Year: 2026
Type: conference-paper
Abstract: We present, to our knowledge, the first systematic transformer-based outlet-ideology classification study for Turkish news.Using a topic-balanced corpus of Turkish political articles drawn from six outlets commonly perceived as left-, centre-, or right-leaning, we formulate a three-way outlet-ideology classification task.On this dataset, we evaluate a monolingual encoder (BERTurk), two multilingual encoders (mBERT, XLM-R), and a LoRAadapted decoder model (Mistral).BERTurk achieves the best performance among individual models (70% accuracy, 71% macro-F1), reaching levels comparable to Englishlanguage studies despite operating in a lowerresource setting.Error analyses show that all encoders reliably distinguish centrist from partisan articles, but frequently confuse left-and right-leaning articles with each other.Moreover, BERTurk is relatively stronger on rightleaning content, whereas the multilingual models favour left-leaning content, suggesting an "ideological fingerprint" of their pre-training data.Crucially, models fine-tuned on an English political-bias task fail to transfer to Turkish, collapsing to near-chance performance.Taken together, these results demonstrate that effective political bias detection requires targetlanguage supervision and cannot be achieved through naïve cross-lingual transfer.Our work establishes a first baseline for Turkish political bias detection and underscores the need for open, carefully designed Turkish (and broader Turkic) bias benchmarks to support robust and fair media analysis.
Authors: Umut Ozbagriacik, Haim Dubossarsky
Institution: Queen Mary University of London
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140078603