---
title: "MentalMARBERT — Alharigy; 2026"
description: "The paper tackles multi-class detection of mental health disorders in Arabic tweets. 0.8506. recall. 33 references."
authors: ["Fatimah Almalki; Areej Alhothali; Lulwah Alharigy;", "Abdulrahman Aladeem"]
year: 2026
venue: "arXiv:2606.12649"
source: "https://arxiv.org/abs/2606.12649"
doi: "10.48550/arxiv.2606.12649"
arxiv: "2606.12649"
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/almalki-2026-mentalmarbert-domain-adaptive-pre-training/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/almalki-2026-mentalmarbert-domain-adaptive-pre-training/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/) / MentalMARBERT: Domain-Adaptive Pre-training and Two-Stage Fine-Tuning for Arabic Mental Health Disorders Detection

# MentalMARBERT: Domain-Adaptive Pre-training and Two-Stage Fine-Tuning for Arabic Mental Health Disorders Detection

**Authors:** Fatimah Almalki; Areej Alhothali; Lulwah Alharigy; and Abdulrahman Aladeem · **Year:** 2026 · **Venue:** arXiv:2606.12649 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2606.12649) · [PDF](https://arxiv.org/pdf/2606.12649) · [DOI 10.48550/arxiv.2606.12649](https://doi.org/10.48550/arxiv.2606.12649) · [arXiv 2606.12649](https://arxiv.org/abs/2606.12649) · [OpenAlex](https://openalex.org/W7164539664)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper tackles multi-class detection of mental health disorders in Arabic tweets. This task is hard because of dialects, informal spelling, scarce labelled data and skewed class sizes. The authors built a new labelled corpus of 50,670 tweets spanning six classes: five disorders (depression, anxiety, OCD, PTSD and bipolar disorder) plus a "None" class for tweets showing no disorder. They also gathered a large unlabelled set of mental-health tweets.

The work has two phases. In Phase 1, AraBERT, CAMeLBERT and MARBERT each received further domain-adaptive and task-adaptive pretraining (DAPT and TAPT) and were compared under one protocol. In Phase 2, the winning backbone, MentalMARBERT, was tested in four set-ups that cross single-stage versus hierarchical two-stage classification with full fine-tuning versus LoRA.

The adapted MARBERT was the only backbone with significant gains in both accuracy and macro-F1. The best configuration was two-stage with full fine-tuning, at macro-F1 0.8617 and accuracy 0.8778. The work matters because Arabic mental-health NLP has mostly been binary and has relied on unadapted general models.

## Key points
- New dataset: 50,670 tweets in six categories, with inter-annotator agreement of Krippendorff's Alpha 0.733 and average pairwise agreement of 0.797.
- Adaptation helped unevenly across backbones:
  - AraBERT showed no significant change after DAPT+TAPT.
  - CAMeLBERT improved only in recall.
  - MARBERT improved significantly in accuracy and macro-F1, which the authors attribute to its Twitter-based original pretraining.
- Full fine-tuning beat LoRA in both architectures. In single-stage, macro-F1 was 0.8564 vs 0.8521; in two-stage, the gap was larger, 0.8617 vs 0.8506. Recall did not differ significantly in either case.
- The two-stage design beat single-stage only under full fine-tuning (accuracy +0.0075, macro-F1 +0.0053). Under LoRA, no metric differed significantly, with p between 0.08 and 0.31.
- Results are reported as mean ± SD with per-metric p-values. The authors credit the hierarchy with cutting confusion between None and the disorder classes.

## Interesting ideas
- Splitting the decision into "is anything there at all?" and then "which kind?" reduced confusion with the dominant empty class; this is useful wherever a "none" label swamps the fine-grained ones.
- Continued pretraining paid off only for the backbone whose original data already resembled the target genre, so source–target alignment can matter more than the adaptation step itself.
- Each comparison was repeated across runs and judged by per-metric significance tests, which exposed effects that hold for one metric and not another.
- With mostly frozen weights (LoRA), the architectural choice stopped making a measurable difference, so cheap adapter training can hide design effects.

## For Mova

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

- **I1** (frames): Irony and indirect speech-act detection in prag could first gate whether a clause is non-literal at all, then pick the type, so literal clauses stop leaking into rare categories.
- **I2** (tree): Before continued pretraining of gparse on in-genre unlabeled text (fables, school tests), start from the encoder whose pretraining genre is closest, and verify the gain per backbone instead of assuming it.
- **I3** (learn): Parser and reader ablations could report mean ± SD over seeds with a p-value per metric, so that small LAS or answer-accuracy deltas are not mistaken for real wins.
- **I4** (learn): Architecture ablations for gparse should be run under full training, or at least confirmed there, before concluding that a design change is useless.

