{"url":"/dataset/weibo-douban","name":"Weibo-Douban","full_name":"WD","description_markdown":"This dataset is used for user identity linkage across two online social networks in Chinese. It contains two popular Chinese social platforms: Sina Weibo\\footnote{https://weibo.com} and Douban\\footnote{https://www.douban.com}. \n\nDetails:\n* 9,714 users and 117,218 relations in Weibo; 9,526 users and 120,245 relations in Douban; 1,397 pair of matched users.\n* Approximate power-law degree distribution and high aggregation coefficient.\n* Multiple text attributes available, including username, geographical location and recent (text) posts of the users.\n* Construction time: April 2020.","description_withheld":null,"homepage":"https://github.com/ChenBaiyang/MAUIL","introduced_date":"2020-12-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/mauil-multi-level-attribute-embedding-for","title":"MAUIL: Multi-level Attribute Embedding for Semi-supervised User Identity Linkage","first_author":null,"url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Entity Alignment","url":"/task/entity-alignment","datasets_with_task":"/datasets/task/entity-alignment"},{"name":"Entity Resolution","url":"/task/entity-resolution","datasets_with_task":"/datasets/task/entity-resolution"},{"name":"Anchor link prediction","url":"/task/anchor-link-prediction","datasets_with_task":"/datasets/task/anchor-link-prediction"},{"name":"Record linking","url":"/task/record-linking","datasets_with_task":"/datasets/task/record-linking"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Weibo-Douban"],"data_loaders":[],"num_papers_in_archive":1,"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."}