Comparative Analysis of Machine Learning Models for Emotion Classification in Textual Data

Gregorius Airlangga(1*),

(1) Universitas Katolik Indonesia Atma Jaya, Indonesia
(*) Corresponding Author

Abstract


This research presents a comprehensive comparative analysis of various machine learning models for emotion classification within textual data, aiming to identify the most effective architectures for understanding and interpreting emotional undertones. With the increasing prevalence of digital communications, the ability to accurately classify emotions in text has significant implications across numerous domains, including social media analysis, customer service, and mental health monitoring. This study evaluates traditional algorithms, such as Logistic Regression, and advanced deep learning models, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Convolutional Neural Networks combined with Recurrent Neural Networks (CNN-RNN), Autoencoders, and Transformers. Through meticulous cross-validation, hyperparameter tuning, and performance evaluation based on accuracy, precision, recall, and F1 scores, the research elucidates the strengths and weaknesses of each model. LSTM and GRU models demonstrated superior performance, highlighting the importance of sequential data processing capabilities. In contrast, the Autoencoder model underperformed, underscoring the necessity for careful model selection tailored to the task's specifics. Surprisingly, Logistic Regression showed notable efficacy, advocating for its potential utility in scenarios prioritizing computational efficiency. This study enhances the understanding of affective computing within natural language processing, offering insights into the strategic deployment of machine learning models for emotion recognition and paving the way for future advancements in the field.

Full Text:

PDF

References


Y. Kang, Z. Cai, C.-W. Tan, Q. Huang, and H. Liu, “Natural language processing (NLP) in management research: A literature review,” J. Manag. Anal., vol. 7, no. 2, pp. 139–172, 2020.

D. Demner-Fushman, N. Elhadad, and C. Friedman, “Natural language processing for health-related texts,” in Biomedical Informatics: Computer Applications in Health Care and Biomedicine, Springer, 2021, pp. 241–272.

M. Thimmapuram, D. Pal, and G. B. Mohammad, “Sentiment Analysis-Based Extraction of Real-Time Social Media Information From Twitter Using Natural Language Processing,” Soc. Netw. Anal. Theory Appl., pp. 149–173, 2022.

J. Xue et al., “Evaluation of the Current State of Chatbots for Digital Health: Scoping Review,” J. Med. Internet Res., vol. 25, p. e47217, 2023.

F. Khennouche, Y. Elmir, Y. Himeur, N. Djebari, and A. Amira, “Revolutionizing generative pre-traineds: Insights and challenges in deploying ChatGPT and generative chatbots for FAQs,” Expert Syst. Appl., vol. 246, p. 123224, 2024.

M. Khaleel and A. Jebrel, “Artificial Intelligence in Computer Science,” Int. J. Electr. Eng. Sustain., pp. 1–21, 2024.

E. Troiano, “Where are emotions in text? A human-based and computational investigation of emotion recognition and generation,” 2023.

Pratibha, A. Kaur, M. Khurana, and R. Damaševičius, “Multimodal Hinglish

Tweet Dataset for Deep Pragmatic Analysis,” Data, vol. 9, no. 2, p. 38, 2024.

M. Zaragozá Portolés, “Emotion recognition system through voice for the reproduction of emotionally tuned music,” 2023.

S. Lin, J. Zhang, L. Wang, and S. Wang, “Digital Realities: Role Stress, Social Media Burnout, and E-Cigarette Behavior in Post-90 s Urban White-Collar Workers,” J. Knowl. Econ., pp. 1–34, 2024.

G. S. Dhanesh and N. Rahman, “Visual communication and public relations: Visual frame building strategies in war and conflict stories,” Public Relat. Rev., vol. 47, no. 1, p. 102003, 2021.

E. Troiano, L. Oberländer, and R. Klinger, “Dimensional modeling of emotions in text with appraisal theories: Corpus creation, annotation reliability, and prediction,” Comput. Linguist., vol. 49, no. 1, pp. 1–72, 2023.

J. Golia, Newspaper confessions: A history of advice columns in a pre-internet age. Oxford University Press, 2021.

A. Whitworth, Mapping information landscapes: new methods for exploring the development and teaching of information literacy. Facet Publishing, 2020.

I. A. Wong, Y. K. P. Wan, and D. Sun, “Understanding hospitality service aesthetics through the lens of aesthetic theory,” J. Hosp. Mark. & Manag., vol. 32, no. 3, pp. 410–444, 2023.

A. V Geetha, T. Mala, D. Priyanka, and E. Uma, “Multimodal Emotion Recognition with deep learning: advancements, challenges, and future directions,” Inf. Fusion, vol. 105, p. 102218, 2024.

M. A. K. Raiaan et al., “A review on large Language Models: Architectures, applications, taxonomies, open issues and challenges,” IEEE Access, 2024.

N. C. Dang, M. N. Moreno-Garc’ia, and F. la Prieta, “Sentiment analysis based on deep learning: A comparative study,” Electronics, vol. 9, no. 3, p. 483, 2020.

F. A. Acheampong, C. Wenyu, and H. Nunoo-Mensah, “Text-based emotion detection: Advances, challenges, and opportunities,” Eng. Reports, vol. 2, no. 7, p. e12189, 2020.

I. A. Farha and W. Magdy, “A comparative study of effective approaches for Arabic sentiment analysis,” Inf. Process. & Manag., vol. 58, no. 2, p. 102438, 2021.

G. Nkhata, S. Gauch, U. Anjum, and J. Zhan, “Fine-tuning BERT with Bidirectional LSTM for Fine-grained Movie Reviews Sentiment Analysis.”

H. Zhang, Y.-N. Cheah, O. M. Alyasiri, and J. An, “Exploring aspect-based sentiment quadruple extraction with implicit aspects, opinions, and ChatGPT: a comprehensive survey,” Artif. Intell. Rev., vol. 57, no. 2, p. 17, 2024.

Kotholo, “Emotions Logistic Regression 93%.” 2020.




DOI: https://doi.org/10.30645/kesatria.v5i2.383

DOI (PDF): https://doi.org/10.30645/kesatria.v5i2.383.g380

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: