{"url":"/dataset/shortpersianemo","name":"ShortPersianEmo","full_name":null,"description_markdown":"ShortPersianEmo is a new data set for emotion recognition in Persian short texts. The ShortPersianEmo dataset is a single-label dataset that contains 5472 short Persian texts collected from Twitter and Digikala. Our dataset is annotated according to Rachael Jack’s emotional model in five emotional classes happiness, sadness, anger, fear, and other. Unlike publicly accessible datasets that do not impose any restrictions on text length, ShortPersianEmo specifically focuses on short texts. The average text length in the ShortPersianEmo dataset is 56 words. Table 1 presents a comparison between the introduced ShortPersianEmo dataset and other datasets from the literature for emotion detection in Persian text. For more information on this dataset please read our paper. If you use this dataset in any research work, please cite our paper.","description_withheld":null,"homepage":"https://github.com/vkiani/ShortPersianEmo","introduced_date":"2023-12-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/investigating-shallow-and-deep-learning","title":"Investigating Shallow and Deep Learning Techniques for Emotion Classification in Short Persian Texts","first_author":"Mahdi Rasouli","url":null},"license":{"name":"GNU GENERAL PUBLIC LICENSE 3","url":"https://github.com/vkiani/ShortPersianEmo/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Emotion Classification","url":"/task/emotion-classification","datasets_with_task":"/datasets/task/emotion-classification"}],"languages":[{"name":"Persian","url":"/datasets/language/persian"},{"name":"Iranian Persian","url":"/datasets/language/iranian-persian"}],"variants":["ShortPersianEmo"],"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/emotion-classification-on-shortpersianemo","task":"Emotion Classification","dataset_variant":"ShortPersianEmo","rows":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"Deep ParsBERT","paper":"/paper/investigating-shallow-and-deep-learning","metrics":{"Macro F1":"0.71"},"code_links":[{"title":"vkiani/ShortPersianEmo","url":"https://github.com/vkiani/ShortPersianEmo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/investigating-shallow-and-deep-learning","title":"Investigating Shallow and Deep Learning Techniques for Emotion Classification in Short Persian Texts","date":"2023-12-16","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."}