---
title: "Improving Arabic Multi-Label Emotion — Aslam 2024"
description: "The paper addresses multi-label emotion classification for Arabic tweets."
authors: ["Muhammad Azeem Aslam", "Wang Jun", "Nisar Ahmed", "Muhammad Imran Zaman", "Li Yanan", "Hu Hongfei", "Wang Shiyu", "Xin Liu"]
year: 2024
venue: "arXiv:2410.03979"
source: "https://arxiv.org/abs/2410.03979"
doi: "10.48550/arxiv.2410.03979"
arxiv: "2410.03979"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/aslam-2024-improving-arabic-multi-label-emotion/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/aslam-2024-improving-arabic-multi-label-emotion/)

[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/4/) / Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function

# Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function

**Authors:** Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed, Muhammad Imran Zaman, Li Yanan, Hu Hongfei, Wang Shiyu, [Xin Liu](https://md.research.elamur.ai/free/en/authors/xin-liu/) · **Year:** 2024 · **Venue:** arXiv:2410.03979 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2410.03979) · [PDF](https://arxiv.org/pdf/2410.03979) · [DOI 10.48550/arxiv.2410.03979](https://doi.org/10.48550/arxiv.2410.03979) · [arXiv 2410.03979](https://arxiv.org/abs/2410.03979) · [OpenAlex](https://openalex.org/W4403929274)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · 2 in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper addresses multi-label emotion classification for Arabic tweets. Arabic is relatively low-resource, its emotion datasets are small, a few emotions dominate the label distribution, and labels tend to co-occur. The authors fine-tune three Arabic encoders, ArabicBERT, MarBERT and AraBERT, and concatenate their contextual embeddings into one richer representation. A second-stage meta-learner reads these stacked vectors: a Bi-LSTM models the sequence, and a fully connected head outputs one probability per emotion. Training uses a hybrid objective with three parts: per-class weights to boost rare emotions, a label correlation matrix to capture which emotions appear together, and a contrastive term to pull similar examples together and push dissimilar ones apart. The system reaches Jaccard accuracy of 0.81, F1 of 0.67 and Hamming loss of 0.15. Per-class analysis shows a smaller performance gap between frequent and rare emotions, and ablations credit each component. The work matters because it offers a reusable recipe for imbalanced, correlated multi-label problems in languages with little data.

## Key points
- The backbones are ArabicBERT, MarBERT and AraBERT. Each is fine-tuned, and their embeddings are stacked as input to a Bi-LSTM plus fully connected meta-learner.
- The hybrid loss combines class weighting, a label correlation matrix and contrastive learning. It is positioned against BCE, Focal Loss and MCFL.
- Reported scores are Jaccard accuracy 0.81, F1 0.67 and Hamming loss 0.15. The authors claim these beat earlier Arabic MLEC systems, which are often benchmarked on SemEval-2018 Task 1 E-c Arabic.
- Anger, Joy and Sadness are the majority classes. Anticipation, Surprise, Trust and Neutral are the minority classes, and these improved noticeably under the hybrid loss.
- Code and data are released at github.com/nisarahmedrana/ArabicMLEC.

## Interesting ideas
- Stacking outputs from several independently fine-tuned encoders and training a small second-stage learner on top lets the combiner learn when each source is reliable, rather than averaging blindly. — For Mova (learn): Instead of simple voting among witness parsers, a lightweight meta-learner could be trained on their agreement patterns to decide which silver arcs to trust.
- Adding a label co-occurrence matrix to the loss rewards predictions whose label sets look like real combinations, which helps whenever outputs are structured sets rather than independent choices. — For Mova (frames): Speech-act, irony and implicature tags in crate prag often co-occur, and a correlation prior learned from annotated data could flag implausible tag combinations as explainable warnings.
- Weighting classes by rarity during training keeps rare categories from being ignored, a cheap fix for any skewed label distribution. — For Mova (tree): Rare dependency relations in UD treebanks, such as vocative, dislocated or reparandum, could get higher weight when training the perceptron parser or gparse.
- Reporting results separately for majority and minority classes exposes whether a gain is real or just driven by frequent labels. — For Mova (learn): Evaluations could list per-deprel and per-frame scores next to overall LAS, so a model that improves the average while degrading rare relations is caught.
