• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

荷兰新冠疫情新闻发布会上的言语行为。

Speech acts in the Dutch COVID-19 Press Conferences.

作者信息

Schueler Daan, Marx Maarten

机构信息

Amsterdam, The Netherlands IRLab, Informatics Institute, University of Amsterdam.

出版信息

Lang Resour Eval. 2023;57(2):869-892. doi: 10.1007/s10579-022-09602-7. Epub 2022 Jul 19.

DOI:10.1007/s10579-022-09602-7
PMID:35874035
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9294846/
Abstract

UNLABELLED

An open source corpus of all Dutch COVID-19 Press Conferences with sentences annotated on the basis of John Searle's Speech Act taxonomy was created. It contains all 58 press conferences held between March 6 2020 and April 20 2021 and has 9.441 manually annotated sentences. Speech acts were annotated in a consistent manner, with a Krippendorff's alpha of .71. The corpus is easy to use and rich in metadata, with lexical, syntactic, discourse (speaker, question or answer) features and information on the type of regulations being present. We analyse the press conferences in terms of speech act usage, giving insight into the use of speech acts over time, the relation of speech act usage to real world phenomena, the general structure of the press conferences and the division of roles between speakers. Relations were found between speech act usage and the type of press conference (i.e. easing, tightening or neutral) as well as the number of hospital admissions. Speech act classes showed preferred locations within the press conferences, indicating a general structure. Distinct roles between speakers were identified. We also investigate the use of our set of labelled sentences for training a speech act classifier and achieve a reasonable accuracy of .73 and a mean reciprocal rank of .74 with the state of the art transformer RoBERTa model.

SUPPLEMENTARY INFORMATION

The online version of this article contains supplementary material available 10.1007/s10579-022-09602-7.

摘要

未标注

创建了一个开源语料库，其中包含所有荷兰语新冠疫情新闻发布会内容，并根据约翰·塞尔的言语行为分类法对句子进行了标注。该语料库包含2020年3月6日至2021年4月20日期间举行的所有58场新闻发布会，有9441个手动标注的句子。言语行为的标注方式一致， Krippendorff's alpha系数为0.71。该语料库易于使用且元数据丰富，具有词汇、句法、语篇（发言者、问题或答案）特征以及相关法规类型的信息。我们从言语行为的使用角度分析新闻发布会，深入了解言语行为随时间的使用情况、言语行为使用与现实世界现象的关系、新闻发布会的总体结构以及发言者之间的角色划分。发现言语行为的使用与新闻发布会的类型（即放宽、收紧或中性）以及住院人数之间存在关联。言语行为类别在新闻发布会中显示出偏好的位置，表明存在总体结构。确定了发言者之间的不同角色。我们还研究了使用我们的标注句子集训练言语行为分类器的情况，并使用先进的变压器RoBERTa模型达到了合理的准确率0.73和平均倒数排名0.74。

补充信息

本文的在线版本包含补充材料，可通过10.1007/s10579-022-09602-7获取。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/965d9702ac54/10579_2022_9602_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/f58951b26306/10579_2022_9602_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/f0e615aa46a0/10579_2022_9602_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/42307002826c/10579_2022_9602_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/10ca1907aec1/10579_2022_9602_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/6a11cc7a4c6a/10579_2022_9602_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/e0894c6e6b40/10579_2022_9602_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/2211a846f2cc/10579_2022_9602_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/2d7357000aff/10579_2022_9602_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/c295cdf538b7/10579_2022_9602_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/9baab52e0098/10579_2022_9602_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/965d9702ac54/10579_2022_9602_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/f58951b26306/10579_2022_9602_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/f0e615aa46a0/10579_2022_9602_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/42307002826c/10579_2022_9602_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/10ca1907aec1/10579_2022_9602_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/6a11cc7a4c6a/10579_2022_9602_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/e0894c6e6b40/10579_2022_9602_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/2211a846f2cc/10579_2022_9602_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/2d7357000aff/10579_2022_9602_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/c295cdf538b7/10579_2022_9602_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/9baab52e0098/10579_2022_9602_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/deaa/9294846/965d9702ac54/10579_2022_9602_Fig11_HTML.jpg

相似文献

1
Speech acts in the Dutch COVID-19 Press Conferences.荷兰新冠疫情新闻发布会上的言语行为。
Lang Resour Eval. 2023;57(2):869-892. doi: 10.1007/s10579-022-09602-7. Epub 2022 Jul 19.
2
The discursive (re)construction of social relations in a crisis situation: A genre analytical approach to press conferences on COVID-19 in China.危机情境下社会关系的话语（再）建构：中国新冠疫情新闻发布会的体裁分析方法
Front Psychol. 2022 Nov 8;13:991813. doi: 10.3389/fpsyg.2022.991813. eCollection 2022.
3
Together They Stand: Interpreting Not-At-Issue Content.他们团结一致：解读无争议内容。
Lang Speech. 2018 Jun;61(2):199-226. doi: 10.1177/0023830917714608. Epub 2017 Jun 27.
4
Studying Chinese Foreign Policy Narratives: Introducing the Ministry of Foreign Affairs Press Conferences Corpus.研究中国外交政策叙事：引入外交部新闻发布会语料库
J Chin Polit Sci. 2021;26(4):743-761. doi: 10.1007/s11366-021-09762-3. Epub 2021 Sep 23.
5
Spontaneous, controlled acts of reference between friends and strangers.朋友和陌生人之间自发、可控的指代行为。
Lang Resour Eval. 2022 Nov 28:1-25. doi: 10.1007/s10579-022-09619-y.
6
A crosslinguistic comparison of the production of utterances in discourse.话语中话语产出的跨语言比较。
Cognition. 1995 Feb;54(2):169-207. doi: 10.1016/0010-0277(94)00635-x.
7
The biomedical discourse relation bank.生物医学话语关系库。
BMC Bioinformatics. 2011 May 23;12:188. doi: 10.1186/1471-2105-12-188.
8
Disparity in Gender Representation of Speakers at National Emergency Medical Services Conferences: A Current Assessment and Proposed Path Forward.国家紧急医疗服务会议中演讲者的性别代表性差距：当前评估和拟议的前进道路。
Prehosp Disaster Med. 2021 Aug;36(4):445-449. doi: 10.1017/S1049023X21000571. Epub 2021 Jun 30.
9
A web-based survey of educational opportunities of medical professionals based on changes in conference design during the COVID-19 pandemic.基于新冠疫情期间会议设计变化的医学专业人员教育机会的网络调查。
Educ Inf Technol (Dordr). 2022;27(7):10371-10386. doi: 10.1007/s10639-022-11032-5. Epub 2022 Apr 18.
10
The Prosody of -exclamatives and -questions in German: Speech Act Differences, Information Structure, and Sex of Speaker.德语中的感叹句和疑问句的韵律：言语行为差异、信息结构和说话者性别。
Lang Speech. 2020 Jun;63(2):306-361. doi: 10.1177/0023830919846147. Epub 2019 May 17.

引用本文的文献

1
Crisis communication in the WHO COVID-19 press conferences: A retrospective analysis.世界卫生组织 COVID-19 新闻发布会中的危机沟通：回顾性分析。
PLoS One. 2023 Mar 13;18(3):e0282855. doi: 10.1371/journal.pone.0282855. eCollection 2023.