{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/n15news-a-new-dataset-for-multimodal-news","title":"N24News: A New Dataset for Multimodal News Classification","arxiv_id":"2108.13327","date":"2021-08-30","proceeding":"LREC 2022 6","authors":["Zhen Wang","Xu Shan","Xiangxie Zhang","Jie Yang"],"abstract":"Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification. In this paper, we propose a new dataset, N24News, which is generated from New York Times with 24 categories and contains both text and image information in each news. We use a multitask multimodal method and the experimental results show multimodal news classification performs better than text-only news classification. Depending on the length of the text, the classification accuracy can be increased by up to 8.11%. Our research reveals the relationship between the performance of a multimodal classifier and its sub-classifiers, and also the possible improvements when applying multimodal in news classification. N24News is shown to have great potential to prompt the multimodal news studies.","url_abs":"https://arxiv.org/abs/2108.13327v4","url_pdf":"https://arxiv.org/pdf/2108.13327v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"n15news-a-new-dataset-for-multimodal-news","repo_url":"https://github.com/billywzh717/n24news","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"news-classification","task_name":"News Classification"}],"methods":[],"datasets_introduced":[{"slug":"n15news","name":"N15News","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-1","task":"","dataset":"","model":"","rank_in_archive_order":3,"of":6,"metrics":{"":"24"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"Multimodal(ViT+BERT, Input: Image + Body)","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"0.9249"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"BERT (Input: Body)","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"0.9203"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"Multimodal(ViT+BERT, Input: Image + Abstract)","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"0.8610"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"BERT (Input: Abstract)","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"0.8471"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"Multimodal(ViT+BERT, Input: Image + Headline) - Dot","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"0.8202"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"Multimodal(ViT+BERT, Input: Image + Caption) - Concatenate","rank_in_archive_order":6,"of":9,"metrics":{"Accuracy":"0.7951"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"BERT (Input: Caption)","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy":"0.7792"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"BERT (Input: Headline)","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"0.7727"},"uses_additional_data":false},{"leaderboard":"/sota/news-classification-on-n15news","task":"News Classification","dataset":"N15News","model":"ViT (Input: Image)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"0.6065"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.13327","atlas_url":"https://app.syntology.ai/?focus=2108.13327","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}