Automation bias with a conversational interface: User confirmation of misparsed information

2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) Pub Date : 2017-03-27 DOI:10.1109/COGSIMA.2017.7929605

Erin G. Zaroukian, J. Bakdash, A. Preece, William M. Webberley

{"title":"Automation bias with a conversational interface: User confirmation of misparsed information","authors":"Erin G. Zaroukian, J. Bakdash, A. Preece, William M. Webberley","doi":"10.1109/COGSIMA.2017.7929605","DOIUrl":null,"url":null,"abstract":"We investigate automation bias for confirming erroneous information with a conversational interface. Participants in our studies used a conversational interface to report information in a simulated intelligence, surveillance, and reconnaissance (ISR) task. In the task, for flexibility and ease of use, participants reported information to the conversational agent in natural language. Then, the conversational agent interpreted the user's reports in a human- and machine-readable language. Next, participants could accept or reject the agent's interpretation. Misparses occur when the agent incorrectly interprets the report and the user erroneously accepts it. We hypothesize that the misparses naturally occur in the experiment due to automation bias and complacency because the agent interpretation was generally correct (92%). These errors indicate some users were unable to maintain situation awareness using the conversational interface. Our results illustrate concerns for implementing a flexible conversational interface in safety critical environments (e.g., military, emergency operations).","PeriodicalId":252066,"journal":{"name":"2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)","volume":"570 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COGSIMA.2017.7929605","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 5

Abstract

We investigate automation bias for confirming erroneous information with a conversational interface. Participants in our studies used a conversational interface to report information in a simulated intelligence, surveillance, and reconnaissance (ISR) task. In the task, for flexibility and ease of use, participants reported information to the conversational agent in natural language. Then, the conversational agent interpreted the user's reports in a human- and machine-readable language. Next, participants could accept or reject the agent's interpretation. Misparses occur when the agent incorrectly interprets the report and the user erroneously accepts it. We hypothesize that the misparses naturally occur in the experiment due to automation bias and complacency because the agent interpretation was generally correct (92%). These errors indicate some users were unable to maintain situation awareness using the conversational interface. Our results illustrate concerns for implementing a flexible conversational interface in safety critical environments (e.g., military, emergency operations).

查看原文本刊更多论文

带有对话界面的自动化偏差:用户确认解析错误的信息

我们调查自动化偏差确认错误的信息与对话界面。在我们的研究中，参与者使用会话界面在模拟情报、监视和侦察(ISR)任务中报告信息。在任务中，为了灵活性和易用性，参与者用自然语言向会话代理报告信息。然后，会话代理用人类和机器可读的语言解释用户的报告。接下来，参与者可以接受或拒绝代理人的解释。当代理错误地解释报告而用户错误地接受报告时，就会出现解析错误。我们假设由于自动化偏差和自满，错误解析在实验中自然发生，因为代理解释通常是正确的(92%)。这些错误表明一些用户无法使用会话界面来维持态势感知。我们的研究结果说明了在安全关键环境(例如，军事、紧急行动)中实现灵活对话界面的关注。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)

自引率

0.00%

发文量