---
title: "Baseline English and Maltese-English Classification Models for"
description: "The paper sets reference points for opinion classification in a small, imbalanced setting where a low-resourced language is… 41 references."
authors: ["Keith Cortis", "Brian Davis"]
year: 2022
venue: "Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages"
source: "https://aclanthology.org/2022.sigul-1.21/"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/cortis-2022-baseline-english-maltese-english-classification/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/cortis-2022-baseline-english-maltese-english-classification/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/9/) / Baseline English and Maltese-English Classification Models for Subjectivity Detection, Sentiment Analysis, Emotion Analysis, Sarcasm Detection, and Irony Detection

# Baseline English and Maltese-English Classification Models for Subjectivity Detection, Sentiment Analysis, Emotion Analysis, Sarcasm Detection, and Irony Detection

**Authors:** [Keith Cortis](https://md.research.elamur.ai/free/en/authors/keith-cortis/) and [Brian Davis](https://md.research.elamur.ai/free/en/authors/brian-davis/) · **Year:** 2022 · **Venue:** [Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages](https://md.research.elamur.ai/free/en/venues/sigul/) ([SIGUL Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages 2022](https://md.research.elamur.ai/free/en/venues/sigul/2022/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2022.sigul-1.21/) · [PDF](https://aclanthology.org/2022.sigul-1.21.pdf)

## Summary
The paper sets reference points for opinion classification in a small, imbalanced setting where a low-resourced language is mixed with English. The authors use their own social opinion dataset about Malta's annual Government Budget (2018–2020). It mixes newswire reader comments with tweets, and every post is annotated on five aspects of opinion: whether it is subjective, its sentiment polarity, the emotion it expresses, and whether it is sarcastic or ironic. They train separate models for English posts and for Maltese-English/Maltese posts using eight classic scikit-learn classifiers. Posts are cleaned, stemmed and turned into TF-IDF vectors, and every model is scored with stratified 10-fold cross-validation so that no data has to be held out. The paper reports results for every task, language subset and algorithm. However, the results tables and their discussion are missing from the extracted text, so no specific winners or scores are given here. The work matters because it gives future Maltese and code-switched opinion mining research a documented, reproducible starting point to beat. It also shows that cheap traditional learners remain a sensible first step when data is scarce.

## Key points
- The dataset has 6,387 online posts from Times of Malta, MaltaToday, The Malta Independent and Twitter, covering the 2018, 2019 and 2020 budgets.
- About 74.09% of posts are English and 24.99% are Maltese-English or Maltese. Maltese-only posts were too few to stand alone, so they were merged with the code-switched posts.
- Eight algorithms were trained:
  - Bernoulli NB and Complement NB
  - SVC, NuSVC and Linear SVC
  - Logistic Regression
  - Decision Tree (CART)
  - Random Forest
- Each post was preprocessed with syntactic cleanup and NLTK Porter stemming, then represented with scikit-learn's TfidfVectorizer.
- Evaluation used stratified 10-fold cross-validation over each language subset, which keeps class ratios constant despite imbalance. Everything ran on an ordinary laptop (i7 CPU, 8 GB RAM).

## Interesting ideas
- Annotating every post along five related opinion axes at once lets the axes be compared and correlated directly, for example sarcasm against negative sentiment.
- Running a whole family of cheap TF-IDF classifiers as a published floor makes later, more complex systems accountable to a simple reference.
- On small corpora, the authors use stratified k-fold cross-validation instead of a fixed held-out split, so the scarce data is fully used and class ratios are preserved in each fold.
- When a category is too sparse to model alone, such as Maltese-only posts, the authors merge it with its nearest neighbour category rather than discarding it.
- The choice of Complement NB is motivated by class imbalance, which shows how a model can be picked to fit the label distribution.

## For Mova

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

- **I1** (frames): A test set where each sentence carries subjectivity, polarity, emotion and irony labels together could check whether prag's irony and speech-act decisions agree with its polarity reading.
- **I2** (learn): Run a TF-IDF/linear baseline on the same tasks as a negative control, so any claimed gain from tree-and-frame reasoning must clearly exceed what bag of words gets for free.
- **I3** (learn): Evaluations on small hand-checked sets, such as irony or fable QA items, could use stratified folds to give steadier numbers than one tiny test split.
- **I4** (tokens): Rare mixed-language or foreign-word inputs could be pooled under one code-switch tag, so the tagger handles them consistently instead of guessing per token.
- **I5** (learn): When training classifiers for rare phenomena like sarcasm, check the label skew first and choose imbalance-aware learners or weighting accordingly.

