{"url":"/dataset/mib-datasets","name":"MIB Dataset","full_name":null,"description_markdown":"You need to request access to download and use the dataset.\r\n\r\nIt contains fake and real accounts of Twitter and their follower's/friends' ids (can create a graph based on that).","description_withheld":null,"homepage":"http://mib.projects.iit.cnr.it/dataset.html","introduced_date":"2015-09-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/fame-for-sale-efficient-detection-of-fake","title":"Fame for sale: efficient detection of fake Twitter followers","first_author":"Stefano Cresci","url":null},"license":null,"modalities":[],"tasks":[{"name":"Twitter Bot Detection","url":"/task/twitter-bot-detection","datasets_with_task":"/datasets/task/twitter-bot-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Italian","url":"/datasets/language/italian"}],"variants":["MIB Dataset"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/twitter-bot-detection-on-mib-datasets","task":"Twitter Bot Detection","dataset_variant":"MIB Dataset","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DNA String Compression - Compression Ratio","paper":"/paper/detecting-bot-behaviour-in-social-media-using","metrics":{"Accuracy":"0.984"},"code_links":[{"title":"pasricha/bot-dna-compression","url":"https://github.com/pasricha/bot-dna-compression"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/detecting-bot-behaviour-in-social-media-using","title":"Detecting Bot Behaviour in Social Media using Digital DNA Compression","date":"2019-12-05","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}