- A contrastive term that separates dissimilar examples sharpens the boundaries between categories that are easily confused. — For Mova (frames): A similar objective could help separate near-neighbour VerbNet classes when assigning semantic roles, with the confusable class pairs logged for explanation.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/)

## Cite

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

```bibtex
@misc{aslam2024improving,
  title = {{Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function}},
  author = {Aslam, Muhammad Azeem and Jun, Wang and Ahmed, Nisar and Zaman, Muhammad Imran and Yanan, Li and Hongfei, Hu and Shiyu, Wang and Liu, Xin},
  year = {2024},
  doi = {10.48550/arxiv.2410.03979},
  eprint = {2410.03979},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2410.03979}
}
```

- [← previous HATFormer: Historic Handwritten Arabic Text Recognition with Transformers](https://md.research.elamur.ai/free/en/papers/chan-2024-hatformer-historic-handwritten-arabic-text/)
- [next → Munazarat 1.0: A Corpus of Arabic Competitive Debates](https://md.research.elamur.ai/free/en/papers/khader-2024-munazarat-1-0-corpus-arabic/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/4/)

## References

72 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alqahtani, G., Alothaim, A.: Emotion analysis of arabic tweets: Language models and available resources. Frontiers in Artificial Intelligence 5, 843038 (2022) [find](https://scholar.google.com/scholar?q=Alqahtani%2C+G%2E%2C+Alothaim%2C+A%2E%3A+Emotion+analysis+of+arabic+tweets%3A+Language+models+and+available+resources%2E+Frontiers+in+Artificial+Intelligence+5%2C+843038+%282022%29)
2. Wikarsa, L., Thahir, S.N.: A text mining application of emotion classifications of twitter’s users using naive bayes method. In: 2015 1st International Conference on Wireless and Telematics (ICWT), pp. 1–6 (2015). IEEE [find](https://scholar.google.com/scholar?q=Wikarsa%2C+L%2E%2C+Thahir%2C+S%2EN%2E%3A+A+text+mining+application+of+emotion+classifications+of+twitter%E2%80%99s+users+using+naive+bayes+method%2E+In%3A+2015+1st+International+Conference+on+Wireless+and+Telematics+%28ICWT%29%2C+pp)
3. Goldenberg, A., Gross, J., Garcia, D.: Emotional sharing on social media: How twitter replies contribute to increased emotional intensity (2018) [find](https://scholar.google.com/scholar?q=Goldenberg%2C+A%2E%2C+Gross%2C+J%2E%2C+Garcia%2C+D%2E%3A+Emotional+sharing+on+social+media%3A+How+twitter+replies+contribute+to+increased+emotional+intensity+%282018%29)
4. Milazzo, F., Augello, A., Pilato, G., Gentile, V., Gentile, A., Sorce, S.: Exploiting correlation between body gestures and spoken sentences for real-time emotion recognition. In: Proceedings of the 12th Biannual Conference on Italian SIGCHI Chapter, pp. 1–6 (2017) [find](https://scholar.google.com/scholar?q=Milazzo%2C+F%2E%2C+Augello%2C+A%2E%2C+Pilato%2C+G%2E%2C+Gentile%2C+V%2E%2C+Gentile%2C+A%2E%2C+Sorce%2C+S%2E%3A+Exploiting+correlation+between+body+gestures+and+spoken+sentences+for+real%2Dtime+emotion+recognition%2E+In%3A+Proceedings+of+the+1)
5. Wankhade, M., Rao, A.C.S., Kulkarni, C.: A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review 55(7), 5731–5780 (2022) [find](https://scholar.google.com/scholar?q=Wankhade%2C+M%2E%2C+Rao%2C+A%2EC%2ES%2E%2C+Kulkarni%2C+C%2E%3A+A+survey+on+sentiment+analysis+methods%2C+applications%2C+and+challenges%2E+Artificial+Intelligence+Review+55%287%29%2C+5731%E2%80%935780+%282022%29)
6. Acheampong, F.A., Wenyu, C., Nunoo-Mensah, H.: Text-based emotion detection: Advances, challenges, and opportunities. Engineering Reports 2(7), 12189 (2020) [find](https://scholar.google.com/scholar?q=Acheampong%2C+F%2EA%2E%2C+Wenyu%2C+C%2E%2C+Nunoo%2DMensah%2C+H%2E%3A+Text%2Dbased+emotion+detection%3A+Advances%2C+challenges%2C+and+opportunities%2E+Engineering+Reports+2%287%29%2C+12189+%282020%29)
7. Plutchik, R.: A general psychoevolutionary theory of emotion. In: Theories of Emotion, pp. 3–33. Elsevier, ??? (1980) [find](https://scholar.google.com/scholar?q=Plutchik%2C+R%2E%3A+A+general+psychoevolutionary+theory+of+emotion%2E+In%3A+Theories+of+Emotion%2C+pp%2E+3%E2%80%9333%2E+Elsevier%2C+%3F%3F%3F+%281980%29)
8. Ekman, P.: An argument for basic emotions. Cognition & emotion 6(3-4), 169–200 (1992) [find](https://scholar.google.com/scholar?q=Ekman%2C+P%2E%3A+An+argument+for+basic+emotions%2E+Cognition+%26+emotion+6%283%2D4%29%2C+169%E2%80%93200+%281992%29) [our card](https://md.research.elamur.ai/free/en/papers/ekman-1992-argument-basic-emotions/)
9. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013) [↗](https://arxiv.org/abs/1301.3781)
10. Boudad, N., Ezzahid, S., Faizi, R., Thami, R.O.H.: Exploring the use of word embedding and deep learning in arabic sentiment analysis. In: Advanced Intelligent Systems for Sustainable Development (AI2SD’2019) Volume 4-Advanced Intelligent Systems for Applied Computing Sciences, pp. 243–253 (2020). Springer [find](https://scholar.google.com/scholar?q=Boudad%2C+N%2E%2C+Ezzahid%2C+S%2E%2C+Faizi%2C+R%2E%2C+Thami%2C+R%2EO%2EH%2E%3A+Exploring+the+use+of+word+embedding+and+deep+learning+in+arabic+sentiment+analysis%2E+In%3A+Advanced+Intelligent+Systems+for+Sustainable+Development+%28AI2)
11. Sabri, T., Bahassine, S., El Beggar, O., Kissi, M.: An improved arabic text classification method using word embedding. International Journal of Electrical & Computer Engineering (2088-8708) 14(1) (2024) [find](https://scholar.google.com/scholar?q=Sabri%2C+T%2E%2C+Bahassine%2C+S%2E%2C+El+Beggar%2C+O%2E%2C+Kissi%2C+M%2E%3A+An+improved+arabic+text+classification+method+using+word+embedding%2E+International+Journal+of+Electrical+%26+Computer+Engineering+%282088%2D8708%29+14%281%29+%2820)
12. Gao, T., Yao, X., Chen, D.: Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021) [↗](https://arxiv.org/abs/2104.08821) [our card](https://md.research.elamur.ai/free/en/papers/gao-2021-simcse-simple-contrastive-learning-sentence/)
13. Zhou, Y., Kang, X., Ren, F.: Employing contrastive strategies for multi-label textual emotion recognition. In: International Conference on Intelligent Information Processing, pp. 299–310 (2022). Springer [find](https://scholar.google.com/scholar?q=Zhou%2C+Y%2E%2C+Kang%2C+X%2E%2C+Ren%2C+F%2E%3A+Employing+contrastive+strategies+for+multi%2Dlabel+textual+emotion+recognition%2E+In%3A+International+Conference+on+Intelligent+Information+Processing%2C+pp%2E+299%E2%80%93310+%282022%29%2E+Sprin)
14. Tursunov, A., Kwon, S., Pang, H.-S.: Discriminating emotions in the valence dimension from speech using timbre features. Applied Sciences 9(12), 2470 (2019) [find](https://scholar.google.com/scholar?q=Tursunov%2C+A%2E%2C+Kwon%2C+S%2E%2C+Pang%2C+H%2E%2DS%2E%3A+Discriminating+emotions+in+the+valence+dimension+from+speech+using+timbre+features%2E+Applied+Sciences+9%2812%29%2C+2470+%282019%29)
15. Bengio, Y., Courville, A., Vincent, P.: Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence 35(8), 1798–1828 (2013) [find](https://scholar.google.com/scholar?q=Bengio%2C+Y%2E%2C+Courville%2C+A%2E%2C+Vincent%2C+P%2E%3A+Representation+learning%3A+A+review+and+new+perspectives%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence+35%288%29%2C+1798%E2%80%931828+%282013%29) [our card](https://md.research.elamur.ai/free/en/papers/bengio-2012-representation-learning-review-new-perspectives/)
16. Lin, N., Qin, G., Wang, G., Zhou, D., Yang, A.: An effective deployment of contrastive learning in multi-label text classification. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 8730–8744 (2023) [find](https://scholar.google.com/scholar?q=Lin%2C+N%2E%2C+Qin%2C+G%2E%2C+Wang%2C+G%2E%2C+Zhou%2C+D%2E%2C+Yang%2C+A%2E%3A+An+effective+deployment+of+contrastive+learning+in+multi%2Dlabel+text+classification%2E+In%3A+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2)
17. Zheng, X., Yu, Z., Chen, L., Zhu, F., Wang, S.: Multi-label contrastive focal loss for pedestrian attribute recognition. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7349–7356 (2021). IEEE [find](https://scholar.google.com/scholar?q=Zheng%2C+X%2E%2C+Yu%2C+Z%2E%2C+Chen%2C+L%2E%2C+Zhu%2C+F%2E%2C+Wang%2C+S%2E%3A+Multi%2Dlabel+contrastive+focal+loss+for+pedestrian+attribute+recognition%2E+In%3A+2020+25th+International+Conference+on+Pattern+Recognition+%28ICPR%29%2C+pp%2E+7349%E2%80%93)
18. Chen, Z., Yang, C., Zhu, M., Peng, Z., Yuan, Y.: Personalized retrogress-resilient federated learning toward imbalanced medical data. IEEE Transactions on Medical Imaging 41(12), 3663–3674 (2022) [find](https://scholar.google.com/scholar?q=Chen%2C+Z%2E%2C+Yang%2C+C%2E%2C+Zhu%2C+M%2E%2C+Peng%2C+Z%2E%2C+Yuan%2C+Y%2E%3A+Personalized+retrogress%2Dresilient+federated+learning+toward+imbalanced+medical+data%2E+IEEE+Transactions+on+Medical+Imaging+41%2812%29%2C+3663%E2%80%933674+%282022%29)
