{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mumin-a-large-scale-multilingual-multimodal","title":"MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset","arxiv_id":"2202.11684","date":"2022-02-23","proceeding":null,"authors":["Dan Saattrup Nielsen","Ryan McConville"],"abstract":"Misinformation is becoming increasingly prevalent on social media and in news articles. It has become so widespread that we require algorithmic assistance utilising machine learning to detect such content. Training these machine learning models require datasets of sufficient scale, diversity and quality. However, datasets in the field of automatic misinformation detection are predominantly monolingual, include a limited amount of modalities and are not of sufficient scale and quality. Addressing this, we develop a data collection and linking system (MuMiN-trawl), to build a public misinformation graph dataset (MuMiN), containing rich social media data (tweets, replies, users, images, articles, hashtags) spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade. The dataset is made available as a heterogeneous graph via a Python package (mumin). We provide baseline results for two node classification tasks related to the veracity of a claim involving social media, and demonstrate that these are challenging tasks, with the highest macro-average F1-score being 62.55% and 61.45% for the two tasks, respectively. The MuMiN ecosystem is available at https://mumin-dataset.github.io/, including the data, documentation, tutorials and leaderboards.","url_abs":"https://arxiv.org/abs/2202.11684v2","url_pdf":"https://arxiv.org/pdf/2202.11684v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mumin-a-large-scale-multilingual-multimodal","repo_url":"https://github.com/MuMiN-dataset/mumin-build","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mumin-a-large-scale-multilingual-multimodal","repo_url":"https://github.com/MuMiN-dataset/mumin-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mumin-a-large-scale-multilingual-multimodal","repo_url":"https://github.com/MuMiN-dataset/mumin-trawl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"misinformation","task_name":"Misinformation"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[{"slug":"mumin","name":"MuMiN","full_name":""},{"slug":"mumin-large","name":"MuMiN-large","full_name":""},{"slug":"mumin-medium","name":"MuMiN-medium","full_name":""},{"slug":"mumin-small","name":"MuMiN-small","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-mumin-large","task":"Node Classification","dataset":"MuMiN-large","model":"HeteroGraphSAGE","rank_in_archive_order":1,"of":4,"metrics":{"Claim Classification Macro-F1":"0.5980","Tweet Classification Macro-F1":"0.6145"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-large","task":"Node Classification","dataset":"MuMiN-large","model":"LaBSE","rank_in_archive_order":2,"of":4,"metrics":{"Claim Classification Macro-F1":"0.5790","Tweet Classification Macro-F1":"0.5280"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-large","task":"Node Classification","dataset":"MuMiN-large","model":"Majority class","rank_in_archive_order":3,"of":4,"metrics":{"Claim Classification Macro-F1":"0.4813","Tweet Classification Macro-F1":"0.4887"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-large","task":"Node Classification","dataset":"MuMiN-large","model":"Random","rank_in_archive_order":4,"of":4,"metrics":{"Claim Classification Macro-F1":"0.3879","Tweet Classification Macro-F1":"0.3690"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-medium","task":"Node Classification","dataset":"MuMiN-medium","model":"HeteroGraphSAGE","rank_in_archive_order":1,"of":4,"metrics":{"Claim Classification Macro-F1":"0.5770","Tweet Classification Macro-F1":"0.5410"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-medium","task":"Node Classification","dataset":"MuMiN-medium","model":"LaBSE","rank_in_archive_order":2,"of":4,"metrics":{"Claim Classification Macro-F1":"0.5585","Tweet Classification Macro-F1":"0.5745"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-medium","task":"Node Classification","dataset":"MuMiN-medium","model":"Majority class","rank_in_archive_order":3,"of":4,"metrics":{"Claim Classification Macro-F1":"0.4806","Tweet Classification Macro-F1":"0.4856"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-medium","task":"Node Classification","dataset":"MuMiN-medium","model":"Random","rank_in_archive_order":4,"of":4,"metrics":{"Claim Classification Macro-F1":"0.3896","Tweet Classification Macro-F1":"0.3772"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-small","task":"Node Classification","dataset":"MuMiN-small","model":"LaBSE","rank_in_archive_order":1,"of":4,"metrics":{"Claim Classification Macro-F1":"0.6255","Tweet Classification Macro-F1":"0.5450"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-small","task":"Node Classification","dataset":"MuMiN-small","model":"HeteroGraphSAGE","rank_in_archive_order":2,"of":4,"metrics":{"Claim Classification Macro-F1":"0.5795","Tweet Classification Macro-F1":"0.5605"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-small","task":"Node Classification","dataset":"MuMiN-small","model":"Majority class","rank_in_archive_order":3,"of":4,"metrics":{"Claim Classification Macro-F1":"0.4756","Tweet Classification Macro-F1":"0.4877"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mumin-small","task":"Node Classification","dataset":"MuMiN-small","model":"Random","rank_in_archive_order":4,"of":4,"metrics":{"Claim Classification Macro-F1":"0.4007","Tweet Classification Macro-F1":"0.3718"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.11684","atlas_url":"https://app.syntology.ai/?focus=2202.11684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.11684"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MuMiN-dataset/mumin-trawl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MuMiN-dataset/mumin-baseline","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MuMiN-dataset/mumin-build","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"23d05019b7c0921e","entry":"build_dgl_dataset","repo":"MuMiN-dataset/mumin-build","repo_kind":"official","path":"src/mumin/dgl.py","file_url":"https://github.com/MuMiN-dataset/mumin-build/blob/HEAD/src/mumin/dgl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23d05019b7c0921e"}},{"code_sha256_prefix":"fbde87e7db148788","entry":"load_dgl_graph","repo":"MuMiN-dataset/mumin-build","repo_kind":"official","path":"src/mumin/dgl.py","file_url":"https://github.com/MuMiN-dataset/mumin-build/blob/HEAD/src/mumin/dgl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbde87e7db148788"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}