Teresa Castle-Green, S. Reeves, J. Fischer, B. Koleva
{"title":"Decision Trees as Sociotechnical Objects in Chatbot Design","authors":"Teresa Castle-Green, S. Reeves, J. Fischer, B. Koleva","doi":"10.1145/3405755.3406133","DOIUrl":null,"url":null,"abstract":"Designers of dialogue-driven systems and 'conversational' agents like chatbots face huge complexities, both in the rich meanings of language and its sophisticated sequential organisation. To this end designers are starting to work out what it means to treat 'conversation' as a design material. But the elephant in the room is that for the most part, the key way of managing the complexities of chatbot design is the decision tree, or some variant of this. Yet decision trees have received little scrutiny as sociotechnical objects which both provide purchase for---but also simultaneously significantly restrict---design practice. CUI research needs to ramp up its concern for various assumptions built into chatbot design processes, and the various stakeholders which may be at play.","PeriodicalId":380130,"journal":{"name":"Proceedings of the 2nd Conference on Conversational User Interfaces","volume":"47 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2nd Conference on Conversational User Interfaces","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3405755.3406133","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
Designers of dialogue-driven systems and 'conversational' agents like chatbots face huge complexities, both in the rich meanings of language and its sophisticated sequential organisation. To this end designers are starting to work out what it means to treat 'conversation' as a design material. But the elephant in the room is that for the most part, the key way of managing the complexities of chatbot design is the decision tree, or some variant of this. Yet decision trees have received little scrutiny as sociotechnical objects which both provide purchase for---but also simultaneously significantly restrict---design practice. CUI research needs to ramp up its concern for various assumptions built into chatbot design processes, and the various stakeholders which may be at play.