A Hybrid Ensemble Deep Learning Approach for Emotion Classification

Karras, Christos; Karras, Aristeidis; Tsolis, Dimitrios; Avlonitis, Markos; Sioutas, Spyros

doi:10.1109/bigdata55660.2022.10020483

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future studies, diverse data such as audio, images, and others can be added to HDECS to enhance accuracy instead of adding sentences to the script. Moreover, HDECS can be utilized by developing new models that employ different deep learning approaches, such as an embedding module that uses embedding models and attention functions [41], or ensemble techniques that combine multiple models [42]. Additionally, it can replace other multimodal data, such as facial expressions, in addition to multimodal data used in HDECS [43].…”

Section: Discussionmentioning

confidence: 99%

A Hybrid Deep Learning Emotion Classification System Using Multimodal Data

Kim,

Son,

Kwak

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes a hybrid deep learning emotion classification system (HDECS), a hybrid multimodal deep learning system designed for emotion classification in a specific national language. Emotion classification is important in diverse fields, including tailored corporate services, AI advancement, and more. Additionally, most sentiment classification techniques in speaking situations are based on a single modality: voice, conversational text, vital signs, etc. However, analyzing these data presents challenges because of the variations in vocal intonation, text structures, and the impact of external stimuli on physiological signals. Korean poses challenges in natural language processing, including subject omission and spacing issues. To overcome these challenges and enhance emotion classification performance, this paper presents a case study using Korean multimodal data. The case study model involves retraining two pretrained models, LSTM and CNN, until their predictions on the entire dataset reach an agreement rate exceeding 0.75. Predictions are used to generate emotional sentences appended to script data, which are further processed using BERT for final emotion prediction. The research result is evaluated by using categorical cross-entropy (CCE) to measure the difference between the model’s predictions and actual labels, F1 score, and accuracy. According to the evaluation, the case model outperforms the existing KLUE/roBERTa model with improvements of 0.5 in CCE, 0.09 in accuracy, and 0.11 in F1 score. As a result, the HDECS is expected to perform well not only on Korean multimodal datasets but also on sentiment classification considering the speech characteristics of various languages and regions.

show abstract

Section: Discussionmentioning

confidence: 99%

A Hybrid Deep Learning Emotion Classification System Using Multimodal Data

Kim,

Son,

Kwak

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

Transformer-Based Indonesian Language Model for Emotion Classification and Sentiment Analysis

Ahmadian,

Abidin,

Riza

et al. 2023

2023 International Conference on Information Technology and Computing (ICITCOM)

View full text Add to dashboard Cite

Modelling and Analysis of Neuro Fuzzy Employee Ranking System in the Public Sector

et al. 2023

View full text Add to dashboard Cite

Human resource management has a significant influence on the performance of any public body. Employee classification and ranking are definitely time-consuming processes, which in many cases lead to controversial results. In addition, assessing employee efficiency through a variety of skills could lead to never-ending calculations and error-prone statistics. On the other hand, hard skill selection is proven to formulate a base for further investigation since subjectivity is not included in the performance equation. This research proposes a ranking model of employee selection based on certain criteria and attributes. The proposed prototype shows a series of results with a low error rate using ANFIS as the base methodology approach. This research was explanatory, and the population of this study consisted of employees with the majority of the sample in the wider region of Western Greece. The results showed a harmonic co-existence of the factors that proportionally affect the productivity of the employees in public service. Therefore, it provides the HR department with valuable information regarding the overall productivity of the public body, as well as significant material based on each profile separately. Therefore, efficiency was achieved through an automated time-saving procedure. The final output will enhance any personnel selection system with data extracted directly from the system, ensuring that the current method outperformed traditional approaches and secured a non-subjective procedure on employee management applied to the public sector.

show abstract

A Hybrid Ensemble Deep Learning Approach for Emotion Classification

Cited by 4 publications

References 14 publications

A Hybrid Deep Learning Emotion Classification System Using Multimodal Data

A Hybrid Deep Learning Emotion Classification System Using Multimodal Data

Transformer-Based Indonesian Language Model for Emotion Classification and Sentiment Analysis

Modelling and Analysis of Neuro Fuzzy Employee Ranking System in the Public Sector

Contact Info

Product

Resources

About