*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 (2): [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (3): [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 · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Keith Cortis and Brian Davis. 2022. Baseline English and Maltese-English Classification Models for Subjectivity Detection, Sentiment Analysis, Emotion Analysis, Sarcasm Detection, and Irony Detection. Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages.

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

```bibtex
@inproceedings{cortis2022baseline,
  title = {{Baseline English and Maltese-English Classification Models for Subjectivity Detection, Sentiment Analysis, Emotion Analysis, Sarcasm Detection, and Irony Detection}},
  author = {Keith Cortis and Brian Davis},
  booktitle = {Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages},
  year = {2022},
  url = {https://aclanthology.org/2022.sigul-1.21/}
}
```

- [← previous Barch: an English Dataset of Bar Chart Summaries](https://md.research.elamur.ai/free/en/papers/skrjanec-2022-barch-english-dataset-bar-chart/)
- [next → Bibliography of Ethiopian Semitic, Cushitic, and Omotic Linguistics XXIV: 2020](https://md.research.elamur.ai/free/en/papers/maria-2022-bibliography-ethiopian-semitic-cushitic-omotic/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/9/)

## References

41 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Appidi, A. R., Srirangam, V. K., Suhas, D., and Shrivastava, M. (2020). Creation of corpus and analy-SVC BNB CNB DT RF 0.772777 0.854936 0.817842 0.842926 0.15322 0.105658 0.112311 0.141601 0.075907 0.024654 0.911396 11.830028 0.371596 0.002719 18.196656 0.802879 0.864388 0.83255 0.847062 0.114555 0.09073 0.105097 0.119309 0.055128 0.040290 0.844383 11.074797 0.5 0 18.066252 0.433592 0.001532 16.025399 0.593306 0.724719 0.711952 0.720501 0.060966 0.102363 0.089007 0.10021 0.043515 0.036038 1.418103 12.771962 0.333333 0 16.399088 0.449516 0.612975 0.601 0.619531 0.049415 0.08929 0.087626 0.101987 0.030229 0.027661 1.324603 15.214964 0.314026 0.432851 0.403896 0.418661 0.035831 0.047303 0.070764 0.06 0.056324 0.036504 1.851777 17.749398 0.234498 0.002648 21.907470 0.162991 0.254581 0.246939 0.276573 0.02325 0.031079 0.061356 0.054324 0.044598 0.040448 2.101381 19.586962 0.125 0 22.532657 0.931012 0.004388 2.055357 0.921376 0.9097 0.915169 0.931012 0.016343 0.036802 0.023135 0.004388 0.058842 0.040891 1.042049 8.552041 0.507068 0.530167 0.491371 0.499671 0.035031 0.087631 0.027111 0.000987 0.043882 0.035901 0.930696 8.509591 0.5 0 1.977244 0.855613 0.884021 0.880597 0.873464 0.031979 0.042444 0.031066 0.004947 0.040492 0.044879 1.090016 10.739472 0.874091 0.00409 3.377020 0.507704 0.611068 0.584066 0.506458 0.034832 0.057851 0.049402 0.013006 0.038205 0.032164 1.082346 10.587719 0.5 0 3.323173 sis in code-mixed kannada-english twitter data for emotion prediction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6703–6709. [find](https://scholar.google.com/scholar?q=Appidi%2C+A%2E+R%2E%2C+Srirangam%2C+V%2E+K%2E%2C+Suhas%2C+D%2E%2C+and+Shrivastava%2C+M%2E+%282020%29%2E+Creation+of+corpus+and+analy%2DSVC+BNB+CNB+DT+RF+0%2E772777+0%2E854936+0%2E817842+0%2E842926+0%2E15322+0%2E105658+0%2E112311+0%2E141601+0%2E075907+0)
2. Bansal, S., Garimella, V., Suhane, A., Patro, J., and Mukherjee, A. (2020). [Code-switching patterns can be an effective route to improve performance of downstream NLP applications: A case study of humour, sarcasm and hate speech detection](https://md.research.elamur.ai/free/en/papers/bansal-2020-code-switching-patterns-can-be/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1018– 1023, Online, July. Association for Computational Linguistics.
3. Bird, S., Klein, E., and Loper, E. (2009). Natural language processing with Python: analyzing text with the natural language toolkit. ” O’Reilly Media, Inc.”. [find](https://scholar.google.com/scholar?q=Bird%2C+S%2E%2C+Klein%2C+E%2E%2C+and+Loper%2C+E%2E+%282009%29%2E+Natural+language+processing+with+Python%3A+analyzing+text+with+the+natural+language+toolkit%2E+%E2%80%9D+O%E2%80%99Reilly+Media%2C+Inc%2E%E2%80%9D%2E)
4. Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32. [find](https://scholar.google.com/scholar?q=Breiman%2C+L%2E+%282001%29%2E+Random+forests%2E+Machine+learning%2C+45%281%29%3A5%E2%80%9332%2E)
5. Brodersen, K. H., Ong, C. S., Stephan, K. E., and Buhmann, J. M. (2010). The balanced accuracy and its posterior distribution. In 2010 20th international conference on pattern recognition, pages 3121–3124. IEEE. [find](https://scholar.google.com/scholar?q=Brodersen%2C+K%2E+H%2E%2C+Ong%2C+C%2E+S%2E%2C+Stephan%2C+K%2E+E%2E%2C+and+Buhmann%2C+J%2E+M%2E+%282010%29%2E+The+balanced+accuracy+and+its+posterior+distribution%2E+In+2010+20th+international+conference+on+pattern+recognition%2C+pages+3121%E2%80%93)
6. Carvalho, J. and Plastino, A. (2021). On the evaluation and combination of state-of-the-art features in twitter sentiment analysis. Artificial Intelligence Review, 54(3):1887–1936. [↗](https://doi.org/10.1007/s10462-020-09895-6)
7. Cateni, S., Colla, V., and Vannucci, M. (2014). A method for resampling imbalanced datasets in binary classification tasks for real-world problems. Neurocomputing, 135:32–41. [↗](https://doi.org/10.1016/j.neucom.2013.05.059)
8. Chinchor, N. (1992). Muc-4 evaluation metrics. In Proceedings of the 4th Conference on Message Understanding, MUC4 ’92, page 22–29, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chinchor%2C+N%2E+%281992%29%2E+Muc%2D4+evaluation+metrics%2E+In+Proceedings+of+the+4th+Conference+on+Message+Understanding%2C+MUC4+%E2%80%9992%2C+page+22%E2%80%9329%2C+USA%2E+Association+for+Computational+Linguistics%2E)
9. Cortes, C. and Vapnik, V. (1995). [Support-vector networks](https://md.research.elamur.ai/free/en/papers/cortes-1995-support-vector-networks/). Machine learning, 20(3):273–297. [↗](https://doi.org/10.1007/bf00994018)
10. Cortis, K. and Davis, B. (2021a). A dataset of multidimensional and multilingual social opinions for malta’s annual government budget. In Proceedings of the International AAAI Conference on Web and Social Media, volume 15, pages 971–981. [find](https://scholar.google.com/scholar?q=Cortis%2C+K%2E+and+Davis%2C+B%2E+%282021a%29%2E+A+dataset+of+multidimensional+and+multilingual+social+opinions+for+malta%E2%80%99s+annual+government+budget%2E+In+Proceedings+of+the+International+AAAI+Conference+on+Web+and+So)
11. Cortis, K. and Davis, B. (2021b). Over a decade of social opinion mining: a systematic review. Artificial intelligence review, pages 1–93. [↗](https://doi.org/10.1007/s10462-021-10030-2)
12. Cortis, K., Freitas, A., Daudert, T., Huerlimann, M., Zarrouk, M., Handschuh, S., and Davis, B. (2017). SemEval-2017 task 5: Fine-grained sentiment analysis on financial microblogs and news. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 519–535, Vancouver, Canada, August. Association for Computational Linguistics. [↗](https://doi.org/10.5281/zenodo.1228821)
13. Cortis, K., Verma, K., and Davis, B. (2021). [Fine-tuning neural language models for multidimensional opinion mining of english-maltese social data](https://md.research.elamur.ai/free/en/papers/cortis-2021-fine-tuning-neural-language-models/). In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 309–314.
14. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). arXiv preprint arXiv:1810.04805. [↗](https://arxiv.org/abs/1810.04805)
15. Gupta, U., Chatterjee, A., Srikanth, R., and Agrawal, P. (2017). A sentiment-and-semantics-based approach for emotion detection in textual conversations. arXiv preprint arXiv:1707.06996. [↗](https://arxiv.org/abs/1707.06996)
16. Hemmatian, F. and Sohrabi, M. K. (2019). A survey on classification techniques for opinion mining and sentiment analysis. Artificial Intelligence Review, 52(3):1495–1545. [find](https://scholar.google.com/scholar?q=Hemmatian%2C+F%2E+and+Sohrabi%2C+M%2E+K%2E+%282019%29%2E+A+survey+on+classification+techniques+for+opinion+mining+and+sentiment+analysis%2E+Artificial+Intelligence+Review%2C+52%283%29%3A1495%E2%80%931545%2E)
