Domain-Generalized Emotion Recognition on German Text Corpora
Text-based emotion recognition plays a crucial role in various domains and applications due to its significance in understanding human behavior and improving communication systems. Although extensive research has been conducted for texts in English, only few studies deal with non-English languages....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10960622/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849699883319033856 |
|---|---|
| author | Oweys Momenzada Michael Palk Stefan Voss |
| author_facet | Oweys Momenzada Michael Palk Stefan Voss |
| author_sort | Oweys Momenzada |
| collection | DOAJ |
| description | Text-based emotion recognition plays a crucial role in various domains and applications due to its significance in understanding human behavior and improving communication systems. Although extensive research has been conducted for texts in English, only few studies deal with non-English languages. Especially for the German language, previous work is limited due to the focus on specific text domains and the usage of lexicon-based approaches, which lack the ability to consider contextual information. In this paper, an approach for emotion recognition on German text corpora is presented, which addresses these challenges with domain-generalized and context-sensitive methodologies. To achieve domain generalization, neural machine translation and weak supervision techniques are combined with multi-view learning, in which various data sources from different domains are utilized to improve the generalizability and to overcome the problem of lack of data. Using the BERT model as the primary architecture to capture contextual information, an overall F1-score of 65.5% and an accuracy of 68.1% are achieved while maintaining well-balanced results on the metrics over all considered domains and emotions. To ensure the legitimacy and reliability of the findings, further comprehensive evaluations and comparisons are conducted. Given the absence of an established benchmark specifically for emotion recognition on German text corpora, the used datasets, evaluations, and results can serve for benchmarking purposes. |
| format | Article |
| id | doaj-art-e105b906a9a44994bfc9ee8ff99c6d51 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-e105b906a9a44994bfc9ee8ff99c6d512025-08-20T03:18:27ZengIEEEIEEE Access2169-35362025-01-0113648676488910.1109/ACCESS.2025.355913510960622Domain-Generalized Emotion Recognition on German Text CorporaOweys Momenzada0Michael Palk1https://orcid.org/0000-0001-7463-6827Stefan Voss2https://orcid.org/0000-0003-1296-4221Institute of Information Systems, University of Hamburg, Hamburg, GermanyInstitute of Information Systems, University of Hamburg, Hamburg, GermanyInstitute of Information Systems, University of Hamburg, Hamburg, GermanyText-based emotion recognition plays a crucial role in various domains and applications due to its significance in understanding human behavior and improving communication systems. Although extensive research has been conducted for texts in English, only few studies deal with non-English languages. Especially for the German language, previous work is limited due to the focus on specific text domains and the usage of lexicon-based approaches, which lack the ability to consider contextual information. In this paper, an approach for emotion recognition on German text corpora is presented, which addresses these challenges with domain-generalized and context-sensitive methodologies. To achieve domain generalization, neural machine translation and weak supervision techniques are combined with multi-view learning, in which various data sources from different domains are utilized to improve the generalizability and to overcome the problem of lack of data. Using the BERT model as the primary architecture to capture contextual information, an overall F1-score of 65.5% and an accuracy of 68.1% are achieved while maintaining well-balanced results on the metrics over all considered domains and emotions. To ensure the legitimacy and reliability of the findings, further comprehensive evaluations and comparisons are conducted. Given the absence of an established benchmark specifically for emotion recognition on German text corpora, the used datasets, evaluations, and results can serve for benchmarking purposes.https://ieeexplore.ieee.org/document/10960622/Emotion recognitiondeep learningbidirectional encoder representations from transformersweak supervisionneural machine translationmulti-view learning |
| spellingShingle | Oweys Momenzada Michael Palk Stefan Voss Domain-Generalized Emotion Recognition on German Text Corpora IEEE Access Emotion recognition deep learning bidirectional encoder representations from transformers weak supervision neural machine translation multi-view learning |
| title | Domain-Generalized Emotion Recognition on German Text Corpora |
| title_full | Domain-Generalized Emotion Recognition on German Text Corpora |
| title_fullStr | Domain-Generalized Emotion Recognition on German Text Corpora |
| title_full_unstemmed | Domain-Generalized Emotion Recognition on German Text Corpora |
| title_short | Domain-Generalized Emotion Recognition on German Text Corpora |
| title_sort | domain generalized emotion recognition on german text corpora |
| topic | Emotion recognition deep learning bidirectional encoder representations from transformers weak supervision neural machine translation multi-view learning |
| url | https://ieeexplore.ieee.org/document/10960622/ |
| work_keys_str_mv | AT oweysmomenzada domaingeneralizedemotionrecognitionongermantextcorpora AT michaelpalk domaingeneralizedemotionrecognitionongermantextcorpora AT stefanvoss domaingeneralizedemotionrecognitionongermantextcorpora |