Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies

• URL: http://arxiv.org/abs/2503.13844v2
• Date: Wed, 23 Jul 2025 08:38:14 GMT
• Title: Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies
• Authors: Elyas Meguellati, Stefano Civelli, Pietro Bernardelle, Shazia Sadiq, Irwin King, Gianluca Demartini,
• Abstract summary: We introduce a lightweight model for persuasive text detection that achieves state-of-the-art performance in Subtask 3 of SemEval 2023 Task 3.<n>We demonstrate the model's practical utility by collecting the Australian Federal Election 2022 Facebook Ads dataset.<n>We then apply the fine-tuned model to label the remainder of the APA22 dataset, revealing distinct patterns in how political campaigns leverage persuasion.
• Score: 32.942040379593976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Political advertising plays a pivotal role in shaping public opinion and influencing electoral outcomes, often through subtle persuasive techniques embedded in broader propaganda strategies. Detecting these persuasive elements is crucial for enhancing voter awareness and ensuring transparency in democratic processes. This paper presents an integrated approach that bridges model development and real-world application through two interconnected studies. First, we introduce a lightweight model for persuasive text detection that achieves state-of-the-art performance in Subtask 3 of SemEval 2023 Task 3 while requiring significantly fewer computational resources and training data than existing methods. Second, we demonstrate the model's practical utility by collecting the Australian Federal Election 2022 Facebook Ads (APA22) dataset, partially annotating a subset for persuasion, and fine-tuning the model to adapt from mainstream news to social media content. We then apply the fine-tuned model to label the remainder of the APA22 dataset, revealing distinct patterns in how political campaigns leverage persuasion through different funding strategies, word choices, demographic targeting, and temporal shifts in persuasion intensity as election day approaches. Our findings not only underscore the necessity of domain-specific modeling for analyzing persuasion on social media but also show how uncovering these strategies can enhance transparency, inform voters, and promote accountability in digital campaigns.

