# Detecting Fake News with Weak Social Supervision

arXiv: https://arxiv.org/abs/1910.11430 · HTML: https://mlsanity.com/paper/1910.11430/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities](https://mlsanity.com/paper/2203.13883/) (2022)
- [Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issues](https://mlsanity.com/paper/2211.05289/) (2022)
- [Construction of Large-Scale Misinformation Labeled Datasets from Social Media Discourse using Label Refinement](https://mlsanity.com/paper/2202.12413/) (2022)
- [FR-Detect: A Multi-Modal Framework for Early Fake News Detection on Social Media Using Publishers Features](https://mlsanity.com/paper/2109.04835/) (2021)
- [Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else?](https://mlsanity.com/paper/2111.05139/) (2021)
- [Weakly-supervised Generative Adversarial Networks for medical image classification](https://mlsanity.com/paper/2111.14605/) (2021)

## Abstract (arXiv)

Limited labeled data is becoming the largest bottleneck for supervised learning systems. This is especially the case for many real-world tasks where large scale annotated examples are either too expensive to acquire or unavailable due to privacy or data access constraints. Weak supervision has shown to be a good means to mitigate the scarcity of annotated data by leveraging weak labels or injecting constraints from heuristic rules and/or external knowledge sources. Social media has little labeled data but possesses unique characteristics that make it suitable for generating weak supervision, resulting in a new type of weak supervision, i.e., weak social supervision. In this article, we illustrate how various aspects of social media can be used to generate weak social supervision. Specifically, we use the recent research on fake news detection as the use case, where social engagements are abundant but annotated examples are scarce, to show that weak social supervision is effective when facing the little labeled data problem. This article opens the door for learning with weak social supervision for other emerging tasks.