使用RoBERTa变压器对推文自我报告不良妊娠结局和潜在COVID-19病例的分类

Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task Pub Date : 2021-06-01 DOI:10.18653/V1/2021.SMM4H-1.18

Lung-Hao Lee, Man-Chen Hung, Chien-Huan Lu, Chang-Hao Chen, Po-Lei Lee, K. Shyu

{"title":"使用RoBERTa变压器对推文自我报告不良妊娠结局和潜在COVID-19病例的分类","authors":"Lung-Hao Lee, Man-Chen Hung, Chien-Huan Lu, Chang-Hao Chen, Po-Lei Lee, K. Shyu","doi":"10.18653/V1/2021.SMM4H-1.18","DOIUrl":null,"url":null,"abstract":"This study describes our proposed model design for SMM4H 2021 shared tasks. We fine-tune the language model of RoBERTa transformers and their connecting classifier to complete the classification tasks of tweets for adverse pregnancy outcomes (Task 4) and potential COVID-19 cases (Task 5). The evaluation metric is F1-score of the positive class for both tasks. For Task 4, our best score of 0.93 exceeded the mean score of 0.925. For Task 5, our best of 0.75 exceeded the mean score of 0.745.","PeriodicalId":378985,"journal":{"name":"Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task","volume":"8 11","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Classification of Tweets Self-reporting Adverse Pregnancy Outcomes and Potential COVID-19 Cases Using RoBERTa Transformers\",\"authors\":\"Lung-Hao Lee, Man-Chen Hung, Chien-Huan Lu, Chang-Hao Chen, Po-Lei Lee, K. Shyu\",\"doi\":\"10.18653/V1/2021.SMM4H-1.18\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study describes our proposed model design for SMM4H 2021 shared tasks. We fine-tune the language model of RoBERTa transformers and their connecting classifier to complete the classification tasks of tweets for adverse pregnancy outcomes (Task 4) and potential COVID-19 cases (Task 5). The evaluation metric is F1-score of the positive class for both tasks. For Task 4, our best score of 0.93 exceeded the mean score of 0.925. For Task 5, our best of 0.75 exceeded the mean score of 0.745.\",\"PeriodicalId\":378985,\"journal\":{\"name\":\"Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task\",\"volume\":\"8 11\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/V1/2021.SMM4H-1.18\",\"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 Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/V1/2021.SMM4H-1.18","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

本研究描述了我们为SMM4H 2021共享任务提出的模型设计。我们对RoBERTa转换器及其连接的分类器的语言模型进行了微调，以完成推文对不良妊娠结局(Task 4)和潜在COVID-19病例(Task 5)的分类任务。两个任务的评价指标都是正面类的f1分。在Task 4中，我们的最高分是0.93，超过了平均分0.925。对于Task 5，我们的最好值0.75超过了平均值0.745。

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

Classification of Tweets Self-reporting Adverse Pregnancy Outcomes and Potential COVID-19 Cases Using RoBERTa Transformers

This study describes our proposed model design for SMM4H 2021 shared tasks. We fine-tune the language model of RoBERTa transformers and their connecting classifier to complete the classification tasks of tweets for adverse pregnancy outcomes (Task 4) and potential COVID-19 cases (Task 5). The evaluation metric is F1-score of the positive class for both tasks. For Task 4, our best score of 0.93 exceeded the mean score of 0.925. For Task 5, our best of 0.75 exceeded the mean score of 0.745.

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 Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task

自引率

0.00%

发文量