@inproceedings{77462a1379c146a496699193ff673d73,
title = "N24News: A New Dataset for Multimodal News Classification",
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.",
keywords = "Multimodal Dataset, News Article, Text Classification",
author = "Zhen Wang and Xu Shan and Xiangxie Zhang and Jie Yang",
year = "2022",
language = "English",
series = "2022 Language Resources and Evaluation Conference, LREC 2022",
publisher = "European Language Resources Association (ELRA)",
pages = "6768--6775",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Jan Odijk and Stelios Piperidis",
booktitle = "2022 Language Resources and Evaluation Conference, LREC 2022",
note = "13th International Conference on Language Resources and Evaluation Conference, LREC 2022 ; Conference date: 20-06-2022 Through 25-06-2022",
}