A Survey of Text-based Emotion Detection: Lexicons, Machine Learning, Deep Models and the Move to Large Language Models

Nidhi Singh

doi:10.55524/ijirem.2026.13.3.2

Abstract

Reading the feeling behind a piece of writing is something humans do without thinking. Teaching a computer to do it has turned out to be much harder. This paper walks through how the problem has been attacked over the last twenty years or so, from the first hand-built word lists in the early 2000s right up to the large language model approaches we see today. We start with the lexicon era, when researchers tagged words with emotions and counted them. Then comes the classical machine learning period. Naive Bayes, Support Vector Machines, Maximum Entropy. These were a real step up but they had limits we will talk about. Deep learning showed up next, first with recurrent networks like LSTMs and then with transformers. BERT and its cousins pushed the accuracy numbers into the eighties. Most recently, models like GPT-4 and Claude have started doing emotion classification with no training data at all, just by being prompted. Alongside the methods we cover the datasets people actually use to measure progress, things like ISEAR, GoEmotions, EmoContext, DailyDialog, and the SemEval task series. We talk about the metrics. And we end with the problems that are still open, including sarcasm, the imbalance between common and rare emotions, code-mixed writing of the kind you see in Indian chat, and the difficulty of evaluating models that change every few months. The aim is to give a student or a working engineer something they can actually use as a starting point, without assuming they have read every paper in the field.

Keywords

Affective Computing, BERT, Claude, Emotion Classification, Emotion Detection, Foundation Models, GoEmotions, Large Language Models, Lexicon Methods

References

Liu, “Sentiment analysis and opinion mining,” Synthesis Lectures on Human Language Technologies, vol. 5, no. 1, pp. 1–167, May 2012. Available from: https://aclanthology.org/anthology-files/anthology-files/pdf/J/J14/J14-2009.pdf
S. Poria, E. Cambria, R. Bajpai, and A. Hussain, “A review of affective computing: From unimodal analysis to multimodal fusion,” Information Fusion, vol. 37, pp. 98–125, Sep. 2017. Available from: https://www.sciencedirect.com/science/article/abs/pii/S1566253517300738
P. Ekman, “An argument for basic emotions,” Cognition and Emotion, vol. 6, no. 3–4, pp. 169–200, May 1992. Available from: https://doi.org/10.1080/02699939208411068
R. Plutchik, “The nature of emotions,” American Scientist, vol. 89, no. 4, pp. 344–350, Jul. 2001. Available from: https://www.jstor.org/stable/27857503
J. A. Russell, “A circumplex model of affect,” Journal of Personality and Social Psychology, vol. 39, no. 6, pp. 1161–1178, Dec. 1980. Available from: https://doi.org/10.1037/h0077714
Demszky, D. Movshovitz-Attias, J. Ko, A. Cowen, G. Nemade, and S. Ravi, “GoEmotions: A dataset of fine-grained emotions,” in Proc. ACL, Online, 2020, pp. 4040–4054. Available from: https://aclanthology.org/2020.acl-main.372/
B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up? Sentiment classification using machine learning techniques,” in Proc. EMNLP, Philadelphia, PA, USA, 2002, pp. 79–86. Available from: https://aclanthology.org/W02-1011.pdf
P. D. Turney, “Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews,” in Proc. ACL, Philadelphia, PA, USA, 2002, pp. 417–424. Available from: https://aclanthology.org/P02-1053.pdf
S. Baccianella, A. Esuli, and F. Sebastiani, “SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining,” in Proc. LREC, Valletta, Malta, 2010, pp. 2200–2204.
S. M. Mohammad and P. D. Turney, “Crowdsourcing a word-emotion association lexicon,” Computational Intelligence, vol. 29, no. 3, pp. 436–465, Aug. 2013. Available from: https://doi.org/10.1111/j.1467-8640.2012.00460.x
J. W. Pennebaker, R. L. Boyd, K. Jordan, and K. Blackburn, “The development and psychometric properties of LIWC2015,” Technical Report, University of Texas at Austin, Austin, TX, USA, 2015.
Strapparava and A. Valitutti, “WordNet-Affect: An affective extension of WordNet,” in Proc. LREC, Lisbon, Portugal, 2004, pp. 1083–1086. Available from: https://tinyurl.com/3j7p7faw
O. Alm, D. Roth, and R. Sproat, “Emotions from text: Machine learning for text-based emotion prediction,” in Proc. HLT/EMNLP, Vancouver, BC, Canada, 2005, pp. 579–586. Available from: https://aclanthology.org/H05-1073.pdf
T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv:1301.3781, Jan. 2013. Available from: https://arxiv.org/abs/1301.3781
J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation,” in Proc. EMNLP, Doha, Qatar, 2014, pp. 1532–1543. Available from: https://aclanthology.org/D14-1162.pdf
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997. Available from: https://ieeexplore.ieee.org/abstract/document/6795963
Chatterjee, K. N. Narahari, M. Joshi, and P. Agrawal, “SemEval-2019 Task 3: EmoContext contextual emotion detection in text,” in Proc. SemEval, Minneapolis, MN, USA, 2019, pp. 39–48. Available from: https://aclanthology.org/S19-2005/
Y. Kim, “Convolutional neural networks for sentence classification,” in Proc. EMNLP, Doha, Qatar, 2014, pp. 1746–1751. Available from: https://aclanthology.org/D14-1181.pdf
A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, Long Beach, CA, USA, 2017, pp. 5998–6008. Available from: https://cir.nii.ac.jp/crid/1370849946232757637
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, Minneapolis, MN, USA, 2019, pp. 4171–4186. Available from: https://aclanthology.org/N19-1423/
Z. Wang, Q. Xie, Y. Feng, Z. Ding, Z. Yang, and R. Xia, “Is ChatGPT a good sentiment analyzer? A preliminary study,” arXiv:2304.04339, Apr. 2023. Available from: https://arxiv.org/abs/2304.04339
W. Zhao, Y. Zhao, X. Lu, S. Wang, Y. Tong, and B. Qin, “Is ChatGPT equipped with emotional dialogue capabilities?” arXiv:2304.09582, Apr. 2023. Available from: https://arxiv.org/abs/2304.09582
Y. Chen, S. Yan, S. Liu, Y. Li, and Y. Xiao, “EmotionQueen: A benchmark for evaluating empathy of large language models,” in Findings of ACL 2024, Bangkok, Thailand, 2024, pp. 2149–2176. Available from: https://aclanthology.org/2024.findings-acl.128/
H. Fei, B. Li, Q. Liu, L. Bing, F. Li, and T.-S. Chua, “Reasoning implicit sentiment with chain-of-thought prompting,” in Proc. ACL (Short Papers), Toronto, ON, Canada, 2023, pp. 1171–1182. Available from: https://aclanthology.org/2023.acl-short.101/
S. Sabour et al., “EmoBench: Evaluating the emotional intelligence of large language models,” arXiv:2402.12071, Feb. 2024. Available from: https://aclanthology.org/2024.acl-long.326.pdf
N. Singh, “Detecting emotions in chat messages with AI: A real-time REST API built on AWS Bedrock,” International Journal of Innovative Research in Engineering and Management (IJIREM), to appear, 2026.
K. R. Scherer and H. G. Wallbott, “Evidence for universality and cultural variation of differential emotion response patterning (ISEAR),” Journal of Personality and Social Psychology, vol. 66, no. 2, pp. 310–328, Feb. 1994. Available from: https://psycnet.apa.org/buy/1994-29654-001
S. M. Mohammad, F. Bravo-Marquez, M. Salameh, and S. Kiritchenko, “SemEval-2018 Task 1: Affect in tweets,” in Proc. SemEval, New Orleans, LA, USA, 2018, pp. 1–17. Available from: https://aclanthology.org/S18-1001/
Y. Li, H. Su, X. Shen, W. Li, Z. Cao, and S. Niu, “DailyDialog: A manually labelled multi-turn dialogue dataset,” in Proc. IJCNLP, Taipei, Taiwan, 2017, pp. 986–995. Available from: https://aclanthology.org/I17-1099/
S. Poria, D. Hazarika, N. Majumder, G. Naik, E. Cambria, and R. Mihalcea, “MELD: A multimodal multi-party dataset for emotion recognition in conversations,” in Proc. ACL, Florence, Italy, 2019, pp. 527–536. Available from: https://aclanthology.org/P19-1050/
S. Buechel and U. Hahn, “EmoBank: Studying the impact of annotation perspective and representation format on dimensional emotion analysis,” in Proc. EACL, Valencia, Spain, 2017, pp. 578–585. Available from: https://aclanthology.org/E17-2092/

