Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts

arXiv cs.CL / 4/3/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces a multimodal analysis pipeline for YouTube Shorts that combines automatic transcription, aspect-based sentiment analysis (ABSA), and semantic scene classification.
The pipeline is evaluated for feasibility and then applied to more than 2,300 conflict-related Shorts and 94,000+ visual frames covering the Israel-Hamas war from state-funded broadcasters.
Results show that sentiment in transcripts varies across outlets and changes over time by specific aspects, while scene-type classifications align with visual cues consistent with real-world events.
The study finds that smaller domain-adapted models outperform large transformers and even LLMs for sentiment analysis, highlighting the effectiveness of resource-efficient approaches for humanities research.
The authors present the pipeline as a reusable template for other short-form platforms (e.g., TikTok, Instagram) to study how algorithmic video environments encode sentiment and visual signals.

Abstract

YouTube Shorts have become central to news consumption on the platform, yet research on how geopolitical events are represented in this format remains limited. To address this gap, we present a multimodal pipeline that combines automatic transcription, aspect-based sentiment analysis (ABSA), and semantic scene classification. The pipeline is first assessed for feasibility and then applied to analyze short-form coverage of the Israel-Hamas war by state-funded outlets. Using over 2,300 conflict-related Shorts and more than 94,000 visual frames, we systematically examine war reporting across major international broadcasters. Our findings reveal that the sentiment expressed in transcripts regarding specific aspects differs across outlets and over time, whereas scene-type classifications reflect visual cues consistent with real-world events. Notably, smaller domain-adapted models outperform large transformers and even LLMs for sentiment analysis, underscoring the value of resource-efficient approaches for humanities research. The pipeline serves as a template for other short-form platforms, such as TikTok and Instagram, and demonstrates how multimodal methods, combined with qualitative interpretation, can characterize sentiment patterns and visual cues in algorithmically driven video environments.