*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: [🐪 Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/)

## Institutions

- [King Abdulaziz University](https://md.research.elamur.ai/free/en/universities/king-abdulaziz-university/) — University, Jeddah, Saudi Arabia · 12 works · 309 citations

## Cite

Cite as: Fatimah Almalki; Areej Alhothali; Lulwah Alharigy; and Abdulrahman Aladeem. 2026. MentalMARBERT: Domain-Adaptive Pre-training and Two-Stage Fine-Tuning for Arabic Mental Health Disorders Detection. arXiv:2606.12649.

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

```bibtex
@misc{alharigy2026mentalmarbert,
  title = {{MentalMARBERT: Domain-Adaptive Pre-training and Two-Stage Fine-Tuning for Arabic Mental Health Disorders Detection}},
  author = {Fatimah Almalki; Areej Alhothali; Lulwah Alharigy; and Abdulrahman Aladeem},
  year = {2026},
  doi = {10.48550/arxiv.2606.12649},
  eprint = {2606.12649},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2606.12649}
}
```

- [← previous Memorization or Lucky Guesses: Detecting Short Sequences from Copyrighted Dutch News in LLM Output](https://md.research.elamur.ai/free/en/papers/veerbeek-2026-memorization-or-lucky-guesses-detecting/)
- [next → Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights](https://md.research.elamur.ai/free/en/papers/valero-2026-merge-conquer-instructing-multilingual-models/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/)

