德國政治文本的意識形態預測

摘要

選舉是國家持續發展中的關鍵里程碑。為更深入理解從左翼到右翼各類運動的政治論述，我們提出一個以Transformer為基礎的模型，能將文本的政治傾向投射至連續的左右政治光譜上，並以介於-1與1之間的標準化標量d表示。此方法使分析者可聚焦於政治光譜中的特定區段——例如保守派——同時排除自由派與極右翼運動。唯有透過多類別分類器方能達成此任務，前提是目標傾向需被涵蓋於其預設類別之一。為從13個候選Transformer中選出最適合此任務的基礎模型，我們建構了四組獨特語料庫：其一包含德國聯邦議院附註的議事記錄；其二基於官方線上決策工具Wahl-O-Mat；其三收錄33家標明政治傾向報紙之文章；其四則納入第20與21屆德國聯邦議院597位議員的535,200則推文。為避免過度擬合，我們分別以兩組語料庫進行訓練、兩組進行測試。在領域內表現上，DeBERTa-large取得最高F1分數0.844，而在X（Twitter）的領域外測試中亦達ACC=0.864。至於報紙領域外測試，Gemma2-2B則表現最佳（MAE=0.172）。本研究證明Transformer模型能達到與民意調查相當之德國新聞政治框架辨識水準。我們的研究發現指出：模型架構與領域特定訓練資料的可得性，在評估政治偏誤時可能與模型規模同等重要。我們亦探討方法論限制，並提出強化偏誤測量穩健性的方向。

English

Elections represent a crucial milestone in a nation's ongoing development. To better understand the political rhetoric from various movements, ranging from left to right, we propose a transformer-based model capable of projecting the political orientation of a text on a continuous left-to-right spectrum, represented by a normalized scalar d between -1 and 1. This approach enables analysts to focus on specific segments of the political landscape, such as conservatives, while excluding liberal and far-right movements. Such a task can only be achieved with multiclass classifiers, provided that the desired orientation is incorporated within one of their predefined classes. To determine the most suitable foundation model among 13 candidate transformers for this task, we constructed four distinct corpora. One corpus comprised annotated plenary notes from the German Bundestag, while another was based on an official online decision-making tool, Wahl-O-Mat. The third corpus consisted of articles from 33 newspapers, each identified by its political orientation, and the fourth included 535,200 tweets from 597 members of the 20th and 21st German Bundestag. To mitigate overfitting, we used two distinct corpora for training and two for testing, respectively. For in-domain performance, DeBERTa-large achieved the highest F1 score F1=0.844 as well as for the X (Twitter) out-of-domain test ACC=0.864. Regarding the newspaper out-of-domain test, Gemma2-2B excelled (MAE = 0.172). This study demonstrates that transformer models can recognize political framing in German news at the level of public opinion polls. Our findings suggest that both the model architecture and the availability of domain-specific training data can be as influential as model size for estimating political bias. We discuss methodological limitations and outline directions for improving the robustness of bias measurement.