# Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News

arXiv: https://arxiv.org/abs/2004.01732 · HTML: https://mlsanity.com/paper/2004.01732/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 24 of 24)

- [WRENCH: A Comprehensive Benchmark for Weak Supervision](https://mlsanity.com/paper/2109.11377/) (2021)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Multimodal Fake News Detection via CLIP-Guided Learning](https://mlsanity.com/paper/2205.14304/) (2022)
- [The Surprising Performance of Simple Baselines for Misinformation Detection](https://mlsanity.com/paper/2104.06952/) (2021)
- [Bootstrapping Multi-view Representations for Fake News Detection](https://mlsanity.com/paper/2206.05741/) (2022)
- [Explainable Tsetlin Machine framework for fake news detection with credibility score assessment](https://mlsanity.com/paper/2105.09114/) (2021)
- [Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models](https://mlsanity.com/paper/2405.16631/) (2024)
- [Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities](https://mlsanity.com/paper/2203.13883/) (2022)
- [PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners](https://mlsanity.com/paper/2205.09229/) (2022)
- [Combining exogenous and endogenous signals with a semi-supervised co-attention network for early detection of COVID-19 fake tweets](https://mlsanity.com/paper/2104.05321/) (2021)
- [MisRoBAERTa: Transformers versus Misinformation](https://mlsanity.com/paper/2304.07759/) (2023)
- [Towards Detecting Harmful Agendas in News Articles](https://mlsanity.com/paper/2302.00102/) (2023)
- [Unsupervised Domain-agnostic Fake News Detection using Multi-modal Weak Signals](https://mlsanity.com/paper/2305.11349/) (2023)
- [Search, Examine and Early-Termination: Fake News Detection with Annotation-Free Evidences](https://mlsanity.com/paper/2407.07931/) (2024)
- [Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph Inference](https://mlsanity.com/paper/2512.01728/) (2025)
- [Binary Classification with Positive Labeling Sources](https://mlsanity.com/paper/2208.01704/) (2022)
- [CroMe: Multimodal Fake News Detection using Cross-Modal Tri-Transformer and Metric Learning](https://mlsanity.com/paper/2501.12422/) (2025)
- [Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection](https://mlsanity.com/paper/2509.01660/) (2025)
- [WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding](https://mlsanity.com/paper/2108.12603/) (2021)
- [ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision](https://mlsanity.com/paper/2204.06863/) (2022)
- [Time-Aware Datasets are Adaptive Knowledgebases for the New Normal](https://mlsanity.com/paper/2211.12508/) (2022)
- [ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information](https://mlsanity.com/paper/2101.05499/) (2021)
- [MetaXT: Meta Cross-Task Transfer between Disparate Label Spaces](https://mlsanity.com/paper/2109.04240/) (2021)
- [Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification](https://mlsanity.com/paper/2409.17474/) (2024)

## Abstract (arXiv)

Social media has greatly enabled people to participate in online activities at an unprecedented rate. However, this unrestricted access also exacerbates the spread of misinformation and fake news online which might cause confusion and chaos unless being detected early for its mitigation. Given the rapidly evolving nature of news events and the limited amount of annotated data, state-of-the-art systems on fake news detection face challenges due to the lack of large numbers of annotated training instances that are hard to come by for early detection. In this work, we exploit multiple weak signals from different sources given by user and content engagements (referred to as weak social supervision), and their complementary utilities to detect fake news. We jointly leverage the limited amount of clean data along with weak signals from social engagements to train deep neural networks in a meta-learning framework to estimate the quality of different weak instances. Experiments on realworld datasets demonstrate that the proposed framework outperforms state-of-the-art baselines for early detection of fake news without using any user engagements at prediction time.