19. Haralabopoulos, G., Anagnostopoulos, I., McAuley, D.: Ensemble deep learning for multilabel binary classification of user-generated content. Algorithms 13(4), 83 (2020) [find](https://scholar.google.com/scholar?q=Haralabopoulos%2C+G%2E%2C+Anagnostopoulos%2C+I%2E%2C+McAuley%2C+D%2E%3A+Ensemble+deep+learning+for+multilabel+binary+classification+of+user%2Dgenerated+content%2E+Algorithms+13%284%29%2C+83+%282020%29)
20. Nandwani, P., Verma, R.: A review on sentiment analysis and emotion detection from text. Social network analysis and mining 11(1), 81 (2021) [find](https://scholar.google.com/scholar?q=Nandwani%2C+P%2E%2C+Verma%2C+R%2E%3A+A+review+on+sentiment+analysis+and+emotion+detection+from+text%2E+Social+network+analysis+and+mining+11%281%29%2C+81+%282021%29)
21. Mohammad, S., Bravo-Marquez, F., Salameh, M., Kiritchenko, S.: Semeval-2018 task 1: Affect in tweets. In: Proceedings of the 12th International Workshop on Semantic Evaluation, pp. 1–17 (2018) [find](https://scholar.google.com/scholar?q=Mohammad%2C+S%2E%2C+Bravo%2DMarquez%2C+F%2E%2C+Salameh%2C+M%2E%2C+Kiritchenko%2C+S%2E%3A+Semeval%2D2018+task+1%3A+Affect+in+tweets%2E+In%3A+Proceedings+of+the+12th+International+Workshop+on+Semantic+Evaluation%2C+pp%2E+1%E2%80%9317+%282018%29) [our card](https://md.research.elamur.ai/free/en/papers/mohammad-2018-semeval-2018-task-1-affect/)
22. Mansy, A., Rady, S., Gharib, T.: An ensemble deep learning approach for emotion detection in arabic tweets. International Journal of Advanced Computer Science and Applications 13(4) (2022) [find](https://scholar.google.com/scholar?q=Mansy%2C+A%2E%2C+Rady%2C+S%2E%2C+Gharib%2C+T%2E%3A+An+ensemble+deep+learning+approach+for+emotion+detection+in+arabic+tweets%2E+International+Journal+of+Advanced+Computer+Science+and+Applications+13%284%29+%282022%29)
23. Khalil, E.A.H., Houby, E.M.E., Mohamed, H.K.: Deep learning for emotion analysis in arabic tweets. Journal of Big Data 8(1), 136 (2021) [find](https://scholar.google.com/scholar?q=Khalil%2C+E%2EA%2EH%2E%2C+Houby%2C+E%2EM%2EE%2E%2C+Mohamed%2C+H%2EK%2E%3A+Deep+learning+for+emotion+analysis+in+arabic+tweets%2E+Journal+of+Big+Data+8%281%29%2C+136+%282021%29)
24. Elfaik, H., et al.: Combining context-aware embeddings and an attentional deep learning model for arabic affect analysis on twitter. IEEE Access 9, 111214– 111230 (2021) [find](https://scholar.google.com/scholar?q=Elfaik%2C+H%2E%2C+et+al%2E%3A+Combining+context%2Daware+embeddings+and+an+attentional+deep+learning+model+for+arabic+affect+analysis+on+twitter%2E+IEEE+Access+9%2C+111214%E2%80%93+111230+%282021%29)
25. Abdelali, A., Mubarak, H., Chowdhury, S.A., Hasanain, M., Mousi, B., Boughorbel, S., Kheir, Y.E., Izham, D., Dalvi, F., Hawasly, M., et al.: Benchmarking arabic ai with large language models. arXiv preprint arXiv:2305.14982 (2023) [↗](https://arxiv.org/abs/2305.14982)
26. Alswaidan, N., Menai, M.E.B.: Hybrid feature model for emotion recognition in arabic text. IEEE Access 8, 37843–37854 (2020) [find](https://scholar.google.com/scholar?q=Alswaidan%2C+N%2E%2C+Menai%2C+M%2EE%2EB%2E%3A+Hybrid+feature+model+for+emotion+recognition+in+arabic+text%2E+IEEE+Access+8%2C+37843%E2%80%9337854+%282020%29)
27. Samy, A.E., El-Beltagy, S.R., Hassanien, E.: A context integrated model for multi-label emotion detection. Procedia computer science 142, 61–71 (2018) [find](https://scholar.google.com/scholar?q=Samy%2C+A%2EE%2E%2C+El%2DBeltagy%2C+S%2ER%2E%2C+Hassanien%2C+E%2E%3A+A+context+integrated+model+for+multi%2Dlabel+emotion+detection%2E+Procedia+computer+science+142%2C+61%E2%80%9371+%282018%29)
28. Asudani, D.S., Nagwani, N.K., Singh, P.: Impact of word embedding models on text analytics in deep learning environment: a review. Artificial intelligence review 56(9), 10345–10425 (2023) [find](https://scholar.google.com/scholar?q=Asudani%2C+D%2ES%2E%2C+Nagwani%2C+N%2EK%2E%2C+Singh%2C+P%2E%3A+Impact+of+word+embedding+models+on+text+analytics+in+deep+learning+environment%3A+a+review%2E+Artificial+intelligence+review+56%289%29%2C+10345%E2%80%9310425+%282023%29)
29. Mao, X., Chang, S., Shi, J., Li, F., Shi, R.: Sentiment-aware word embedding for emotion classification. Applied Sciences 9(7), 1334 (2019) [find](https://scholar.google.com/scholar?q=Mao%2C+X%2E%2C+Chang%2C+S%2E%2C+Shi%2C+J%2E%2C+Li%2C+F%2E%2C+Shi%2C+R%2E%3A+Sentiment%2Daware+word+embedding+for+emotion+classification%2E+Applied+Sciences+9%287%29%2C+1334+%282019%29)
