Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models

• URL: http://arxiv.org/abs/2604.08566v1
• Date: Wed, 18 Mar 2026 16:19:51 GMT
• Title: Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models
• Abstract summary: This study examines how different artificial intelligence architectures interpret sentiment in conflict-related media discourse.<n> Drawing on a corpus of 10,990 Arabic news headlines (Eleraqi 2026), the research conducts a comparative analysis between three large language models and six fine-tuned Arabic BERT models.<n>The results reveal pronounced and non-random divergence in sentiment distributions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This study examines how different artificial intelligence architectures interpret sentiment in conflict-related media discourse, using the 2023 Gaza War as a case study. Drawing on a corpus of 10,990 Arabic news headlines (Eleraqi 2026), the research conducts a comparative analysis between three large language models and six fine-tuned Arabic BERT models. Rather than evaluating accuracy against a single human-annotated gold standard, the study adopts an epistemological approach that treats sentiment classification as an interpretive act produced by model architectures. To quantify systematic differences across models, the analysis employs information-theoretic and distributional metrics, including Shannon Entropy, Jensen-Shannon Distance, and a Variance Score measuring deviation from aggregate model behavior. The results reveal pronounced and non-random divergence in sentiment distributions. Fine-tuned BERT models, particularly MARBERT, exhibit a strong bias toward neutral classifications, while LLMs consistently amplify negative sentiment, with LLaMA-3.1-8B showing near-total collapse into negativity. Frame-conditioned analysis further demonstrates that GPT-4.1 adjusts sentiment judgments in line with narrative frames (e.g., humanitarian, legal, security), whereas other LLMs display limited contextual modulation. These findings suggest that the choice of model constitutes a choice of interpretive lens, shaping how conflict narratives are algorithmically framed and emotionally evaluated. The study contributes to media studies and computational social science by foregrounding algorithmic discrepancy as an object of analysis and by highlighting the risks of treating automated sentiment outputs as neutral or interchangeable measures of media tone in contexts of war and crisis.

Related papers

• REGARD: Regional Affective Differences in Large Language Models [32.505127447635864]
  We study what drives affective framing differences across LLMs on post-Soviet entities using target-directed Valence-Arousal-Dominance profiling.<n>Post-hoc Ward-linkage clustering of all 19 models by affective and response-behavior profiles yields three behavioral clusters.<n>These findings show that VAD profiling captures emotional intensity, a dimension of affective framing that is largely invisible to conventional sentiment-based evaluation.
  arXiv  Detail & Related papers  (2026-07-22T20:47:57Z)
• To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias [61.40435736418359]
  We introduce a unified framework that standardizes heterogeneous benchmarks to contrast isolated demographic assessments with forced-choice comparative settings.<n>We show that comparative settings act as aggressive catalysts for latent discrimination, a shift primarily driven by underspecified contexts.<n>Finally, we demonstrate that this comparative prejudice is a generalized phenomenon that scales positively with model size.
  arXiv  Detail & Related papers  (2026-06-23T13:53:50Z)
• Approaches to Analysing Historical Newspapers Using LLMs [1.0225484904475783]
  This study presents a computational analysis of the Slovene historical newspapers textitSlovenec and textitSlovenski narod from the sPeriodika corpus.<n>We examine how collective identities, political orientations, and national belonging were represented in public discourse at the turn of the twentieth century.
  arXiv  Detail & Related papers  (2026-03-26T05:38:30Z)
• Explaining News Bias Detection: A Comparative SHAP Analysis of Transformer Model Decision Mechanisms [0.2538209532048867]
  We present a comparative interpretability study of two bias detection models: a bias detector fine-tuned on the BABE dataset and a domain-adapted pre-trained RoBERTa model fine-tuned on the BABE dataset.<n>We analyze word-level attributions across correct and incorrect predictions to characterize how different model architectures operationalize linguistic bias.
  arXiv  Detail & Related papers  (2025-12-29T19:58:11Z)
• Bridging Human and Model Perspectives: A Comparative Analysis of Political Bias Detection in News Media Using Large Language Models [0.3227658251731014]
  This study aims to present a comparative framework for evaluating the detection of political bias across human annotations and multiple language models.<n>We construct a manually annotated dataset of news articles and assess annotation consistency, bias polarity, and inter-model agreement.<n> Experimental results show that among traditional transformer-based models, RoBERTa achieves the highest alignment with human labels.
  arXiv  Detail & Related papers  (2025-11-18T15:58:04Z)
• Geopolitical Parallax: Beyond Walter Lippmann Just After Large Language Models [0.06372261626436676]
  This study investigates geopolitical parallax-systematic divergence in news quality and subjectivity assessments.<n>We compare article-level embeddings from Chinese-origin (Qwen, BGE, Jina) and Western-origin (Snowflake, Granite) model families.<n>Our findings reveal consistent, non-random divergences aligned with model origin.
  arXiv  Detail & Related papers  (2025-08-27T00:39:59Z)
• How Effectively Can BERT Models Interpret Context and Detect Bengali Communal Violent Text? [0.3029213689620348]
  Communal violent text remains an underexplored area in existing research.<n>We introduce a fine-tuned BanglaBERT model tailored for this task, achieving a macro F1 score of 0.60.<n>This ensemble model demonstrated an improved performance, achieving a macro F1 score of 0.63, thus highlighting its effectiveness in this domain.
  arXiv  Detail & Related papers  (2025-06-24T17:48:49Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis [56.84237932819403]
  This paper aims to estimate and mitigate the bad effect of textual modality for strong OOD generalization. Inspired by this, we devise a model-agnostic counterfactual framework for multimodal sentiment analysis.
  arXiv  Detail & Related papers  (2022-07-24T03:57:40Z)
• A comprehensive comparative evaluation and analysis of Distributional Semantic Models [61.41800660636555]
  We perform a comprehensive evaluation of type distributional vectors, either produced by static DSMs or obtained by averaging the contextualized vectors generated by BERT. The results show that the alleged superiority of predict based models is more apparent than real, and surely not ubiquitous. We borrow from cognitive neuroscience the methodology of Representational Similarity Analysis (RSA) to inspect the semantic spaces generated by distributional models.
  arXiv  Detail & Related papers  (2021-05-20T15:18:06Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.