Cites this article as

N. Singh "A Survey of Text-based Emotion Detection: Lexicons, Machine Learning, Deep Models and the Move to Large Language Models", International Journal of Innovative Research in Engineering and Management (IJIREM), Vol-13, Issue-3, Page No-7-18, 2026. Available from: https://doi.org/10.55524/ijirem.2026.13.3.2

Corresponding Author

Nidhi Singh

Department of Computer Science & Engineering, Institute of Technology and Management, Lucknow, Uttar Pradesh, India

Download Full Paper

Download PDF

No. of Downloads: 1 | No. of Views: 26

A Multimodal Deep Learning Approach for Depression Detection using Audio and Video Data

T. Srajan Kumar, Kandula Siri Chandana, Gavara Archana, Gundeti Dhanush Reddy, Jonna Madhu Reddy.

April 2026 - Vol 13, Issue 2
Social Media Fake Account Detection and Prevention Using Multi-Layered AI Analysis

Devi Priya Gottumukkala, K. Mounika, S. J. Harivallika, J. Vinay Kumar, K. Surya Siddhu.

April 2026 - Vol 13, Issue 2
Deep Learning-Based Prediction of Lung Disease: A Comprehensive Analysis and Proposed Methodology

Naveen Kumar Navuri, Mundrika Tejasri, Pakirla Veera Pavani, Pasupuleti Gokul Venkat Uday.

April 2026 - Vol 13, Issue 2

-->

A Survey of Text-based Emotion Detection: Lexicons, Machine Learning, Deep Models and the Move to Large Language Models

Citations

Download Full Paper PDF

Total View 26

Total Download 1