30. Fang, L., Luo, Y., Feng, K., Zhao, K., Hu, A.: A knowledge-enriched ensemble method for word embedding and multi-sense embedding. IEEE Transactions on Knowledge and Data Engineering (2022) [find](https://scholar.google.com/scholar?q=Fang%2C+L%2E%2C+Luo%2C+Y%2E%2C+Feng%2C+K%2E%2C+Zhao%2C+K%2E%2C+Hu%2C+A%2E%3A+A+knowledge%2Denriched+ensemble+method+for+word+embedding+and+multi%2Dsense+embedding%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering+%282022%29)
31. Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014) [find](https://scholar.google.com/scholar?q=Pennington%2C+J%2E%2C+Socher%2C+R%2E%2C+Manning%2C+C%2ED%2E%3A+Glove%3A+Global+vectors+for+word+representation%2E+In%3A+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pp%2E+1532%E2%80%931)
32. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems 26 (2013) [find](https://scholar.google.com/scholar?q=Mikolov%2C+T%2E%2C+Sutskever%2C+I%2E%2C+Chen%2C+K%2E%2C+Corrado%2C+G%2ES%2E%2C+Dean%2C+J%2E%3A+Distributed+representations+of+words+and+phrases+and+their+compositionality%2E+Advances+in+neural+information+processing+systems+26+%282013%29)
33. Joulin, A., Grave, E., Bojanowski, P., Douze, M., Jégou, H., Mikolov, T.: Fasttext. zip: Compressing text classification models. arXiv preprint arXiv:1612.03651 (2016) [↗](https://arxiv.org/abs/1612.03651) [our card](https://md.research.elamur.ai/free/en/papers/joulin-2016-fasttext-zip-compressing-text-classification/)
34. Li, X., Sun, X., Meng, Y., Liang, J., Wu, F., Li, J.: Dice loss for data-imbalanced nlp tasks. arXiv preprint arXiv:1911.02855 (2019) [↗](https://arxiv.org/abs/1911.02855) [our card](https://md.research.elamur.ai/free/en/papers/li-2020-dice-loss-data-imbalanced-nlp/)
35. Al-Twairesh, N.: The evolution of language models applied to emotion analysis of arabic tweets. Information 12(2), 84 (2021) [find](https://scholar.google.com/scholar?q=Al%2DTwairesh%2C+N%2E%3A+The+evolution+of+language+models+applied+to+emotion+analysis+of+arabic+tweets%2E+Information+12%282%29%2C+84+%282021%29)
36. Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018) [↗](https://arxiv.org/abs/1810.04805)
37. David, M.S., Renjith, S.: Comparison of word embeddings in text classification based on rnn and cnn. In: IOP Conference Series: Materials Science and Engineering, vol. 1187, p. 012029 (2021). IOP Publishing [find](https://scholar.google.com/scholar?q=David%2C+M%2ES%2E%2C+Renjith%2C+S%2E%3A+Comparison+of+word+embeddings+in+text+classification+based+on+rnn+and+cnn%2E+In%3A+IOP+Conference+Series%3A+Materials+Science+and+Engineering%2C+vol%2E+1187%2C+p%2E+012029+%282021%29%2E+IOP+Publ)
38. Muromägi, A., Sirts, K., Laur, S.: Linear ensembles of word embedding models. arXiv preprint arXiv:1704.01419 (2017) [↗](https://arxiv.org/abs/1704.01419)
39. Speer, R., Chin, J.: An ensemble method to produce high-quality word embeddings (2016). arXiv preprint arXiv:1604.01692 (2016) [↗](https://arxiv.org/abs/1604.01692)
40. Antoun, W., Baly, F., Hajj, H.: Arabert: Transformer-based model for arabic language understanding. arXiv preprint arXiv:2003.00104 (2020) [↗](https://arxiv.org/abs/2003.00104) [our card](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/)
41. Safaya, A., Abdullatif, M., Yuret, D.: Kuisail at semeval-2020 task 12: Bert-cnn for offensive speech identification in social media. arXiv preprint arXiv:2007.13184 (2020) [↗](https://arxiv.org/abs/2007.13184) [our card](https://md.research.elamur.ai/free/en/papers/safaya-2020-kuisail-semeval-2020-task-12/)
42. Abdul-Mageed, M., Elmadany, A., Nagoudi, E.M.B.: Arbert & marbert: Deep bidirectional transformers for arabic. arXiv preprint arXiv:2101.01785 (2020) [↗](https://arxiv.org/abs/2101.01785) [our card](https://md.research.elamur.ai/free/en/papers/abdul-2021-mageed-arbert-marbert-deep-bidirectional-transformers/)
43. Aoumeur, N.E., Li, Z., Alshari, E.M.: Improving the polarity of text through word2vec embedding for primary classical arabic sentiment analysis. Neural processing letters 55(3), 2249–2264 (2023) [find](https://scholar.google.com/scholar?q=Aoumeur%2C+N%2EE%2E%2C+Li%2C+Z%2E%2C+Alshari%2C+E%2EM%2E%3A+Improving+the+polarity+of+text+through+word2vec+embedding+for+primary+classical+arabic+sentiment+analysis%2E+Neural+processing+letters+55%283%29%2C+2249%E2%80%932264+%282023%29)
44. Fadel, A., Tuffaha, I., Al-Ayyoub, M.: Pretrained ensemble learning for fine-grained propaganda detection. In: Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, pp. 139–142 (2019) [find](https://scholar.google.com/scholar?q=Fadel%2C+A%2E%2C+Tuffaha%2C+I%2E%2C+Al%2DAyyoub%2C+M%2E%3A+Pretrained+ensemble+learning+for+fine%2Dgrained+propaganda+detection%2E+In%3A+Proceedings+of+the+Second+Workshop+on+Natural+Language+Processing+for+Internet+Freedom%3A+C)
45. Alammary, A.S.: Bert models for arabic text classification: a systematic review. Applied Sciences 12(11), 5720 (2022) [find](https://scholar.google.com/scholar?q=Alammary%2C+A%2ES%2E%3A+Bert+models+for+arabic+text+classification%3A+a+systematic+review%2E+Applied+Sciences+12%2811%29%2C+5720+%282022%29)
46. Berrimi, M., Oussalah, M., Moussaoui, A., Saidi, M.: Attention mechanism architecture for arabic sentiment analysis. ACM Transactions on Asian and Low-Resource Language Information Processing 22(4), 1–26 (2023) [find](https://scholar.google.com/scholar?q=Berrimi%2C+M%2E%2C+Oussalah%2C+M%2E%2C+Moussaoui%2C+A%2E%2C+Saidi%2C+M%2E%3A+Attention+mechanism+architecture+for+arabic+sentiment+analysis%2E+ACM+Transactions+on+Asian+and+Low%2DResource+Language+Information+Processing+22%284%29%2C+1)
47. Elbedwehy, S., Medhat, T.: Improved arabic image captioning model using feature concatenation with pre-trained word embedding. Neural Computing and Applications 35(26), 19051–19067 (2023) [find](https://scholar.google.com/scholar?q=Elbedwehy%2C+S%2E%2C+Medhat%2C+T%2E%3A+Improved+arabic+image+captioning+model+using+feature+concatenation+with+pre%2Dtrained+word+embedding%2E+Neural+Computing+and+Applications+35%2826%29%2C+19051%E2%80%9319067+%282023%29)
48. Kamr, A.M., Mohamed, E.: akabert at semeval-2022 task 6: an ensemble transformer-based model for arabic sarcasm detection. In: Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pp. 885–890 (2022) [find](https://scholar.google.com/scholar?q=Kamr%2C+A%2EM%2E%2C+Mohamed%2C+E%2E%3A+akabert+at+semeval%2D2022+task+6%3A+an+ensemble+transformer%2Dbased+model+for+arabic+sarcasm+detection%2E+In%3A+Proceedings+of+the+16th+International+Workshop+on+Semantic+Evaluation+%28Se) [our card](https://md.research.elamur.ai/free/en/papers/kamr-2022-akabert-semeval-2022-task-6/)
49. Chouikhi, H., Chniter, H., Jarray, F.: Stacking bert based models for arabic sentiment analysis. In: KEOD, pp. 144–150 (2021) [find](https://scholar.google.com/scholar?q=Chouikhi%2C+H%2E%2C+Chniter%2C+H%2E%2C+Jarray%2C+F%2E%3A+Stacking+bert+based+models+for+arabic+sentiment+analysis%2E+In%3A+KEOD%2C+pp%2E+144%E2%80%93150+%282021%29)
50. Padma, S., Devi, B.K.: Classification of real value and complex value data using machine learning concepts. International Journal of Computer Science and Information Technologies 5(2), 2361–2364 (2014) [find](https://scholar.google.com/scholar?q=Padma%2C+S%2E%2C+Devi%2C+B%2EK%2E%3A+Classification+of+real+value+and+complex+value+data+using+machine+learning+concepts%2E+International+Journal+of+Computer+Science+and+Information+Technologies+5%282%29%2C+2361%E2%80%932364+%282014)
51. Kumar, P., Bhatnagar, R., Gaur, K., Bhatnagar, A.: Classification of imbalanced data: review of methods and applications. In: IOP Conference Series: Materials Science and Engineering, vol. 1099, p. 012077 (2021). IOP Publishing [find](https://scholar.google.com/scholar?q=Kumar%2C+P%2E%2C+Bhatnagar%2C+R%2E%2C+Gaur%2C+K%2E%2C+Bhatnagar%2C+A%2E%3A+Classification+of+imbalanced+data%3A+review+of+methods+and+applications%2E+In%3A+IOP+Conference+Series%3A+Materials+Science+and+Engineering%2C+vol%2E+1099%2C+p%2E+01)
52. Durand, T., Mehrasa, N., Mori, G.: Learning a deep convnet for multi-label classification with partial labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 647–657 (2019) [find](https://scholar.google.com/scholar?q=Durand%2C+T%2E%2C+Mehrasa%2C+N%2E%2C+Mori%2C+G%2E%3A+Learning+a+deep+convnet+for+multi%2Dlabel+classification+with+partial+labels%2E+In%3A+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+pp)