## References

33 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. World Health Organization. Mental health. [https://www.who.int](https://www.who.int), 2025. Accessed September 2025. [↗](https://www.who.int)
2. M. Effatpanah et al. Burden of mental disorders in the eastern mediterranean region, 1990–2019: Findings from the global burden of disease study 2019. Balkan Medical Journal, 40(2):112–122, 2023. [find](https://scholar.google.com/scholar?q=M%2E+Effatpanah+et+al%2E+Burden+of+mental+disorders+in+the+eastern+mediterranean+region%2C+1990%E2%80%932019%3A+Findings+from+the+global+burden+of+disease+study+2019%2E+Balkan+Medical+Journal%2C+40%282%29%3A112%E2%80%93122%2C+2023%2E)
3. Abdulaziz M. Al-Garni, Ayed A. Shati, Nora A. Almonawar, Ghadi M. Alamri, Lujain A. Alasmre, Thamraa N. Saad, Faisal M. Alshehri, Esraa Abdellatif Hammouda, and Ramy Mohammed Ghazy. Prevalence of depression, anxiety, and stress among students enrolled at king khalid university: a cross-sectional study. BMC Public Health, 25(354):1–11, 2025. [find](https://scholar.google.com/scholar?q=Abdulaziz+M%2E+Al%2DGarni%2C+Ayed+A%2E+Shati%2C+Nora+A%2E+Almonawar%2C+Ghadi+M%2E+Alamri%2C+Lujain+A%2E+Alasmre%2C+Thamraa+N%2E+Saad%2C+Faisal+M%2E+Alshehri%2C+Esraa+Abdellatif+Hammouda%2C+and+Ramy+Mohammed+Ghazy%2E+Prevalence+of+depr)
4. Wissam Antoun, Fady Baly, and Hazem Hajj. Arabert: Transformer-based model for arabic language understanding. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, 2020. [our card](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/)
5. Malek Tounsi, Hanen Ameur, and Salma Jamoussi. Deep Learning for Detecting Mental Disorder from User Content on Social Media. SN Computer Science, 2025. [find](https://scholar.google.com/scholar?q=Malek+Tounsi%2C+Hanen+Ameur%2C+and+Salma+Jamoussi%2E+Deep+Learning+for+Detecting+Mental+Disorder+from+User+Content+on+Social+Media%2E+SN+Computer+Science%2C+2025%2E)
6. Tianlin Zhang, Annika M. Schoene, Shaoxiong Ji, and Sophia Ananiadou. Natural language processing applied to mental illness detection: a narrative review. npj Digital Medicine, 5(1):1–14, 2022. [find](https://scholar.google.com/scholar?q=Tianlin+Zhang%2C+Annika+M%2E+Schoene%2C+Shaoxiong+Ji%2C+and+Sophia+Ananiadou%2E+Natural+language+processing+applied+to+mental+illness+detection%3A+a+narrative+review%2E+npj+Digital+Medicine%2C+5%281%29%3A1%E2%80%9314%2C+2022%2E)
7. Abhishek Pandey and Sanjay Kumar. Mental health and stress prediction using nlp and transformer-based techniques. 2024 IEEE Symposium on Wireless Technology & Applications (ISWTA), pages 61–66, 2024. p-value Two-Stage Mean Diff Sig 0.8654 ± 0.0023 0.8421 ± 0.0019 0.8625 ± 0.0042 0.8506 ± 0.0013 × × × × +0.0016 +0.0018 +0.0008 +0.0015 0.09 0.12 0.31 0.08 [find](https://scholar.google.com/scholar?q=Abhishek+Pandey+and+Sanjay+Kumar%2E+Mental+health+and+stress+prediction+using+nlp+and+transformer%2Dbased+techniques%2E+2024+IEEE+Symposium+on+Wireless+Technology+%26+Applications+%28ISWTA%29%2C+pages+61%E2%80%9366%2C+2024%2E+)
8. Shaoxiong Ji, Tianlin Zhang, Luna Ansari, Jie Fu, Prayag Tiwari, and Erik Cambria. Mentalbert: Publicly available pretrained language models for mental healthcare. In Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 7184–7190, Marseille, France, 2022. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Shaoxiong+Ji%2C+Tianlin+Zhang%2C+Luna+Ansari%2C+Jie+Fu%2C+Prayag+Tiwari%2C+and+Erik+Cambria%2E+Mentalbert%3A+Publicly+available+pretrained+language+models+for+mental+healthcare%2E+In+Proceedings+of+the+13th+Conferenc)
9. Muhammad Abdul-mageed. ARBERT & MARBERT : Deep Bidirectional Transformers for Arabic. (ii):7088– 7105, 2021. [our card](https://md.research.elamur.ai/free/en/papers/abdul-mageed-2021-arbert-marbert-deep-bidirectional-transformers/)
10. Anoushka Thakkar, Ankita Gupta, and Avinash De Sousa. Artificial intelligence in positive mental health: a narrative review. Frontiers in Digital Health, Volume 6 - 2024, 2024. [find](https://scholar.google.com/scholar?q=Anoushka+Thakkar%2C+Ankita+Gupta%2C+and+Avinash+De+Sousa%2E+Artificial+intelligence+in+positive+mental+health%3A+a+narrative+review%2E+Frontiers+in+Digital+Health%2C+Volume+6+%2D+2024%2C+2024%2E)
