A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection

• URL: http://arxiv.org/abs/2510.21679v1
• Date: Fri, 24 Oct 2025 17:34:28 GMT
• Title: A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection
• Abstract summary: We introduce a benchmark dataset of expert-annotated video ads from Facebook and YouTube.<n>The dataset provides annotations for 13 framing types for more than 50 companies or advocacy groups across 20 countries.<n>Our dataset contributes to research in multimodal analysis of strategic communication in the energy sector.
• Score: 36.01013743439459
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Companies spend large amounts of money on public relations campaigns to project a positive brand image. However, sometimes there is a mismatch between what they say and what they do. Oil & gas companies, for example, are accused of "greenwashing" with imagery of climate-friendly initiatives. Understanding the framing, and changes in framing, at scale can help better understand the goals and nature of public relations campaigns. To address this, we introduce a benchmark dataset of expert-annotated video ads obtained from Facebook and YouTube. The dataset provides annotations for 13 framing types for more than 50 companies or advocacy groups across 20 countries. Our dataset is especially designed for the evaluation of vision-language models (VLMs), distinguishing it from past text-only framing datasets. Baseline experiments show some promising results, while leaving room for improvement for future work: GPT-4.1 can detect environmental messages with 79% F1 score, while our best model only achieves 46% F1 score on identifying framing around green innovation. We also identify challenges that VLMs must address, such as implicit framing, handling videos of various lengths, or implicit cultural backgrounds. Our dataset contributes to research in multimodal analysis of strategic communication in the energy sector.

Related papers

• A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis [50.35687669938033]
  News outlets shape public opinion at a scale that makes automated detection of political bias and factuality essential.<n>The field still lacks unified resources, comprehensive evaluations across diverse approaches, and systematic analyses of the representations and fusion strategies that matter most.<n>We introduce MBFC-2025, a large-scale label set covering approximately 2,600 outlets from Media Bias/Fact Check (MBFC)<n>We construct multiview representations for ACL-2020, which includes around 900 outlets, as well as for MBFC-2025.
  arXiv  Detail & Related papers  (2026-05-02T09:17:53Z)
• From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media [22.261744577934554]
  We aim to facilitate such research by analysing how computer vision methods can be used for social media discourse analysis.<n>This analysis includes application-based taxonomy design, model selection, prompt engineering, and validation.<n>We benchmark six promptable vision-language models and 15 zero-shot CLIP-like models on two datasets from X (formerly Twitter)
  arXiv  Detail & Related papers  (2026-04-23T15:44:14Z)
• Detecting Basic Values in A Noisy Russian Social Media Text Data: A Multi-Stage Classification Framework [0.0]
  This study presents a multi-stage classification framework for detecting human values in noisy Russian language social media.<n>We use spam and nonpersonal content filtering, targeted selection of value relevant and politically relevant posts, LLM based annotation, and multi-label classification.<n>We show that the model generally aligns with human judgments but systematically overestimates the Openness to Change value domain.
  arXiv  Detail & Related papers  (2026-03-19T12:20:04Z)
• Reference Points in LLM Sentiment Analysis: The Role of Structured Context [0.0]
  This study investigates how supplementary information affect sentiment analysis using large language models (LLMs)<n>We show that structured prompting can enable smaller models to achieve competitive performance.
  arXiv  Detail & Related papers  (2025-08-15T13:04:32Z)
• From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text [26.872469954141067]
  This paper investigates how Vision-Language Models (VLMs) can amplify geo-economic biases when generating chart summaries.<n>We conduct a large-scale evaluation of geo-economic biases in VLM-generated chart summaries across 6,000 chart-country pairs.<n>Our analysis reveals that existing VLMs tend to produce more positive descriptions for high-income countries compared to middle- or low-income countries.
  arXiv  Detail & Related papers  (2025-08-13T03:09:00Z)
• Short-video Propagation Influence Rating: A New Real-world Dataset and A New Large Graph Model [66.8976337702408]
  Cross-platform Short-Video dataset includes 117,720 videos, 381,926 samples, and 535 topics across 5 biggest Chinese platforms.<n>Large Graph Model (LGM) named NetGPT can bridge heterogeneous graph-structured data with the powerful reasoning ability and knowledge of Large Language Models (LLMs)<n>Our NetGPT can comprehend and analyze the short-video propagation graph, enabling it to predict the long-term propagation influence of short-videos.
  arXiv  Detail & Related papers  (2025-03-31T05:53:15Z)
• iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News [25.367927300697424]
  iNews is a novel dataset specifically designed to facilitate the modeling of personalized affective responses to news content.<n>Our dataset comprises annotations from 291 demographically diverse UK participants across 2,899 multimodal Facebook news posts from major UK outlets.
  arXiv  Detail & Related papers  (2025-03-05T10:09:53Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• HOTVCOM: Generating Buzzworthy Comments for Videos [49.39846630199698]
  This study introduces textscHotVCom, the largest Chinese video hot-comment dataset, comprising 94k diverse videos and 137 million comments. We also present the textttComHeat framework, which synergistically integrates visual, auditory, and textual data to generate influential hot-comments on the Chinese video dataset.
  arXiv  Detail & Related papers  (2024-09-23T16:45:13Z)
• Revisiting Few-Shot Object Detection with Vision-Language Models [49.79495118650838]
  We revisit the task of few-shot object detection (FSOD) in the context of recent foundational vision-language models (VLMs) We propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external data. We discuss our recent CVPR 2024 Foundational FSOD competition and share insights from the community.
  arXiv  Detail & Related papers  (2023-12-22T07:42:00Z)
• Multimodal Group Emotion Recognition In-the-wild Using Privacy-Compliant Features [0.0]
  Group-level emotion recognition can be useful in many fields including social robotics, conversational agents, e-coaching and learning analytics. This paper explores privacy-compliant group-level emotion recognition ''in-the-wild'' within the EmotiW Challenge 2023.
  arXiv  Detail & Related papers  (2023-12-06T08:58:11Z)
• Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Models [16.231171704561714]
  This study uses Information Extraction (IE) methods to extract structured insights related to ESG aspects from companies' sustainability reports. We then leverage graph-based representations to conduct statistical analyses concerning the extracted insights.
  arXiv  Detail & Related papers  (2023-10-09T11:34:41Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)

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.