17. Hilts, A. and Yu, E. (2010). Modeling social media support for the elicitation of citizen opinion. In Proceedings of the International Workshop on Modeling Social Media, pages 1–4. [find](https://scholar.google.com/scholar?q=Hilts%2C+A%2E+and+Yu%2C+E%2E+%282010%29%2E+Modeling+social+media+support+for+the+elicitation+of+citizen+opinion%2E+In+Proceedings+of+the+International+Workshop+on+Modeling+Social+Media%2C+pages+1%E2%80%934%2E)
18. Joulin, A., Grave, E., Bojanowski, P., and Mikolov, T. (2016). Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759. [↗](https://arxiv.org/abs/1607.01759)
19. Kothari, A., Magdy, W., Darwish, K., Mourad, A., and Taei, A. (2013). Detecting comments on news articles in microblogs. In Proceedings of the International AAAI Conference on Web and Social Media, volume 7. [find](https://scholar.google.com/scholar?q=Kothari%2C+A%2E%2C+Magdy%2C+W%2E%2C+Darwish%2C+K%2E%2C+Mourad%2C+A%2E%2C+and+Taei%2C+A%2E+%282013%29%2E+Detecting+comments+on+news+articles+in+microblogs%2E+In+Proceedings+of+the+International+AAAI+Conference+on+Web+and+Social+Media%2C+vo)
20. LeCun, Y., Boser, B. E., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W. E., and Jackel, L. D. (1990). Handwritten digit recognition with a backpropagation network. In Advances in neural information processing systems, pages 396–404. [find](https://scholar.google.com/scholar?q=LeCun%2C+Y%2E%2C+Boser%2C+B%2E+E%2E%2C+Denker%2C+J%2E+S%2E%2C+Henderson%2C+D%2E%2C+Howard%2C+R%2E+E%2E%2C+Hubbard%2C+W%2E+E%2E%2C+and+Jackel%2C+L%2E+D%2E+%281990%29%2E+Handwritten+digit+recognition+with+a+backpropagation+network%2E+In+Advances+in+neural+info)
21. Lewis, D. D. (1998). Naive (bayes) at forty: The independence assumption in information retrieval. In European conference on machine learning, pages 4– 15. Springer. [find](https://scholar.google.com/scholar?q=Lewis%2C+D%2E+D%2E+%281998%29%2E+Naive+%28bayes%29+at+forty%3A+The+independence+assumption+in+information+retrieval%2E+In+European+conference+on+machine+learning%2C+pages+4%E2%80%93+15%2E+Springer%2E)
22. Ligthart, A., Catal, C., and Tekinerdogan, B. (2021). Systematic reviews in sentiment analysis: a tertiary study. Artificial Intelligence Review, pages 1–57. [↗](https://doi.org/10.1007/s10462-021-09973-3)
23. Liu, B. (2010). Sentiment analysis and subjectivity. In Handbook of Natural Language Processing, Second Edition. Taylor and Francis Group, Boca. [find](https://scholar.google.com/scholar?q=Liu%2C+B%2E+%282010%29%2E+Sentiment+analysis+and+subjectivity%2E+In+Handbook+of+Natural+Language+Processing%2C+Second+Edition%2E+Taylor+and+Francis+Group%2C+Boca%2E)
24. Mamta, Ekbal, A., Bhattacharyya, P., Srivastava, S., Kumar, A., and Saha, T. (2020). Multi-domain tweet corpora for sentiment analysis: Resource creation and evaluation. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 5046–5054, Marseille, France, May. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Mamta%2C+Ekbal%2C+A%2E%2C+Bhattacharyya%2C+P%2E%2C+Srivastava%2C+S%2E%2C+Kumar%2C+A%2E%2C+and+Saha%2C+T%2E+%282020%29%2E+Multi%2Ddomain+tweet+corpora+for+sentiment+analysis%3A+Resource+creation+and+evaluation%2E+In+Proceedings+of+the+12th+Lan)
25. McCullagh, P. (1984). Generalized linear models. European Journal of Operational Research, 16(3):285– 292. [↗](https://doi.org/10.1016/0377-2217(84)90282-0)
26. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). [Efficient estimation of word representations in vector space](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/). arXiv preprint arXiv:1301.3781. [↗](https://arxiv.org/abs/1301.3781)
27. Mohammad, S., Bravo-Marquez, F., Salameh, M., and Kiritchenko, S. (2018). [Semeval-2018 task 1: Affect in tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2018-semeval-2018-task-1-affect/). In Proceedings of the 12th international workshop on semantic evaluation, pages 1– 17.
28. More, A. (2016). Survey of resampling techniques for improving classification performance in unbalanced datasets. arXiv preprint arXiv:1608.06048. [↗](https://arxiv.org/abs/1608.06048)
