Comparative Analysis of Deep Learning Architectures for Emotion Recognition in Text

Gregorius Airlangga(1*),

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

Abstract


This study delves into the intricacies of emotion recognition within textual data, presenting a comprehensive analysis of three prominent deep learning models: Long Short-Term Memory networks (LSTMs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Employing a 5-fold cross-validation methodology, the research meticulously evaluates each model's performance in accurately classifying a spectrum of emotions, using metrics such as accuracy, precision, recall, and F1 score. Results indicate that LSTMs outperform their counterparts with an accuracy of 93.48%, closely followed by CNNs at 91.78%, while RNNs lag, showcasing the importance of sophisticated architectural features in handling complex emotional nuances. The study not only highlights the strengths and limitations of each model but also sheds light on the significant role of temporal and contextual understanding in emotion recognition tasks. Through this investigation, we provide insights into the evolving landscape of natural language processing and its capability to decode human emotions, proposing directions for future research in enhancing model performance. This work has broader implications for applications in mental health, customer service, and social media analysis, aiming to refine the interaction between humans and machines in understanding and processing emotional content

Full Text:

PDF

References


P. Nandwani and R. Verma, “A review on sentiment analysis and emotion detection from text,” Soc. Netw. Anal. Min., vol. 11, no. 1, p. 81, 2021.

A. Ramsay and T. Ahmad, Machine Learning for Emotion Analysis in Python: Build AI-powered tools for analyzing emotion using natural language processing and machine learning. Packt Publishing Ltd, 2023.

S. Kusal, S. Patil, J. Choudrie, K. Kotecha, D. Vora, and I. Pappas, “A systematic review of applications of natural language processing and future challenges with special emphasis in text-based emotion detection,” Artif. Intell. Rev., vol. 56, no. 12, pp. 15129–15215, 2023.

W. Chung and D. Zeng, “Dissecting emotion and user influence in social media communities: An interaction modeling approach,” Inf. & Manag., vol. 57, no. 1, p. 103108, 2020.

K. Chakraborty, S. Bhattacharyya, and R. Bag, “A survey of sentiment analysis from social media data,” IEEE Trans. Comput. Soc. Syst., vol. 7, no. 2, pp. 450–464, 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.

D. Kalla and N. Smith, “Study and analysis of chat GPT and its impact on different fields of study,” Int. J. Innov. Sci. Res. Technol., vol. 8, no. 3, 2023.

A. Yadav and D. K. Vishwakarma, “Sentiment analysis using deep learning architectures: a review,” Artif. Intell. Rev., vol. 53, no. 6, pp. 4335–4385, 2020.

C. Dalvi, M. Rathod, S. Patil, S. Gite, and K. Kotecha, “A survey of ai-based facial emotion recognition: Features, ml & dl techniques, age-wise datasets and future directions,” Ieee Access, vol. 9, pp. 165806–165840, 2021.

H. I. Abdalla and A. A. Amer, “On the integration of similarity measures with machine learning models to enhance text classification performance,” Inf. Sci. (Ny)., vol. 614, pp. 263–288, 2022.

C. Shorten, T. M. Khoshgoftaar, and B. Furht, “Deep Learning applications for COVID-19,” J. big Data, vol. 8, no. 1, pp. 1–54, 2021.

G. Chandrasekaran, S. Dhanasekaran, C. Moorthy, and A. Arul Oli, “Multimodal sentiment analysis leveraging the strength of deep neural networks enhanced by the XGBoost classifier,” Comput. Methods Biomech. Biomed. Engin., pp. 1–23, 2024.

G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artif. Intell. Rev., vol. 53, no. 8, pp. 5929–5955, 2020.

M. Rai and J. K. Pandey, Using Machine Learning to Detect Emotions and Predict Human Psychology. IGI Global, 2024.

A. Onan and K. F. Balbal, “Improving Turkish text sentiment classification through task-specific and universal transformations: an ensemble data augmentation approach,” IEEE Access, 2024.

F. Carvalho, F. P. Junior, E. Ogasawara, L. Ferrari, and G. Guedes, “Evaluation of the Brazilian Portuguese version of linguistic inquiry and word count 2015 (BP-LIWC2015),” Lang. Resour. Eval., vol. 58, no. 1, pp. 203–222, 2024.

F. Mehraliyev, I. C. C. Chan, and A. P. Kirilenko, “Sentiment analysis in hospitality and tourism: a thematic and methodological review,” Int. J. Contemp. Hosp. Manag., vol. 34, no. 1, pp. 46–77, 2022.

S. Alshattnawi, A. Shatnawi, A. M. R. AlSobeh, and A. A. Magableh, “Beyond Word-Based Model Embeddings: Contextualized Representations for Enhanced Social Media Spam Detection,” Appl. Sci., vol. 14, no. 6, p. 2254, 2024.

L. Williams, E. Anthi, and P. Burnap, “Comparing hierarchical approaches to enhance supervised emotive text classification,” Big Data Cogn. Comput., vol. 8, no. 4, p. 38, 2024.

S. Lee, D. K. Han, and H. Ko, “Fusion-ConvBERT: parallel convolution and BERT fusion for speech emotion recognition,” Sensors, vol. 20, no. 22, p. 6688, 2020.

J. Kocoń et al., “ChatGPT: Jack of all trades, master of none,” Inf. Fusion, vol. 99, p. 101861, 2023.

Y. Zhu et al., “Large language models for information retrieval: A survey,” arXiv Prepr. arXiv2308.07107, 2023.

P. H. Andersen et al., “Towards machine recognition of facial expressions of pain in horses,” Animals, vol. 11, no. 6, p. 1643, 2021.

S. Bursic and others, “On Wiring Emotion to Words: A Bayesian Model,” 2022.

C. Thaokar, J. K. Rout, M. Rout, and N. K. Ray, “N-Gram Based Sarcasm Detection for News and Social Media Text Using Hybrid Deep Learning Models,” SN Comput. Sci., vol. 5, no. 1, p. 163, 2024.

S. L. Heggernes, “A critical review of the role of texts in fostering Intercultural Communicative competence in the English Language classroom,” Educ. Res. Rev., vol. 33, p. 100390, 2021.

Q. C. Song, C. Tang, and S. Wee, “Making sense of model generalizability: A tutorial on cross-validation in R and Shiny,” Adv. Methods Pract. Psychol. Sci., vol. 4, no. 1, p. 2515245920947067, 2021.

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




DOI: https://doi.org/10.30645/kesatria.v5i2.384

DOI (PDF): https://doi.org/10.30645/kesatria.v5i2.384.g381

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: