataset (accuracy = 65.9).https://ieeexplore.ieee.org/document/10138896/Emotion classificationGATUCCAdependencysemanticsyntactic |
| spellingShingle | Iqra Ameer Necva Bolucu Grigori Sidorov Burcu Can Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic IEEE Access Emotion classification GAT UCCA dependency semantic syntactic |
| title | Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic |
| title_full | Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic |
| title_fullStr | Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic |
| title_full_unstemmed | Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic |
| title_short | Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic |
| title_sort | emotion classification in texts over graph neural networks semantic representation is better than syntactic |
| topic | Emotion classification GAT UCCA dependency semantic syntactic |
| url | https://ieeexplore.ieee.org/document/10138896/ |
| work_keys_str_mv | AT iqraameer emotionclassificationintextsovergraphneuralnetworkssemanticrepresentationisbetterthansyntactic AT necvabolucu emotionclassificationintextsovergraphneuralnetworkssemanticrepresentationisbetterthansyntactic AT grigorisidorov emotionclassificationintextsovergraphneuralnetworkssemanticrepresentationisbetterthansyntactic AT burcucan emotionclassificationintextsovergraphneuralnetworkssemanticrepresentationisbetterthansyntactic |