A Hybrid Neural Network Architecture for Semantic-Contextual Analysis of Emotions in Social Media

dc.contributor.authorKashtan, Vita Yu.en
dc.contributor.authorHnatushenko, Volodymyr V.en
dc.contributor.authorOvcharenko, Maksymen
dc.contributor.authorIvanko, Artemen
dc.date.accessioned2025-10-23T08:53:57Z
dc.date.issued2025
dc.descriptionV. Kashtan: ORCID 0000-0002-0395-5895; Vol. Hnatushenko: ORCID 0000-0003-3140-3788; M. Ovcharenko: ORCID 0009-0006-0730-0913; A. Ivanko: ORCID 0009-0002-0491-5374en
dc.description.abstractENG: The paper proposes a hybrid neural network architecture for multi-class classification of the emotional state of social media texts, which combines contextual vector representations generated by the BERT model with extended structured features related to the user and message metadata. The proposed approach uses a multilayer perceptron network that combines linguistic and contextual information in a single representation. The results of the experimental study confirm the superiority of the proposed approach over traditional LSTM and CNN architectures, as well as over the separate use of BERT embeddings. The achieved classification accuracy is 90%, and the F1-measure is 0.91, which indicates the high efficiency of the model in conditions of high variability of language structures and stylistic features of social content.en
dc.description.sponsorshipDnipro University of Technology, Dniproen
dc.identifier.citationKashtan V., Hnatushenko Vol., Ovcharenko M., Ivanko A. A Hybrid Neural Network Architecture for Semantic-Contextual Analysis of Emotions in Social Media. CEUR Workshop Proceedings. Vol. 4005 : Proc. of the Modern Data Science Technologies Doctoral Consortium (MoDaST 2025), Lviv, Ukraine, June 15-16, 2025. Lviv, 2025. P. 15–28.en
dc.identifier.issn1613-0073
dc.identifier.urihttps://ceur-ws.org/Vol-4005/en
dc.identifier.urihttps://crust.ust.edu.ua/handle/123456789/21140en
dc.language.isoen
dc.publisherCEUR-WS Team, Aachen, Germanyen
dc.rightsCreative Commons License Attribution 4.0 International (CC BY 4.0)en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectemotion stateen
dc.subjectcontextual analysisen
dc.subjectsemantic analysisen
dc.subjectdeep learningen
dc.subjectneural network architectureen
dc.subjectКІТСuk_UA
dc.subject.classificationTECHNOLOGYen
dc.subject.classificationTECHNOLOGY::Information technologyen
dc.titleA Hybrid Neural Network Architecture for Semantic-Contextual Analysis of Emotions in Social Mediaen
dc.typeArticleen

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Kashtan_Hnatushenko_Ovcharenko.pdf
Size:
3.38 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: