---
title: "Emotion Classification in Short English Texts using Deep"
description: "The author builds a new corpus, SmallEnglishEmotions, from tweets collected with… 77% accuracy. 9 references, cited by 1 paper here."
authors: ["Siddhanth Bhat"]
year: 2024
venue: "arXiv:2402.16034"
source: "https://arxiv.org/abs/2402.16034"
doi: "10.48550/arxiv.2402.16034"
arxiv: "2402.16034"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/bhat-2024-emotion-classification-short-english-texts/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/bhat-2024-emotion-classification-short-english-texts/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/13/) / Emotion Classification in Short English Texts using Deep Learning Techniques

# Emotion Classification in Short English Texts using Deep Learning Techniques

**Authors:** Siddhanth Bhat · **Year:** 2024 · **Venue:** arXiv:2402.16034 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2402.16034) · [PDF](https://arxiv.org/pdf/2402.16034) · [DOI 10.48550/arxiv.2402.16034](https://doi.org/10.48550/arxiv.2402.16034) · [arXiv 2402.16034](https://arxiv.org/abs/2402.16034) · [OpenAlex](https://openalex.org/W4392224048)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper looks at how to recognise emotions in very short English posts, where little context is available to a classifier. The author builds a new corpus, SmallEnglishEmotions, from tweets collected with Snscrape between 2020 and 2023. The queries were keyed to topics such as sports, politics, news and the USA, and only texts of 20–70 words were kept. Five annotators labelled each tweet with one of five classes (happiness, sadness, anger, fear, other), following Rachael Jack's emotion model. They used a small React-based labelling tool that let them skip unclear items. The study compares a reinforcement-based model, SVM, BERT and pretrained DistilBERT, measured by accuracy and macro-F1 on the new corpus and on an unnamed standard Twitter dataset of longer texts. DistilBERT performs best on both, reaching 77% accuracy on the short-text corpus. All models score higher on short texts, which the author attributes to less ambiguous labelling. The contribution is mainly a modest benchmark, and the experimental setup is only thinly described.

## Key points
- SmallEnglishEmotions has 6372 tweets: happiness 1125, sadness 1463, fear 1256, anger 1125, other 1403. Texts are 20–70 words long, about 50 on average.
- Each item has exactly one label from five human annotators. A dedicated "ignore" option kept multi-emotion or unclear tweets out of the data.
- Training setup:
  - Keras and Scikit Learn on Google Colab with a T4 GPU.
  - Adam optimiser, batch size 32.
  - Early stopping with up to 100 epochs and patience 10.
  - Input capped at 100 words.
  - Each model trained and evaluated ten times.
- Results on SmallEnglishEmotions (macro-F1 / accuracy):
  - Reinforcement: 57% / 62%
  - SVM: 58% / 65%
  - BERT: 63% / 67%
  - DistilBERT: 73% / 77%
- On the longer standard dataset, DistilBERT still leads with 71% macro-F1 and 67% accuracy. The weaker models drop sharply there; Reinforcement falls to 33% / 35%.

## Interesting ideas
- **Abstain instead of forcing a label.** Annotators were given an explicit way to skip ambiguous items rather than being forced to pick a label, which keeps label noise out of a single-label corpus.
- **Length filtering as a controlled variable.** The author cut collected texts to a fixed length window so that difficulty could be compared across short and long inputs with the same models.
- **A catch-all "other" class.** Including an explicit "other" category stops the classifier from squeezing neutral or unusual texts into a named emotion.
- **Topic-keyed collection queries.** Gathering raw text through separate keyword queries per topic gives a corpus with deliberate domain spread rather than one dominant source.
- **Repeated runs with two metrics.** Each model was run ten times and scored with both accuracy and macro-F1, which separates real gains from run-to-run noise and class-imbalance effects.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): when witness parsers or LLM teacher tiers disagree on a silver sentence, the item could be marked "abstain" and left out of training rather than resolved by majority vote.
- **I2** (learn): evaluation sets could be split into sentence-length bands, showing whether parser or reader errors grow with length instead of hiding that in one average score.
- **I3** (frames): speech-act and affect frames could carry an explicit "none/other" value, so prag does not invent an emotion or irony reading when the evidence is weak.
- **I4** (tree): unlabelled text for silver treebanks could be gathered per domain bucket, so the parser sees varied registers before UD dialect conversion and training.
- **I5** (learn): repair rules and retrained parsers could be judged over several seeds with macro-averaged per-relation scores, next to the existing negative controls.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 870 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 306 works

