Fake news, especially on social media, is now viewed as one of the main digital threats to democracy, journalism, and freedom of expression. Our economies are not immune to the spread of fake news either, with fake news being connected to stock market fluctuations and massive trades. The goal of this special issue is to promote exchange of research and studies that (1) aim to understand and characterize fake news and its patterns and how it can be differentiated from other similar concepts such as false/satire news, misinformation, disinformation, among others, which helps deepen our understanding of fake news; and (2) systematically detect fake news by determining its credibility, verifying its facts, assessing its style, or determining its propagation. To facilitate further research in fake news, this special issue especially welcomes research articles, new open access datasets, repositories, and benchmarks for fake news research, broadening research on fake news detection and its development.
Our guest editors for the issue are:
- Reza Zafarani, Syracuse University
- Huan Liu, Arizona State University
- Vir V. Phoha, Syracuse University
- Javad Azimi, Facebook
Topics of interest for the issue include:
- Patterns of Fake News
- Internet measurements on Fake News
- User behavior analysis with respect to Fake News
- Patterns of Fake News Distribution/Consumption/Response
- Tracing and characterizing the propagation of fake news and true news
- Fake News Detection
- Supervised Fake News Detection
- Semi-Supervised Fake News Detection
- Unsupervised Fake News Detection
- Early Detection of Fake News
- Deep Nets for Fake News Detection
- Representation for Fake News
- Supervised Fake News Detection
- Mining of News Content
- Text Mining of News Content
- Analysis of Images, Videos, and Audio
- Text Mining of News Content
- Fake Checking
- Knowledge-based (e.g., Knowledge-graphs) analysis
- Analyzing News Credibility/Credibility Assessment
- Analyzing Source Credibility
- Malicious Entity Detection
- Fake News Benchmarks
- Fake News Datasets
- Fake News Open Repositories
We welcome two types of research contributions:
- Research manuscripts reporting novel methodologies and results (up to 25 pages)
- Benchmark, Datasets, Repositories, and Demonstration Systems that enable further research and facilitate research on fake news.These papers should be of interest to the broad fake news research community(10pages + links to such systems)
Visit https://dtrap.acm.org/ to submit your manuscript and for important dates and deadlines.