{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/hopeedi","name":"HopeEDI","full_name":"HopeEDI: A Multilingual Hope Speech Detection Dataset for Equality, Diversity, and Inclusion","description_markdown":"Over the past few years, systems have been developed to control online content and eliminate abusive, offensive or hate speech content. However, people in power sometimes misuse this form of censorship to obstruct the democratic right of freedom of speech. Therefore, it is imperative that research should take a positive reinforcement approach towards online content that is encouraging, positive and supportive contents. Until now, most studies have focused on solving this problem of negativity in the English language, though the problem is much more than just harmful content. Furthermore, it is multilingual as well. Thus, we have constructed a Hope Speech dataset for Equality, Diversity and Inclusion (HopeEDI) containing user-generated comments from the social media platform YouTube with 28,451, 20,198 and 10,705 comments in English, Tamil and Malayalam, respectively, manually labelled as containing hope speech or not. To our knowledge, this is the first research of its kind to annotate hope speech for equality, diversity and inclusion in a multilingual setting. We determined that the inter-annotator agreement of our dataset using Krippendorff’s alpha. Further, we created several baselines to benchmark the resulting dataset and the results have been expressed using precision, recall and F1-score. The dataset is publicly available for the research community. We hope that this resource will spur further research on encouraging inclusive and responsive speech that reinforces positiveness.","description_withheld":null,"homepage":"https://competitions.codalab.org/competitions/27653#participate-get-data","introduced_date":"2020-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/hopeedi-a-multilingual-hope-speech-detection","title":"HopeEDI: A Multilingual Hope Speech Detection Dataset for Equality, Diversity, and Inclusion","first_author":"Bharathi Raja Chakravarthi","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Hope Speech Detection","url":"/task/hope-speech-detection","datasets_with_task":"/datasets/task/hope-speech-detection"},{"name":"Hope Speech Detection for English","url":"/task/hope-speech-detection-for-english","datasets_with_task":"/datasets/task/hope-speech-detection-for-english"},{"name":"Hope Speech Detection for Tamil","url":"/task/hope-speech-detection-for-tamil","datasets_with_task":"/datasets/task/hope-speech-detection-for-tamil"},{"name":"Hope Speech Detection for Malayalam","url":"/task/hope-speech-detection-for-malayalam","datasets_with_task":"/datasets/task/hope-speech-detection-for-malayalam"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Malayalam","url":"/datasets/language/malayalam"}],"variants":["HopeEDI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dravidianlangtech/hope_edi","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hope_edi","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hope-speech-detection-for-english-on-hopeedi","task":"Hope Speech Detection for English","dataset_variant":"HopeEDI","rows":2,"metrics":["Weighted Average F1-score"],"first_row_in_archive_order":{"model":"RoBERTa","paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","metrics":{"Weighted Average F1-score":"0.93"},"code_links":[{"title":"SoLID-UNCC/TeamUNCC-HopeSpeech","url":"https://github.com/SoLID-UNCC/TeamUNCC-HopeSpeech"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/hope-speech-detection-for-malayalam-on","task":"Hope Speech Detection for Malayalam","dataset_variant":"HopeEDI","rows":2,"metrics":["Weighted Average F1-score"],"first_row_in_archive_order":{"model":"XLM-RoBERTa","paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","metrics":{"Weighted Average F1-score":"0.87"},"code_links":[{"title":"SoLID-UNCC/TeamUNCC-HopeSpeech","url":"https://github.com/SoLID-UNCC/TeamUNCC-HopeSpeech"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/hope-speech-detection-for-tamil-on-hopeedi","task":"Hope Speech Detection for Tamil","dataset_variant":"HopeEDI","rows":2,"metrics":["Weighted Average F1-score"],"first_row_in_archive_order":{"model":"XLM-RoBERTa","paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","metrics":{"Weighted Average F1-score":"0.60"},"code_links":[{"title":"SoLID-UNCC/TeamUNCC-HopeSpeech","url":"https://github.com/SoLID-UNCC/TeamUNCC-HopeSpeech"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/hope-speech-detection-on-hopeedi","task":"Hope Speech Detection","dataset_variant":"HopeEDI","rows":2,"metrics":["Weighted Average F1-score"],"first_row_in_archive_order":{"model":"RoBERTa","paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","metrics":{"Weighted Average F1-score":"0.93"},"code_links":[{"title":"SoLID-UNCC/TeamUNCC-HopeSpeech","url":"https://github.com/SoLID-UNCC/TeamUNCC-HopeSpeech"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","slug":"teamuncc-lt-edi-eacl2021-hope-speech","title":"TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers","date":"2021-04-19","arxiv_id":null,"rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/hopeedi-a-multilingual-hope-speech-detection","slug":"hopeedi-a-multilingual-hope-speech-detection","title":"HopeEDI: A Multilingual Hope Speech Detection Dataset for Equality, Diversity, and Inclusion","date":"2020-12-01","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","slug":"teamuncc-lt-edi-eacl2021-hope-speech","title":"TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers","date":"2021-04-19","arxiv_id":null,"rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/hopeedi-a-multilingual-hope-speech-detection","slug":"hopeedi-a-multilingual-hope-speech-detection","title":"HopeEDI: A Multilingual Hope Speech Detection Dataset for Equality, Diversity, and Inclusion","date":"2020-12-01","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"0051376602c727acac3cdaf3ac6e55780532798108b1b9381af178cf1166178a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}