53. Dong, J.: Focal loss improves the model performance on multi-label image classifications with imbalanced data. In: Proceedings of the 2nd International Conference on Industrial Control Network And System Engineering Research, pp. 18–21 (2020) [find](https://scholar.google.com/scholar?q=Dong%2C+J%2E%3A+Focal+loss+improves+the+model+performance+on+multi%2Dlabel+image+classifications+with+imbalanced+data%2E+In%3A+Proceedings+of+the+2nd+International+Conference+on+Industrial+Control+Network+And+Sys)
54. Jiang, D., He, J., et al.: Text semantic classification of long discourses based on neural networks with improved focal loss. Computational Intelligence and Neuroscience 2021 (2021) [find](https://scholar.google.com/scholar?q=Jiang%2C+D%2E%2C+He%2C+J%2E%2C+et+al%2E%3A+Text+semantic+classification+of+long+discourses+based+on+neural+networks+with+improved+focal+loss%2E+Computational+Intelligence+and+Neuroscience+2021+%282021%29)
55. Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017) [find](https://scholar.google.com/scholar?q=Lin%2C+T%2E%2DY%2E%2C+Goyal%2C+P%2E%2C+Girshick%2C+R%2E%2C+He%2C+K%2E%2C+Dolla%CC%81r%2C+P%2E%3A+Focal+loss+for+dense+object+detection%2E+In%3A+Proceedings+of+the+IEEE+International+Conference+on+Computer+Vision%2C+pp%2E+2980%E2%80%932988+%282017%29) [our card](https://md.research.elamur.ai/free/en/papers/lin-2017-focal-loss-dense-object-detection/)
56. Sun, X., Dong, K., Ma, L., Sutcliffe, R., He, F., Chen, S., Feng, J.: Drug-drug interaction extraction via recurrent hybrid convolutional neural networks with an improved focal loss. Entropy 21(1), 37 (2019) [find](https://scholar.google.com/scholar?q=Sun%2C+X%2E%2C+Dong%2C+K%2E%2C+Ma%2C+L%2E%2C+Sutcliffe%2C+R%2E%2C+He%2C+F%2E%2C+Chen%2C+S%2E%2C+Feng%2C+J%2E%3A+Drug%2Ddrug+interaction+extraction+via+recurrent+hybrid+convolutional+neural+networks+with+an+improved+focal+loss%2E+Entropy+21%281%29%2C+37)
57. Zhu, Z., Dai, W., Hu, Y., Li, J.: Speech emotion recognition model based on bi-gru and focal loss. Pattern Recognition Letters 140, 358–365 (2020) [find](https://scholar.google.com/scholar?q=Zhu%2C+Z%2E%2C+Dai%2C+W%2E%2C+Hu%2C+Y%2E%2C+Li%2C+J%2E%3A+Speech+emotion+recognition+model+based+on+bi%2Dgru+and+focal+loss%2E+Pattern+Recognition+Letters+140%2C+358%E2%80%93365+%282020%29)
58. Ridnik, T., Ben-Baruch, E., Zamir, N., Noy, A., Friedman, I., Protter, M., Zelnik-Manor, L.: Asymmetric loss for multi-label classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 82–91 (2021) [find](https://scholar.google.com/scholar?q=Ridnik%2C+T%2E%2C+Ben%2DBaruch%2C+E%2E%2C+Zamir%2C+N%2E%2C+Noy%2C+A%2E%2C+Friedman%2C+I%2E%2C+Protter%2C+M%2E%2C+Zelnik%2DManor%2C+L%2E%3A+Asymmetric+loss+for+multi%2Dlabel+classification%2E+In%3A+Proceedings+of+the+IEEE%2FCVF+International+Conference+on)
59. Deng, J., Ren, F.: Multi-label emotion detection via emotion-specified feature extraction and emotion correlation learning. IEEE Transactions on Affective Computing 14(1), 475–486 (2020) [find](https://scholar.google.com/scholar?q=Deng%2C+J%2E%2C+Ren%2C+F%2E%3A+Multi%2Dlabel+emotion+detection+via+emotion%2Dspecified+feature+extraction+and+emotion+correlation+learning%2E+IEEE+Transactions+on+Affective+Computing+14%281%29%2C+475%E2%80%93486+%282020%29)
60. Bendjoudi, I., Hamad, D., Vanderhaegen, F., Dornaika, F.: Audio-visual and heart signals for attention and emotion analysis. In: ESREL 2020 PSAM 15-The 30th European Safety and Reliability Conference and the 15th Probabilistic Safety Assessment and Management Conference, pp. 2795–2801 (2020). Research Publishing Services [find](https://scholar.google.com/scholar?q=Bendjoudi%2C+I%2E%2C+Hamad%2C+D%2E%2C+Vanderhaegen%2C+F%2E%2C+Dornaika%2C+F%2E%3A+Audio%2Dvisual+and+heart+signals+for+attention+and+emotion+analysis%2E+In%3A+ESREL+2020+PSAM+15%2DThe+30th+European+Safety+and+Reliability+Conference+)
61. Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., Krishnan, D.: Supervised contrastive learning. Advances in neural information processing systems 33, 18661–18673 (2020) [find](https://scholar.google.com/scholar?q=Khosla%2C+P%2E%2C+Teterwak%2C+P%2E%2C+Wang%2C+C%2E%2C+Sarna%2C+A%2E%2C+Tian%2C+Y%2E%2C+Isola%2C+P%2E%2C+Maschinot%2C+A%2E%2C+Liu%2C+C%2E%2C+Krishnan%2C+D%2E%3A+Supervised+contrastive+learning%2E+Advances+in+neural+information+processing+systems+33%2C+18661%E2%80%931)
