表情符号敏感反语检测的数据集分析与增强

Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019) Pub Date : 2019-11-01 DOI:10.18653/v1/d19-5527

Shirley Anugrah Hayati, Aditi Chaudhary, Naoki Otani, A. Black

{"title":"表情符号敏感反语检测的数据集分析与增强","authors":"Shirley Anugrah Hayati, Aditi Chaudhary, Naoki Otani, A. Black","doi":"10.18653/v1/d19-5527","DOIUrl":null,"url":null,"abstract":"Irony detection is an important task with applications in identification of online abuse and harassment. With the ubiquitous use of non-verbal cues such as emojis in social media, in this work we aim to study the role of these structures in irony detection. Since the existing irony detection datasets have <10% ironic tweets with emoji, classifiers trained on them are insensitive to emojis. We propose an automated pipeline for creating a more balanced dataset.","PeriodicalId":414714,"journal":{"name":"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)","volume":"7 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Dataset Analysis and Augmentation for Emoji-Sensitive Irony Detection\",\"authors\":\"Shirley Anugrah Hayati, Aditi Chaudhary, Naoki Otani, A. Black\",\"doi\":\"10.18653/v1/d19-5527\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Irony detection is an important task with applications in identification of online abuse and harassment. With the ubiquitous use of non-verbal cues such as emojis in social media, in this work we aim to study the role of these structures in irony detection. Since the existing irony detection datasets have <10% ironic tweets with emoji, classifiers trained on them are insensitive to emojis. We propose an automated pipeline for creating a more balanced dataset.\",\"PeriodicalId\":414714,\"journal\":{\"name\":\"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)\",\"volume\":\"7 4\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/d19-5527\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/d19-5527","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

反语检测是一项重要的任务，在识别网络滥用和骚扰方面有着广泛的应用。随着社交媒体中表情符号等非语言线索的普遍使用，本研究旨在研究这些结构在反语检测中的作用。由于现有的反讽检测数据集含有表情符号的反讽推文不到10%，因此在这些数据集上训练的分类器对表情符号不敏感。我们提出了一个自动化的管道来创建一个更平衡的数据集。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Dataset Analysis and Augmentation for Emoji-Sensitive Irony Detection

Irony detection is an important task with applications in identification of online abuse and harassment. With the ubiquitous use of non-verbal cues such as emojis in social media, in this work we aim to study the role of these structures in irony detection. Since the existing irony detection datasets have <10% ironic tweets with emoji, classifiers trained on them are insensitive to emojis. We propose an automated pipeline for creating a more balanced dataset.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)

自引率

0.00%

发文量