Related papers

• Optimizing Influence Campaigns: Nudging under Bounded Confidence [0.0]
  We show that to persuade under bounded confidence, an agent must nudge its targets to gradually shift their opinions. We show how to construct an agent's nudging policy under the bounded confidence opinion dynamics model. We find that our nudging based policies outperform other common techniques that do not consider the bounded confidence effect.
  arXiv  Detail & Related papers  (2025-03-24T04:30:58Z)
• IOHunter: Graph Foundation Model to Uncover Online Information Operations [8.532129691916348]
  We introduce a methodology designed to identify users orchestrating information operations, a.k.a. IO drivers, across various influence campaigns.<n>Our framework, named IOHunter, leverages the combined strengths of Language Models and Graph Neural Networks to improve generalization in supervised, scarcely-supervised, and cross-IO contexts.<n>This research marks a step toward developing Graph Foundation Models specifically tailored for the task of IO detection on social media platforms.
  arXiv  Detail & Related papers  (2024-12-19T09:14:24Z)
• On the Use of Proxies in Political Ad Targeting [49.61009579554272]
  We show that major political advertisers circumvented mitigations by targeting proxy attributes. Our findings have crucial implications for the ongoing discussion on the regulation of political advertising.
  arXiv  Detail & Related papers  (2024-10-18T17:15:13Z)
• PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent [71.20471076045916]
  Propaganda plays a critical role in shaping public opinion and fueling disinformation. Propainsight systematically dissects propaganda into techniques, arousal appeals, and underlying intent. Propagaze combines human-annotated data with high-quality synthetic data.
  arXiv  Detail & Related papers  (2024-09-19T06:28:18Z)
• Representation Bias in Political Sample Simulations with Large Language Models [54.48283690603358]
  This study seeks to identify and quantify biases in simulating political samples with Large Language Models. Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao dataset, and China Family Panel Studies.
  arXiv  Detail & Related papers  (2024-07-16T05:52:26Z)
• P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models [57.571395694391654]
  We find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries. We propose P3SUM, a diffusion model-based summarization approach controlled by political perspective classifiers. Experiments on three news summarization datasets demonstrate that P3SUM outperforms state-of-the-art summarization systems.
  arXiv  Detail & Related papers  (2023-11-16T10:14:28Z)
• Leveraging Large Language Models to Detect Influence Campaigns in Social Media [9.58546889761175]
  Social media influence campaigns pose significant challenges to public discourse and democracy. Traditional detection methods fall short due to the complexity and dynamic nature of social media. We propose a novel detection method using Large Language Models (LLMs) that incorporates both user metadata and network structures.
  arXiv  Detail & Related papers  (2023-11-14T00:25:09Z)
• Embedding Democratic Values into Social Media AIs via Societal Objective Functions [13.903836222333977]
  We introduce a method for translating established, vetted social scientific constructs into AI objective functions. We create a democratic attitude model that estimates the extent to which a social media post promotes anti-democratic attitudes. This method presents a novel strategy to draw on social science theory and methods to mitigate societal harms in social media AIs.
  arXiv  Detail & Related papers  (2023-07-26T02:27:24Z)
• The Face of Populism: Examining Differences in Facial Emotional Expressions of Political Leaders Using Machine Learning [50.24983453990065]
  We use a deep-learning approach to process a sample of 220 YouTube videos of political leaders from 15 different countries. We observe statistically significant differences in the average score of negative emotions between groups of leaders with varying degrees of populist rhetoric.
  arXiv  Detail & Related papers  (2023-04-19T18:32:49Z)
• KHAN: Knowledge-Aware Hierarchical Attention Networks for Accurate Political Stance Prediction [37.261840137596195]
  We propose a novel knowledge-aware approach to political stance prediction (KHAN) We employ (1) hierarchical attention networks (HAN) to learn the relationships among words and sentences in three different levels and (2) knowledge encoding (KE) to incorporate external knowledge for real-world entities into the process of political stance prediction. Through extensive evaluations on three real-world datasets, we demonstrate the superiority of DASH in terms of (1) accuracy, (2) efficiency, and (3) effectiveness.
  arXiv  Detail & Related papers  (2023-02-23T16:09:42Z)
• Weakly Supervised Learning for Analyzing Political Campaigns on Facebook [24.29993132301275]
  We propose a weakly supervised approach to identify the stance and issue of political ads on Facebook. We analyze the temporal dynamics of the political ads on election polls.
  arXiv  Detail & Related papers  (2022-10-19T15:35:37Z)
• Persuasion Strategies in Advertisements [68.70313043201882]
  We introduce an extensive vocabulary of persuasion strategies and build the first ad image corpus annotated with persuasion strategies. We then formulate the task of persuasion strategy prediction with multi-modal learning. We conduct a real-world case study on 1600 advertising campaigns of 30 Fortune-500 companies.
  arXiv  Detail & Related papers  (2022-08-20T07:33:13Z)
• Analyzing Online Political Advertisements [10.386018392170083]
  We present the first computational study on online political ads with the aim to infer the political ideology of an ad sponsor. We develop two new large datasets for the two tasks consisting of ads from the U.S.
  arXiv  Detail & Related papers  (2021-05-09T23:18:37Z)
• Political Posters Identification with Appearance-Text Fusion [49.55696202606098]
  We propose a method that efficiently utilizes appearance features and text vectors to accurately classify political posters. The majority of this work focuses on political posters that are designed to serve as a promotion of a certain political event.
  arXiv  Detail & Related papers  (2020-12-19T16:14:51Z)
• Cross-Domain Learning for Classifying Propaganda in Online Contents [67.10699378370752]
  We present an approach to leverage cross-domain learning, based on labeled documents and sentences from news and tweets, as well as political speeches with a clear difference in their degrees of being propagandistic. Our experiments demonstrate the usefulness of this approach, and identify difficulties and limitations in various configurations of sources and targets for the transfer step.
  arXiv  Detail & Related papers  (2020-11-13T10:19:13Z)
• A Dip Into a Deep Well: Online Political Advertisements, Valence, and European Electoral Campaigning [0.7106986689736826]
  The paper examines online political ads by using a dataset collected from Google's transparency reports. According to the results, most of the political ads have expressed positive sentiments.
  arXiv  Detail & Related papers  (2020-01-28T22:33:45Z)

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.