29. Padurariu, C. and Breaban, M. E. (2019). Dealing with data imbalance in text classification. Procedia Computer Science, 159:736–745. [find](https://scholar.google.com/scholar?q=Padurariu%2C+C%2E+and+Breaban%2C+M%2E+E%2E+%282019%29%2E+Dealing+with+data+imbalance+in+text+classification%2E+Procedia+Computer+Science%2C+159%3A736%E2%80%93745%2E)
30. Pang, B. and Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends® in Information Retrieval, 2(1-2):1–135, January. [↗](https://doi.org/10.1561/9781601981516)
31. Patwa, P., Aguilar, G., Kar, S., Pandey, S., PYKL, S., Gambäck, B., Chakraborty, T., Solorio, T., and Das, A. (2020). [Semeval-2020 task 9: Overview of sentiment analysis of code-mixed tweets](https://md.research.elamur.ai/free/en/papers/patwa-2020-semeval-2020-task-9-overview/). In Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval-2020), Barcelona, Spain, December. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2008.04277)
32. Pennington, J., Socher, R., and Manning, C. D. (2014). [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543.
33. Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., Al-Smadi, M., Al-Ayyoub, M., Zhao, Y., Qin, B., De Clercq, O., et al. (2016). [Semeval-2016 task 5: Aspect based sentiment analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/). In International workshop on semantic evaluation, pages 19–30. [↗](https://doi.org/10.60692/1cmj7-8b839)
34. Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1(1):81–106. [↗](https://doi.org/10.1007/bf00116251)
35. Ravi, K. and Ravi, V. (2015). A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowledge-based systems, 89:14– 46. [↗](https://doi.org/10.1016/j.knosys.2015.06.015)
36. Rosenthal, S., Farra, N., and Nakov, P. (2017). [Semeval-2017 task 4: Sentiment analysis in twitter](https://md.research.elamur.ai/free/en/papers/rosenthal-2017-semeval-2017-task-4-sentiment/). In Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017), pages 502– 518.
37. Salton, G. and McGill, M. J. (1986). Introduction to modern information retrieval. scikit learn. a). Bernoulli naı̈ve bayes. [https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.BernoulliNB.html](https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.BernoulliNB.html). scikit learn. b). Complement naı̈ve bayes. https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.ComplementNB.html. scikit learn. c). Decision tree. https://scikit-learn.org/stable/modules/ tree.html. scikit learn. d). Linear support vector classification. https://scikit-learn.org/stable/modules/generated/sklearn.svm. LinearSVC.html. scikit learn. e). Logistic regression. https://scikit-learn.org/stable/modules/ generated/sklearn.linear_model. LogisticRegression.html. scikit learn. f). Nu-support support vector classification. https://scikit-learn.org/stable/modules/generated/sklearn. svm.NuSVC.html. scikit learn. g). Random forest. https://scikit-learn.org/stable/modules/ generated/sklearn.ensemble. RandomForestClassifier.html. scikit learn. h). Support vector classification. https://scikit-learn.org/stable/modules/ generated/sklearn.svm.SVC.html. [↗](https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.BernoulliNB.html)
38. Van Hee, C., Lefever, E., and Hoste, V. (2018). [Semeval-2018 task 3: Irony detection in english tweets](https://md.research.elamur.ai/free/en/papers/hee-2018-semeval-2018-task-3-irony/). In Proceedings of The 12th International Workshop on Semantic Evaluation, pages 39–50.
39. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). arXiv preprint arXiv:1706.03762. [↗](https://arxiv.org/abs/1706.03762)
40. Yimam, S. M., Alemayehu, H. M., Ayele, A., and Biemann, C. (2020). [Exploring amharic sentiment analysis from social media texts: Building annotation tools and classification models](https://md.research.elamur.ai/free/en/papers/yimam-2020-exploring-amharic-sentiment-analysis-social/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 1048–1060.
41. Yu, H.-F., Huang, F.-L., and Lin, C.-J. (2011). Dual coordinate descent methods for logistic regression and maximum entropy models. Machine Learning, 85(1-2):41–75. [↗](https://doi.org/10.1007/s10994-010-5221-8)

*Updated 1 November 2026*