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

arXiv: https://arxiv.org/abs/2503.13844 · HTML: https://mlsanity.com/paper/2503.13844/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [Argumentation Mining in User-Generated Web Discourse](https://mlsanity.com/paper/1601.02403/) (2016)
- [Detecting Propaganda Techniques in Memes](https://mlsanity.com/paper/2109.08013/) (2021)
- [Proppy: A System to Unmask Propaganda in Online News](https://mlsanity.com/paper/1912.06810/) (2019)
- [The Spread of Propaganda by Coordinated Communities on Social Media](https://mlsanity.com/paper/2109.13046/) (2021)
- [Pull out all the stops: Textual analysis via punctuation sequences](https://mlsanity.com/paper/1901.00519/) (2018)
- [KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection](https://mlsanity.com/paper/2304.11924/) (2023)
- [Understanding the Complexity of Detecting Political Ads](https://mlsanity.com/paper/2103.00822/) (2021)

## Built on by (most cited first, 1 of 1)

- [BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech](https://mlsanity.com/paper/2610.09464/) (2026)

## Abstract (arXiv)

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.