62. Hu, X., Lin, L., Liu, A., Wen, L., Philip, S.Y., et al.: A multi-level supervised contrastive learning framework for low-resource natural language inference. IEEE/ACM Transactions on Audio, Speech, and Language Processing (2023) [find](https://scholar.google.com/scholar?q=Hu%2C+X%2E%2C+Lin%2C+L%2E%2C+Liu%2C+A%2E%2C+Wen%2C+L%2E%2C+Philip%2C+S%2EY%2E%2C+et+al%2E%3A+A+multi%2Dlevel+supervised+contrastive+learning+framework+for+low%2Dresource+natural+language+inference%2E+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+an)
63. Eden, A.H.: Three paradigms of computer science. Minds and machines 17, 135– 167 (2007) [find](https://scholar.google.com/scholar?q=Eden%2C+A%2EH%2E%3A+Three+paradigms+of+computer+science%2E+Minds+and+machines+17%2C+135%E2%80%93+167+%282007%29)
64. Alrasheedy, M.N., Muniyandi, R.C., Fauzi, F.: Text-based emotion detection and applications: A literature review. In: 2022 International Conference on Cyber Resilience (ICCR), pp. 1–9 (2022). IEEE [find](https://scholar.google.com/scholar?q=Alrasheedy%2C+M%2EN%2E%2C+Muniyandi%2C+R%2EC%2E%2C+Fauzi%2C+F%2E%3A+Text%2Dbased+emotion+detection+and+applications%3A+A+literature+review%2E+In%3A+2022+International+Conference+on+Cyber+Resilience+%28ICCR%29%2C+pp%2E+1%E2%80%939+%282022%29%2E+IEEE)
65. Unnithan, N.A., Shalini, K., HB, B.G., Soman, K., et al.: Amrita student at semeval-2018 task 1: distributed representation of social media text for affects in tweets. In: Proceedings of The 12th International Workshop on Semantic Evaluation, pp. 319–323 (2018) [find](https://scholar.google.com/scholar?q=Unnithan%2C+N%2EA%2E%2C+Shalini%2C+K%2E%2C+HB%2C+B%2EG%2E%2C+Soman%2C+K%2E%2C+et+al%2E%3A+Amrita+student+at+semeval%2D2018+task+1%3A+distributed+representation+of+social+media+text+for+affects+in+tweets%2E+In%3A+Proceedings+of+The+12th+Inte)
66. Abdelali, A., Hassan, S., Mubarak, H., Darwish, K., Samih, Y.: Pre-training bert on arabic tweets: Practical considerations. arXiv preprint arXiv:2102.10684 (2021) [↗](https://arxiv.org/abs/2102.10684) [our card](https://md.research.elamur.ai/free/en/papers/abdelali-2021-pre-training-bert-arabic-tweets/)
67. George, A., HB, B.G., Soman, K., et al.: Teamcen at semeval-2018 task 1: global vectors representation in emotion detection. In: Proceedings of the 12th International Workshop on Semantic Evaluation, pp. 334–338 (2018) [find](https://scholar.google.com/scholar?q=George%2C+A%2E%2C+HB%2C+B%2EG%2E%2C+Soman%2C+K%2E%2C+et+al%2E%3A+Teamcen+at+semeval%2D2018+task+1%3A+global+vectors+representation+in+emotion+detection%2E+In%3A+Proceedings+of+the+12th+International+Workshop+on+Semantic+Evaluation%2C+)
68. Abdullah, M., Shaikh, S.: Teamuncc at semeval-2018 task 1: Emotion detection in english and arabic tweets using deep learning. In: Proceedings of the 12th International Workshop on Semantic Evaluation, pp. 350–357 (2018) [find](https://scholar.google.com/scholar?q=Abdullah%2C+M%2E%2C+Shaikh%2C+S%2E%3A+Teamuncc+at+semeval%2D2018+task+1%3A+Emotion+detection+in+english+and+arabic+tweets+using+deep+learning%2E+In%3A+Proceedings+of+the+12th+International+Workshop+on+Semantic+Evaluation)
69. Mulki, H., Ali, C.B., Haddad, H., Babaoğlu, I.: Tw-star at semeval-2018 task 1: Preprocessing impact on multi-label emotion classification. In: Proceedings of The 12th International Workshop on Semantic Evaluation, pp. 167–171 (2018) [find](https://scholar.google.com/scholar?q=Mulki%2C+H%2E%2C+Ali%2C+C%2EB%2E%2C+Haddad%2C+H%2E%2C+Babaog%CC%86lu%2C+I%2E%3A+Tw%2Dstar+at+semeval%2D2018+task+1%3A+Preprocessing+impact+on+multi%2Dlabel+emotion+classification%2E+In%3A+Proceedings+of+The+12th+International+Workshop+on+Seman)
70. Badaro, G., El Jundi, O., Khaddaj, A., Maarouf, A., Kain, R., Hajj, H., El-Hajj, W.: Ema at semeval-2018 task 1: Emotion mining for arabic. In: Proceedings of The 12th International Workshop on Semantic Evaluation, pp. 236–244 (2018) [find](https://scholar.google.com/scholar?q=Badaro%2C+G%2E%2C+El+Jundi%2C+O%2E%2C+Khaddaj%2C+A%2E%2C+Maarouf%2C+A%2E%2C+Kain%2C+R%2E%2C+Hajj%2C+H%2E%2C+El%2DHajj%2C+W%2E%3A+Ema+at+semeval%2D2018+task+1%3A+Emotion+mining+for+arabic%2E+In%3A+Proceedings+of+The+12th+International+Workshop+on+Semant)
71. Xu, P., Liu, Z., Winata, G.I., Lin, Z., Fung, P.: Emograph: Capturing emotion correlations using graph networks. arXiv preprint arXiv:2008.09378 (2020) [↗](https://arxiv.org/abs/2008.09378)
72. Alhuzali, H., Ananiadou, S.: Spanemo: Casting multi-label emotion classification as span-prediction. arXiv preprint arXiv:2101.10038 (2021) [↗](https://arxiv.org/abs/2101.10038)