🧭 Topics (2): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works · [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works

## Cite

Cite as: Siddhanth Bhat. 2024. Emotion Classification in Short English Texts using Deep Learning Techniques. arXiv:2402.16034.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{bhat2024emotion,
  title = {{Emotion Classification in Short English Texts using Deep Learning Techniques}},
  author = {Siddhanth Bhat},
  year = {2024},
  doi = {10.48550/arxiv.2402.16034},
  eprint = {2402.16034},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2402.16034}
}
```

- [← previous dzNLP at NADI 2024 Shared Task: Multi-Classifier Ensemble with Weighted Voting and TF-IDF Features](https://md.research.elamur.ai/free/en/papers/lichouri-2024-dznlp-nadi-2024-shared-task/)
- [next → Enhancing English Grammar Skills of Grade 9 Students Through the Use of an English Grammar Application](https://md.research.elamur.ai/free/en/papers/magbanua-2024-enhancing-english-grammar-skills-grade/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/13/)

## References

9 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sancheng Peng et al. “A survey on deep learning for textual emotion analysis in social networks”. In: Digital Communications and Networks 8.5 (2022), pp. 745–762. [↗](https://doi.org/10.1016/j.dcan.2021.10.003)
2. Francisca Adoma Acheampong, Chen Wenyu, and Henry Nunoo-Mensah. “Text-based emotion detection: Advances, challenges, and opportunities”. In: Engineering Reports 2.7 (2020), e12189. [↗](https://doi.org/10.1002/eng2.12189)
3. Bernhard Kratzwald et al. “Deep learning for affective computing: Text-based emotion recognition in decision support”. In: Decision support systems 115 (2018), pp. 24–35. [↗](https://doi.org/10.1016/j.dss.2018.09.002)
4. Amir Lakizadeh and Elham Moradizadeh. “Text sentiment classification based on separate embedding of aspect and context”. In: Journal of AI and Data Mining 10.1 (2022), pp. 139–149. [↗](https://doi.org/10.22044/jadm.2021.11022.2249)
5. Vimala Balakrishnan and Wandeep Kaur. “String-based multinomial Naıüve Bayes for emotion detection among Facebook diabetes community”. In: Procedia Computer Science 159 (2019), pp. 30–37. [find](https://scholar.google.com/scholar?q=Vimala+Balakrishnan+and+Wandeep+Kaur%2E+%E2%80%9CString%2Dbased+multinomial+Na%C4%B1u%CC%88ve+Bayes+for+emotion+detection+among+Facebook+diabetes+community%E2%80%9D%2E+In%3A+Procedia+Computer+Science+159+%282019%29%2C+pp%2E+30%E2%80%9337%2E)
6. Sourojit Ghosh, Niamh Froelich, and Cecilia Aragon. ““I Love You, My Dear Friend”: Analyzing the Role of Emotions in the Building of Friendships in Online Fanfiction Communities”. In: International Conference on Human-Computer Interaction. Springer. 2023, pp. 466–485. [find](https://scholar.google.com/scholar?q=Sourojit+Ghosh%2C+Niamh+Froelich%2C+and+Cecilia+Aragon%2E+%E2%80%9C%E2%80%9CI+Love+You%2C+My+Dear+Friend%E2%80%9D%3A+Analyzing+the+Role+of+Emotions+in+the+Building+of+Friendships+in+Online+Fanfiction+Communities%E2%80%9D%2E+In%3A+International+Co)
7. Motahare Nasiri and Hossein Rahmani. “DENOVA: Predicting Five-Factor Model using Deep Learning based on ANOVA”. In: Journal of AI and Data Mining 9.4 (2021), pp. 451–463. [↗](https://doi.org/10.22044/jadm.2021.10471.2186)
8. Akshi Kumar and Victor Hugo C Albuquerque. “Sentiment analysis using XLM-R transformer and zero-shot transfer learning on resource-poor indian language”. In: Transactions on Asian and Low-Resource Language Information Processing 20.5 (2021), pp. 1–13. [↗](https://doi.org/10.1145/3461764)
9. Victor Sanh et al. “DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter”. In: arXiv preprint arXiv:1910.01108 (2019). [↗](https://arxiv.org/abs/1910.01108)

*Updated 1 November 2026*