{"title":"Artiruno:用于多标准决策和口头决策分析的免费软件工具","authors":"Kodi B. Arfer","doi":"10.1002/mcda.1827","DOIUrl":null,"url":null,"abstract":"<p>Verbal decision analysis (VDA) is a family of methods for multi-criteria decision analysis that require no numerical judgements from the agent. Although many such methods have been developed, they share the potential issue of asking the agent many more questions than necessary, particularly under multilevel approaches. Furthermore, whether VDA improves decisions, compared to no intervention, has yet to be investigated empirically. I introduce a new VDA method, Artiruno, with a freely licensed implementation in Python. Artiruno makes inferences mid-interview so as to require minimal input from the agent, while using a multilevel scheme that allows it to ask complex questions when necessary. Inferences are facilitated by an axiom allowing comparisons to be partitioned across groups of criteria. Artiruno's performance in a variety of simple and complex scenarios can be verified with automated software tests. For an empirical test, I conducted an experiment in which 107 people from an Internet subject pool considered an important decision they faced in their own lives, and were randomly assigned to use Artiruno or to receive no intervention. These subjects proved mostly able to use Artiruno, and they found it helpful, but Artiruno seemed to have little influence on their decisions or outcomes.</p>","PeriodicalId":45876,"journal":{"name":"Journal of Multi-Criteria Decision Analysis","volume":"31 1-2","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Artiruno: A free-software tool for multi-criteria decision-making with verbal decision analysis\",\"authors\":\"Kodi B. Arfer\",\"doi\":\"10.1002/mcda.1827\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Verbal decision analysis (VDA) is a family of methods for multi-criteria decision analysis that require no numerical judgements from the agent. Although many such methods have been developed, they share the potential issue of asking the agent many more questions than necessary, particularly under multilevel approaches. Furthermore, whether VDA improves decisions, compared to no intervention, has yet to be investigated empirically. I introduce a new VDA method, Artiruno, with a freely licensed implementation in Python. Artiruno makes inferences mid-interview so as to require minimal input from the agent, while using a multilevel scheme that allows it to ask complex questions when necessary. Inferences are facilitated by an axiom allowing comparisons to be partitioned across groups of criteria. Artiruno's performance in a variety of simple and complex scenarios can be verified with automated software tests. For an empirical test, I conducted an experiment in which 107 people from an Internet subject pool considered an important decision they faced in their own lives, and were randomly assigned to use Artiruno or to receive no intervention. These subjects proved mostly able to use Artiruno, and they found it helpful, but Artiruno seemed to have little influence on their decisions or outcomes.</p>\",\"PeriodicalId\":45876,\"journal\":{\"name\":\"Journal of Multi-Criteria Decision Analysis\",\"volume\":\"31 1-2\",\"pages\":\"\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-04-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Multi-Criteria Decision Analysis\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/mcda.1827\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MANAGEMENT\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Multi-Criteria Decision Analysis","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mcda.1827","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MANAGEMENT","Score":null,"Total":0}
Artiruno: A free-software tool for multi-criteria decision-making with verbal decision analysis
Verbal decision analysis (VDA) is a family of methods for multi-criteria decision analysis that require no numerical judgements from the agent. Although many such methods have been developed, they share the potential issue of asking the agent many more questions than necessary, particularly under multilevel approaches. Furthermore, whether VDA improves decisions, compared to no intervention, has yet to be investigated empirically. I introduce a new VDA method, Artiruno, with a freely licensed implementation in Python. Artiruno makes inferences mid-interview so as to require minimal input from the agent, while using a multilevel scheme that allows it to ask complex questions when necessary. Inferences are facilitated by an axiom allowing comparisons to be partitioned across groups of criteria. Artiruno's performance in a variety of simple and complex scenarios can be verified with automated software tests. For an empirical test, I conducted an experiment in which 107 people from an Internet subject pool considered an important decision they faced in their own lives, and were randomly assigned to use Artiruno or to receive no intervention. These subjects proved mostly able to use Artiruno, and they found it helpful, but Artiruno seemed to have little influence on their decisions or outcomes.
期刊介绍:
The Journal of Multi-Criteria Decision Analysis was launched in 1992, and from the outset has aimed to be the repository of choice for papers covering all aspects of MCDA/MCDM. The journal provides an international forum for the presentation and discussion of all aspects of research, application and evaluation of multi-criteria decision analysis, and publishes material from a variety of disciplines and all schools of thought. Papers addressing mathematical, theoretical, and behavioural aspects are welcome, as are case studies, applications and evaluation of techniques and methodologies.