--- title: "Lannisters@DravidianLangTech 2026 — paper by S et al. (2026)" description: "The work still offers a reproducible baseline for gender-targeted abuse detection in a low-resource language. 4 references." authors: ["Kalaivani K S", "Jaisanth K", "Nandhini B"] year: 2026 venue: "Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages" source: "https://aclanthology.org/2026.dravidianlangtech-1.44/" doi: "10.18653/v1/2026.dravidianlangtech-1.44" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/s-2026-lannisters-dravidianlangtech-2026-comparative-ablation/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/s-2026-lannisters-dravidianlangtech-2026-comparative-ablation/) [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/34/) / Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms # Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms **Authors:** Kalaivani K S, Jaisanth K and Nandhini B · **Year:** 2026 · **Venue:** [Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages](https://md.research.elamur.ai/free/en/venues/dravidianlangtech/) ([Workshop on Speech, Vision, and Language Technologies for Dravidian Languages 2026](https://md.research.elamur.ai/free/en/venues/dravidianlangtech/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.dravidianlangtech-1.44/) · [PDF](https://aclanthology.org/2026.dravidianlangtech-1.44.pdf) · [DOI 10.18653/v1/2026.dravidianlangtech-1.44](https://doi.org/10.18653/v1/2026.dravidianlangtech-1.44) · [OpenAlex](https://openalex.org/W7166807299) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary The paper addresses automatic detection of abusive comments aimed at women on Tamil social media. Noisy spelling, dialect variation, code-mixing, and sarcastic or indirect phrasing make keyword or rule-based filtering impractical there. Built for the DravidianLangTech 2026 shared task, the system treats the problem as binary classification (Abusive vs. Non-Abusive). The authors clean the text with a dedicated pipeline. It decodes HTML, normalizes Unicode, strips URLs and mentions, keeps hashtags and emojis, and maps obfuscated slurs to a placeholder. They then enlarge the minority Abusive class with random deletion, word swapping and back-translation via English. DistilBERT, mBERT and XLM-RoBERTa are fine-tuned under identical settings. XLM-RoBERTa performs best, reaching 91.17% validation accuracy and 0.8865 macro F1. An ablation suggests that preprocessing, augmentation and tuning each improve results. Remaining errors concentrate on sarcasm, implicit abuse and dialectal or Tamil-English mixed comments. All scores come from a local split created after augmentation, and no official test result is reported, so the numbers may be optimistic. The work still offers a reproducible baseline for gender-targeted abuse detection in a low-resource language. ## Key points - Data: 3,652 training and 913 test Tamil comments. Augmenting the Abusive class raised the total to 7,190, split 80:20 into 5,752 training and 1,438 validation instances. - Validation accuracy by model: DistilBERT 87.4%, mBERT 89.2%, XLM-RoBERTa 91.17%. XLM-RoBERTa also scored weighted F1 0.9119 and macro F1 0.8865. - XLM-RoBERTa setup: - 6 epochs, learning rate 2e-5, batch size 16, weight decay 0.01, label smoothing 0.1. - Maximum sequence length 256, dropout 0.1. - Class-weighted cross-entropy and early stopping on macro F1. - Retrained on all data before final predictions, using a Tesla T4 GPU. - Ablation (accuracy / macro F1): - Base model: 0.78 / 0.78 - With preprocessing: 0.88 / 0.85 - Adding augmentation: 0.92 / 0.89 - Adding tuning: 0.93 / 0.91 The final 0.91 does not match the 0.8865 reported elsewhere. The per-class F1 values (Abusive 0.94, Non-Abusive 0.83) also look odd given that Non-Abusive is the majority class. - Code is available at github.com/Nandhinibalu05/SocialMediaTamilAbuse. The authors acknowledge limitations: a small dataset, limited variety in the augmented data, and difficulty with sarcasm and bias. *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 (4): [🖥️ 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 · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 306 works 🧭 Topics (1): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works ## Cite Cite as: Kalaivani K S, Jaisanth K and Nandhini B. 2026. Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms. Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{s2026lannisters, title = {{Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms}}, author = {Kalaivani K S, Jaisanth K and Nandhini B}, booktitle = {Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages}, year = {2026}, doi = {10.18653/v1/2026.dravidianlangtech-1.44}, url = {https://doi.org/10.18653/v1/2026.dravidianlangtech-1.44} } ``` - [← previous Language-Specific versus Cross-Lingual Knowledge Graphs for Implicit Aspect Identification in Arabic: A Comparative Study of Reasoning and Adaptation Strategies](https://md.research.elamur.ai/free/en/papers/alawwad-2026-language-specific-versus-cross-lingual/) - [next → LARA: LLM-based Agile Power Distribution Network Restoration from Disastrous Events](https://md.research.elamur.ai/free/en/papers/warrier-2026-lara-llm-based-agile-power/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/) ## References 4 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Bharathi Raja Chakravarthi, Ruba Priyadharshini, Navya Jose, Anand Kumar M, Thomas Mandl, Prasanna Kumar Kumaresan, Rahul Ponnusamy, Hariharan R L, John Philip McCrae, and Elizabeth Sherly. 2021. [Findings of the shared task on offensive language identification in tamil, malayalam, and kannada](https://md.research.elamur.ai/free/en/papers/chakravarthi-2021-findings-shared-task-offensive-language/). In Pr… 2. Ziqi Zhang, David Robinson, and Jonathan Tepper. 2022. Hate speech detection: A literature review. ACM Computing Surveys, 54(5). [find](https://scholar.google.com/scholar?q=Ziqi+Zhang%2C+David+Robinson%2C+and+Jonathan+Tepper%2E+2022%2E+Hate+speech+detection%3A+A+literature+review%2E+ACM+Computing+Surveys%2C+54%285%29%2E) 3. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, and Vishrav Chaudhary. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Kartikay+Khandelwal%2C+Naman+Goyal%2C+and+Vishrav+Chaudhary%2E+2020%2E+Unsupervised+cross%2Dlingual+representation+learning+at+scale%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association) 4. Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. [Automated hate speech detection and the problem of offensive language](https://md.research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/). In Proceedings of ICWSM. *Updated 1 November 2026*