11. Giuliano Lorenzoni, Cristina Tavares, Nathalia Nascimento, Paulo Alencar, and Donald Cowan. Assessing ML Classification Algorithms and NLP Techniques for Depression Detection: An Experimental Case Study. 2024. [find](https://scholar.google.com/scholar?q=Giuliano+Lorenzoni%2C+Cristina+Tavares%2C+Nathalia+Nascimento%2C+Paulo+Alencar%2C+and+Donald+Cowan%2E+Assessing+ML+Classification+Algorithms+and+NLP+Techniques+for+Depression+Detection%3A+An+Experimental+Case+Stu)
12. AI Jaman, M Islam, S Sakib, and M Khan. Utilization of machine learning classifiers to predict different forms of mental illness: schizophrenia, PTSD, bipolar disorder and depression. (June), 2021. [find](https://scholar.google.com/scholar?q=AI+Jaman%2C+M+Islam%2C+S+Sakib%2C+and+M+Khan%2E+Utilization+of+machine+learning+classifiers+to+predict+different+forms+of+mental+illness%3A+schizophrenia%2C+PTSD%2C+bipolar+disorder+and+depression%2E+%28June%29%2C+2021%2E)
13. Areej Alzoubi, Ahmad Alaiad, Khaled Alkhattib, Ahed J Alkhatib, Aseel Abu Aqoulah, Almo’men bellah Alawnah, and Ola Hayajnah. Detection of depression from arabic tweets using machine learning. Sustainable Machine Intelligence Journal, 6:1–12, 2024. [find](https://scholar.google.com/scholar?q=Areej+Alzoubi%2C+Ahmad+Alaiad%2C+Khaled+Alkhattib%2C+Ahed+J+Alkhatib%2C+Aseel+Abu+Aqoulah%2C+Almo%E2%80%99men+bellah+Alawnah%2C+and+Ola+Hayajnah%2E+Detection+of+depression+from+arabic+tweets+using+machine+learning%2E+Sustain)
14. Rabia Qayyum, Hammad Afzal, Khawir Mahmood, and Naima Iltaf. Detection and Analysis of Mental Health Illness using Social Media. 4th International Conference on Communication Technologies, ComTech 2023, pages 34–41, 2023. [find](https://scholar.google.com/scholar?q=Rabia+Qayyum%2C+Hammad+Afzal%2C+Khawir+Mahmood%2C+and+Naima+Iltaf%2E+Detection+and+Analysis+of+Mental+Health+Illness+using+Social+Media%2E+4th+International+Conference+on+Communication+Technologies%2C+ComTech+202)
15. Muhammad Arif, Iqra Ameer, Necva Bölücü, Grigori Sidorov, Alexander Gelbukh, and Vinnayak Elangovan. Mental Illness Classification on Social Media Texts Using Deep Learning and Transfer Learning. Computacion y Sistemas, 28(2):451–464, 2024. [find](https://scholar.google.com/scholar?q=Muhammad+Arif%2C+Iqra+Ameer%2C+Necva+B%C3%B6l%C3%BCc%C3%BC%2C+Grigori+Sidorov%2C+Alexander+Gelbukh%2C+and+Vinnayak+Elangovan%2E+Mental+Illness+Classification+on+Social+Media+Texts+Using+Deep+Learning+and+Transfer+Learning%2E+Comp)
16. Xuhai Xu, Bingsheng Yao, Yuanzhe Dong, Saadia Gabriel, Hong Yu, James Hendler, Marzyeh Ghassemi, Anind K. Dey, and Dakuo Wang. Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(1):1–32, 2024. [find](https://scholar.google.com/scholar?q=Xuhai+Xu%2C+Bingsheng+Yao%2C+Yuanzhe+Dong%2C+Saadia+Gabriel%2C+Hong+Yu%2C+James+Hendler%2C+Marzyeh+Ghassemi%2C+Anind+K%2E+Dey%2C+and+Dakuo+Wang%2E+Mental%2DLLM%3A+Leveraging+Large+Language+Models+for+Mental+Health+Prediction)
17. Abdelrahaman A. Hassan, Radwa J. Hanafy, and Mohammed E. Fouda. Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models. 2024. [find](https://scholar.google.com/scholar?q=Abdelrahaman+A%2E+Hassan%2C+Radwa+J%2E+Hanafy%2C+and+Mohammed+E%2E+Fouda%2E+Automated+Multi%2DLabel+Annotation+for+Mental+Health+Illnesses+Using+Large+Language+Models%2E+2024%2E)
18. Suzan Elmajali and Irfan Ahmad. Toward Early Detection of Depression: Detecting Depression Symptoms in Arabic Tweets Using Pretrained Transformers. IEEE Access, 12(June):88134–88145, 2024. [find](https://scholar.google.com/scholar?q=Suzan+Elmajali+and+Irfan+Ahmad%2E+Toward+Early+Detection+of+Depression%3A+Detecting+Depression+Symptoms+in+Arabic+Tweets+Using+Pretrained+Transformers%2E+IEEE+Access%2C+12%28June%29%3A88134%E2%80%9388145%2C+2024%2E)
19. Loukas Ilias, Spiros Mouzakitis, and Dimitris Askounis. Calibration of Transformer-Based Models for Identifying Stress and Depression in Social Media. IEEE Transactions on Computational Social Systems, 11(2):1979–1990, 2024. [find](https://scholar.google.com/scholar?q=Loukas+Ilias%2C+Spiros+Mouzakitis%2C+and+Dimitris+Askounis%2E+Calibration+of+Transformer%2DBased+Models+for+Identifying+Stress+and+Depression+in+Social+Media%2E+IEEE+Transactions+on+Computational+Social+Systems)
