Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions

Emotions are closely tied to human behavior and play a critical role in daily life. With the widespread use of social media, individuals frequently express their feelings online, making emotion extraction from social networks an active area of research. This has applications in domains such as patie...

Full description

Saved in:
Bibliographic Details
Main Authors: Aqsa Younas, Shazia Riaz, Saqib Ali, Rafiullah Khan, Mohib Ullah, Daehan Kwak
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11048884/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320013188562944
author Aqsa Younas
Shazia Riaz
Saqib Ali
Rafiullah Khan
Mohib Ullah
Daehan Kwak
author_facet Aqsa Younas
Shazia Riaz
Saqib Ali
Rafiullah Khan
Mohib Ullah
Daehan Kwak
author_sort Aqsa Younas
collection DOAJ
description Emotions are closely tied to human behavior and play a critical role in daily life. With the widespread use of social media, individuals frequently express their feelings online, making emotion extraction from social networks an active area of research. This has applications in domains such as patient emotion monitoring, emotional text-to-speech synthesis, and empathetic chatbots. While numerous studies have focused on single-emotion detection, limited work has addressed the simultaneous identification of multiple coexisting emotions. These emotions are often influenced by contextual factors, including past emotional states and social interactions. Leveraging such dependencies can significantly enhance emotion detection performance. This study proposes a fast, accurate, and robust method for predicting future emotions based on current emotional states, while also identifying interrelated emotions present within social media posts. We annotate a public dataset with multilabel emotion tags and model contextual dependencies, both temporal and social, using a novel Stacked Long Short-Term Memory (LSTM) architecture. The model incorporates encoder-decoder layers to capture short- and long-term dependencies among emotions and employs a time-distributed dense layer to differentiate features associated with each emotion. Our experiments show significant improvements in capturing contextual correlations among multiple emotions. The proposed model achieved a micro F1-score of 0.50 on the GoEmotions dataset and demonstrated comparable performance to transformer-based models on the DepressionEmo dataset, while requiring fewer computational resources. These findings underscore the effectiveness and efficiency of our approach in modeling complex emotional dynamics across social networks.
format Article
id doaj-art-3a460822451048baafd1b80cb8919087
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3a460822451048baafd1b80cb89190872025-08-20T03:50:16ZengIEEEIEEE Access2169-35362025-01-011311755811757010.1109/ACCESS.2025.358276411048884Stacked LSTM Model for Contextual Correlation Detection Among Multiple EmotionsAqsa Younas0https://orcid.org/0000-0003-3834-2762Shazia Riaz1https://orcid.org/0000-0001-9016-0478Saqib Ali2https://orcid.org/0000-0001-5170-7346Rafiullah Khan3https://orcid.org/0000-0002-0229-7747Mohib Ullah4https://orcid.org/0000-0003-0534-8826Daehan Kwak5https://orcid.org/0000-0001-5614-0190Department of Computer Science, National University of Computer and Emerging Sciences, Chiniot-Faisalabad Campus, Chiniot, Islamabad, PakistanDepartment of Computer Science, Government College Women University Faisalabad, Faisalabad, PakistanDepartment of Computer Science, University of Agriculture, Faisalabad, PakistanSchool of Computing, Macquarie University, Sydney, NSW, AustraliaSchool of Computing, Macquarie University, Sydney, NSW, AustraliaDepartment of Computer Science and Technology, Kean University, Union, NJ, USAEmotions are closely tied to human behavior and play a critical role in daily life. With the widespread use of social media, individuals frequently express their feelings online, making emotion extraction from social networks an active area of research. This has applications in domains such as patient emotion monitoring, emotional text-to-speech synthesis, and empathetic chatbots. While numerous studies have focused on single-emotion detection, limited work has addressed the simultaneous identification of multiple coexisting emotions. These emotions are often influenced by contextual factors, including past emotional states and social interactions. Leveraging such dependencies can significantly enhance emotion detection performance. This study proposes a fast, accurate, and robust method for predicting future emotions based on current emotional states, while also identifying interrelated emotions present within social media posts. We annotate a public dataset with multilabel emotion tags and model contextual dependencies, both temporal and social, using a novel Stacked Long Short-Term Memory (LSTM) architecture. The model incorporates encoder-decoder layers to capture short- and long-term dependencies among emotions and employs a time-distributed dense layer to differentiate features associated with each emotion. Our experiments show significant improvements in capturing contextual correlations among multiple emotions. The proposed model achieved a micro F1-score of 0.50 on the GoEmotions dataset and demonstrated comparable performance to transformer-based models on the DepressionEmo dataset, while requiring fewer computational resources. These findings underscore the effectiveness and efficiency of our approach in modeling complex emotional dynamics across social networks.https://ieeexplore.ieee.org/document/11048884/Deep learningmultilabel emotion detectionsocial correlationsocial media platformstemporal correlationuser interaction
spellingShingle Aqsa Younas
Shazia Riaz
Saqib Ali
Rafiullah Khan
Mohib Ullah
Daehan Kwak
Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions
IEEE Access
Deep learning
multilabel emotion detection
social correlation
social media platforms
temporal correlation
user interaction
title Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions
title_full Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions
title_fullStr Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions
title_full_unstemmed Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions
title_short Stacked LSTM Model for Contextual Correlation Detection Among Multiple Emotions
title_sort stacked lstm model for contextual correlation detection among multiple emotions
topic Deep learning
multilabel emotion detection
social correlation
social media platforms
temporal correlation
user interaction
url https://ieeexplore.ieee.org/document/11048884/
work_keys_str_mv AT aqsayounas stackedlstmmodelforcontextualcorrelationdetectionamongmultipleemotions
AT shaziariaz stackedlstmmodelforcontextualcorrelationdetectionamongmultipleemotions
AT saqibali stackedlstmmodelforcontextualcorrelationdetectionamongmultipleemotions
AT rafiullahkhan stackedlstmmodelforcontextualcorrelationdetectionamongmultipleemotions
AT mohibullah stackedlstmmodelforcontextualcorrelationdetectionamongmultipleemotions
AT daehankwak stackedlstmmodelforcontextualcorrelationdetectionamongmultipleemotions