{"url":"/dataset/bn-authprof","name":"BN-AuthProf","full_name":"Bangla Author Profiling Dataset","description_markdown":"Although research on author profiling has quite progressed in abundant resources languages, it is still infancy for limited resources languages such as Bengali. This repository contains our Bangla Author Profiling Dataset (BN-AuthProf). The primary objective is to introduce and benchmark the performance of machine learning approaches on Age and Gender Classification tasks from the social media status of people. \r\n\r\nBN-AuthProf dataset consists of 300 anonymized authors and 30,131 manually curated Facebook posts in Bangla, tagged with age and gender information.","description_withheld":null,"homepage":"https://github.com/crusnic-corp/BN-AuthProf","introduced_date":"2024-04-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/bn-authprof-benchmarking-machine-learning-for","title":"BN-AuthProf: Benchmarking Machine Learning for Bangla Author Profiling on Social Media Texts","first_author":"Raisa Tasnim","url":null},"license":{"name":"MIT","url":"https://github.com/crusnic-corp/BN-AuthProf?tab=MIT-1-ov-file#readme"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Age And Gender Classification","url":"/task/age-and-gender-classification","datasets_with_task":"/datasets/task/age-and-gender-classification"},{"name":"Gender Prediction","url":"/task/gender-prediction","datasets_with_task":"/datasets/task/gender-prediction"},{"name":"Age and Gender Estimation","url":"/task/age-and-gender-estimation","datasets_with_task":"/datasets/task/age-and-gender-estimation"},{"name":"Gender Classification","url":"/task/gender-classification","datasets_with_task":"/datasets/task/gender-classification"},{"name":"Author Attribution","url":"/task/author-attribution","datasets_with_task":"/datasets/task/author-attribution"},{"name":"Authorship Attribution","url":"/task/authorship-attribution","datasets_with_task":"/datasets/task/authorship-attribution"},{"name":"Author Profiling","url":"/task/author-profiling","datasets_with_task":"/datasets/task/author-profiling"}],"languages":[{"name":"Bengali","url":"/datasets/language/bengali"}],"variants":["BN-AuthProf"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/age-and-gender-classification-on-bn-authprof","task":"Age And Gender Classification","dataset_variant":"BN-AuthProf","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"Multinomial Naive Bayes (MNB)","paper":"/paper/bn-authprof-benchmarking-machine-learning-for","metrics":{"F1 score":"0.905"},"code_links":[{"title":"crusnic-corp/BN-AuthProf","url":"https://github.com/crusnic-corp/BN-AuthProf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/bn-authprof-benchmarking-machine-learning-for","title":"BN-AuthProf: Benchmarking Machine Learning for Bangla Author Profiling on Social Media Texts","date":"2024-12-03","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."}