20. Alireza Pourkeyvan, Ramin Safa, and Ali Sorourkhah. Harnessing the power of hugging face transformers for predicting mental health disorders in social networks. IEEE Access, 12:28025–28035, 2024. [find](https://scholar.google.com/scholar?q=Alireza+Pourkeyvan%2C+Ramin+Safa%2C+and+Ali+Sorourkhah%2E+Harnessing+the+power+of+hugging+face+transformers+for+predicting+mental+health+disorders+in+social+networks%2E+IEEE+Access%2C+12%3A28025%E2%80%9328035%2C+2024%2E)
21. Yining Hua, Fenglin Liu, Kailai Yang, Zehan Li, Yi-han Sheu, Peilin Zhou, Lauren V. Moran, Sophia Ananiadou, and Andrew Beam. Large Language Models in Mental Health Care: a Scoping Review. pages 1–22, 2024. [find](https://scholar.google.com/scholar?q=Yining+Hua%2C+Fenglin+Liu%2C+Kailai+Yang%2C+Zehan+Li%2C+Yi%2Dhan+Sheu%2C+Peilin+Zhou%2C+Lauren+V%2E+Moran%2C+Sophia+Ananiadou%2C+and+Andrew+Beam%2E+Large+Language+Models+in+Mental+Health+Care%3A+a+Scoping+Review%2E+pages+1%E2%80%9322%2C)
22. Wei Zhai, Hongzhi Qi, Qing Zhao, Jianqiang Li, Ziqi Wang, Han Wang, Bing Xiang Yang, and Guanghui Fu. Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis. 2023. [find](https://scholar.google.com/scholar?q=Wei+Zhai%2C+Hongzhi+Qi%2C+Qing+Zhao%2C+Jianqiang+Li%2C+Ziqi+Wang%2C+Han+Wang%2C+Bing+Xiang+Yang%2C+and+Guanghui+Fu%2E+Chinese+MentalBERT%3A+Domain%2DAdaptive+Pre%2Dtraining+on+Social+Media+for+Chinese+Mental+Health+Text+An)
23. Apify. Twitter search scraper, 2025. Accessed: 2025-09-01. [find](https://scholar.google.com/scholar?q=Apify%2E+Twitter+search+scraper%2C+2025%2E+Accessed%3A+2025%2D09%2D01%2E)
24. Klaus Krippendorff. Content Analysis: An Introduction to Its Methodology. Sage Publications, 4th edition, 2018. [find](https://scholar.google.com/scholar?q=Klaus+Krippendorff%2E+Content+Analysis%3A+An+Introduction+to+Its+Methodology%2E+Sage+Publications%2C+4th+edition%2C+2018%2E)
25. Joseph L. Fleiss, Bruce Levin, and Myunghee Cho Paik. Statistical Methods for Rates and Proportions. John Wiley & Sons, 3rd edition, 2003. [find](https://scholar.google.com/scholar?q=Joseph+L%2E+Fleiss%2C+Bruce+Levin%2C+and+Myunghee+Cho+Paik%2E+Statistical+Methods+for+Rates+and+Proportions%2E+John+Wiley+%26+Sons%2C+3rd+edition%2C+2003%2E)
26. Jacob Cohen. A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1):37–46, 1960. [find](https://scholar.google.com/scholar?q=Jacob+Cohen%2E+A+coefficient+of+agreement+for+nominal+scales%2E+Educational+and+Psychological+Measurement%2C+20%281%29%3A37%E2%80%9346%2C+1960%2E)
27. Mary L. McHugh. Interrater reliability: The kappa statistic. Biochemia Medica, 22(3):276–282, 2012. [find](https://scholar.google.com/scholar?q=Mary+L%2E+McHugh%2E+Interrater+reliability%3A+The+kappa+statistic%2E+Biochemia+Medica%2C+22%283%29%3A276%E2%80%93282%2C+2012%2E)
28. J. Richard Landis and Gary G. Koch. The measurement of observer agreement for categorical data. Biometrics, 33(1):159–174, 1977. [find](https://scholar.google.com/scholar?q=J%2E+Richard+Landis+and+Gary+G%2E+Koch%2E+The+measurement+of+observer+agreement+for+categorical+data%2E+Biometrics%2C+33%281%29%3A159%E2%80%93174%2C+1977%2E)
29. Go Inoue, Bashar Alhafni, Nurpeiis Baimukan, Houda Bouamor, and Nizar Habash. The interplay of variant, size, and task type in arabic pre-trained language models. 9 2021. [our card](https://md.research.elamur.ai/free/en/papers/inoue-2021-interplay-variant-size-task-type/)
30. Suchin Gururangan, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A Smith. Don ’ t Stop Pretraining : Adapt Language Models to Domains and Tasks. 2019. [find](https://scholar.google.com/scholar?q=Suchin+Gururangan%2C+Swabha+Swayamdipta%2C+Kyle+Lo%2C+Iz+Beltagy%2C+Doug+Downey%2C+and+Noah+A+Smith%2E+Don+%E2%80%99+t+Stop+Pretraining+%3A+Adapt+Language+Models+to+Domains+and+Tasks%2E+2019%2E)
31. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations (ICLR), 2022. [our card](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/)
32. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186, 2019. [our card](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/)
33. Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. Optuna: A next-generation hyperparameter optimization framework. 7 2019. [our card](https://md.research.elamur.ai/free/en/papers/akiba-2019-optuna-next-generation-hyperparameter-optimization/)