# cantnlp@DravidianLangTech 2026: organic domain adaptation improves multi-class hope speech detection in Tulu Source: [cantnlp@DravidianLangTech 2026: organic domain adaptation improves multi-class hope speech detection in Tulu]() Collection index: [llms.txt]() Data updated: 2026-05-13T05:00:20.520Z Authors: Andrew Li, Sidney Wong Published: 2026-05-10T22:32:36.000Z ## Abstract This paper presents our systems and results for the Hope Speech Detection in Code-Mixed Tulu Language shared task at the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages (DravidianLangTech-2026). We trained an XLM-RoBERTa-based text classification system for detecting hope speech in code-mixed Tulu social media comments. We compared this organically adapted hope speech detection model with our baseline model. On the development set, the organically adapted model outperformed the baseline system. While our submitted systems performed more modestly on the official test set, these results suggest that further adapting XLM-RoBERTa on organically collected Tulu social media text containing code-mixed and mixed-script variation can improve hope speech detection in code-mixed Tulu. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Coarse-Grained Hope Speech Classification on Tulu Hope Speech Detection official (test)](): Coarse-Grained Hope Speech Classification; Tulu Hope Speech Detection official (test); Macro F1-score: 50. - [Fine-Grained Hope Speech Classification on Tulu Hope Speech Detection official (test)](): Fine-Grained Hope Speech Classification; Tulu Hope Speech Detection official (test); Macro F1: 33. ## Original sources and implementation [Original paper]() [PDF]()