{"url":"/dataset/diaasq","name":"DiaASQ","full_name":"Conversational Aspect-based Sentiment Quadruple Extraction","description_markdown":"DiaASQ is a fine-grained Aspect-based Sentiment Analysis (ABSA) benchmark under the conversation scenario. It challenges existing ABSA methods by 1) extracting quadruple of target-aspect-opinion-sentiment in a dialogue, and 2) modeling the dialogue discourse structures. The dataset is constructed by systematically crawling tweets from digital bloggers, followed by a series of preprocessing steps including filtering, normalizing, pruning, and annotating the collected dialogues, resulting in a final corpus of 1,000 dialogues. To enhance the multilingual usability, DiaASQ has both the English and Chinese versions of languages.","description_withheld":null,"homepage":"https://diaasq-page.pages.dev/","introduced_date":"2022-11-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/diaasq-a-benchmark-of-conversational-aspect","title":"DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis","first_author":"Bobo Li","url":null},"license":{"name":"MIT license","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Aspect-Based Sentiment Analysis (ABSA)","url":"/task/aspect-based-sentiment-analysis","datasets_with_task":"/datasets/task/aspect-based-sentiment-analysis"},{"name":"Dialogue Understanding","url":"/task/dialogue-understanding","datasets_with_task":"/datasets/task/dialogue-understanding"},{"name":"Aspect-Category-Opinion-Sentiment Quadruple Extraction","url":"/task/aspect-category-opinion-sentiment-quadruple","datasets_with_task":"/datasets/task/aspect-category-opinion-sentiment-quadruple"},{"name":"Conversational Sentiment Quadruple Extraction","url":"/task/conversational-sentiment-quadruple-extraction","datasets_with_task":"/datasets/task/conversational-sentiment-quadruple-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["DiaASQ","DiaASQ (EN)","DiaASQ (ZH)"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/conversational-sentiment-quadruple-extraction","task":"Conversational Sentiment Quadruple Extraction","dataset_variant":"DiaASQ (EN)","rows":1,"metrics":["Pair F1 (aspect-opinion)","Pair F1 (target-aspect)","Pair F1 (target-opinion)","Quad F1 (identification)","Quad F1 (micro)","Span F1 (aspect)","Span F1 (opinion)","Span F1 (target)"],"first_row_in_archive_order":{"model":"E2E-DiaASQ","paper":"/paper/diaasq-a-benchmark-of-conversational-aspect","metrics":{"Pair F1 (aspect-opinion)":"44.27","Pair F1 (target-aspect)":"47.91","Pair F1 (target-opinion)":"45.58","Quad F1 (identification)":"36.80","Quad F1 (micro)":"33.31","Span F1 (aspect)":"74.71","Span F1 (opinion)":"60.22","Span F1 (target)":"88.62"},"code_links":[{"title":"unikcc/diaasq","url":"https://github.com/unikcc/diaasq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/conversational-sentiment-quadruple-extraction-1","task":"Conversational Sentiment Quadruple Extraction","dataset_variant":"DiaASQ (ZH)","rows":1,"metrics":["Pair F1 (aspect-opinion)","Pair F1 (target-aspect)","Pair F1 (target-opinion)","Quad F1 (identification)","Quad F1 (micro)","Span F1 (aspect)","Span F1 (opinion)","Span F1 (target)"],"first_row_in_archive_order":{"model":"E2E-DiaASQ","paper":"/paper/diaasq-a-benchmark-of-conversational-aspect","metrics":{"Pair F1 (aspect-opinion)":"45.44","Pair F1 (target-aspect)":"48.61","Pair F1 (target-opinion)":"43.31","Quad F1 (identification)":"37.51","Quad F1 (micro)":"34.94","Span F1 (aspect)":"76.94","Span F1 (opinion)":"59.35","Span F1 (target)":"90.23"},"code_links":[{"title":"unikcc/diaasq","url":"https://github.com/unikcc/diaasq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/diaasq-a-benchmark-of-conversational-aspect","title":"DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis","date":"2022-11-10","rows_on_this_dataset":2,"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."}