Publications
Code · Zenodo · October 21, 2026
Turkish–Kazakh Sentiment Classification: Research Code and Aggregate Results
Abstract
Research code and aggregate results for Turkish–Kazakh sentiment classification. The repository contains the experimental scripts, pinned dataset and model revisions, recorded software dependencies, supplementary methods, and validation tools. The evaluation covers lexical models, frozen multilingual embeddings, fine-tuned XLM-R, and a separate zero-shot Qwen3-8B comparison. Raw review texts, individual predictions, and model weights are not redistributed.
Sentiment Analysis and Opinion MiningTopic ModelingHate Speech and Cyberbullying Detectionsentiment classificationTurkish languageKazakh language
More by İsmail Burak Yavru
- PopRobust: Reproducibility Package for Multi-Protocol Popularity-Robust Recommendation BenchmarkingMendeley Data · 2026
- AARS: Simulation-Budgeted Few-Shot Adaptation of Building Energy Surrogates in Unseen ClimatesZenodo · 2026
- Robust and Explainable Wearable Stress Recognition under Physical Activity ConfoundingInternational Conference on Computer Science and Engineering · 2026
- SUPER: Smart User-Centric Popularity Exposure Reduction for Fair and Diverse RecommendationsIEEE Access · 2026 · Citations: 1
