{"url":"/dataset/news-seo-dataset","name":"News SEO Dataset","full_name":"Detection and Discovery of Misinformation Sources using Attributed Webgraphs","description_markdown":"Search Engine Optimization (SEO) attributes provide strong signals for predicting news site reliability. We introduce a novel attributed webgraph dataset with labeled news domains and their connections to outlinking and backlinking domains. Finally, we introduce and evaluate a novel graph-based algorithm for discovering previously unknown misinformation news sources.\r\n\r\nThis dataset is provided courtesy of Ahrefs.com.","description_withheld":null,"homepage":"https://doi.org/10.1184/R1/25174193.v1","introduced_date":"2024-01-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/detection-and-discovery-of-misinformation","title":"Detection and Discovery of Misinformation Sources using Attributed Webgraphs","first_author":null,"url":null},"license":{"name":"BST-3","url":"https://github.com/CASOS-IDeaS-CMU/Detection-and-Discovery-of-Misinformation-Sources/blob/master/LICENSE"},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Fake News Detection","url":"/task/fake-news-detection","datasets_with_task":"/datasets/task/fake-news-detection"}],"languages":[],"variants":["News SEO Dataset"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}