Digging into user control: perceptions of adherence and instability in transparent models

Digging into user control: perceptions of adherence and instability in transparent models
复制标题

深入研究用户控制:透明模型中对依从性和不稳定性的看法

DOI:
10.1145/3377325.3377491
复制
发表时间:
2020
期刊:
IUI '20: Proceedings of the 25th International Conference on Intelligent User Interfaces
影响因子:
--
通讯作者:
Findlater, Leah
Findlater, Leah
中科院分区:
--
文献类型:
--
作者:
Smith-Renner, Alison;Kumar, Varun;Boyd-Graber, Jordan;Seppi, Kevin;Findlater, Leah

文献摘要

参考文献

被引文献

相似文献

我们探索交互式系统中的可预测性和控制,其中控制很容易验证。人在回路技术允许用户通过暴露和支持与底层模型表示的交互来指导无监督算法,增加透明度和有希望的细粒度控制。然而,这些模型必须平衡用户输入和底层数据,这意味着它们有时更新缓慢,不佳或不可预测-要么不按预期(坚持)纳入用户输入,要么进行其他意外更改(不稳定)。虽然先前的工作暴露了模型内部并支持用户反馈,但当透明模型限制控制时,对用户的反应关注较少。专注于交互式主题模型,我们探索用户的感知控制使用一项研究,100名参与者组织文件的三个不同的主题建模方法之一。这些方法采用不同的输入,导致不同的坚持,稳定性,更新速度和模型质量。参与者最不喜欢缓慢的更新,其次是缺乏坚持。不稳定性是两极分化的:一些参与者喜欢它,当它出现有趣的信息,而其他人不喜欢。在各种建模方法中,参与者的差异仅在于他们是否注意到了坚持。
We explore predictability and control in interactive systems where controls are easy to validate. Human-in-the-loop techniques allow users to guide unsupervised algorithms by exposing and supporting interaction with underlying model representations, increasing transparency and promising fine-grained control. However, these models must balance user input and the underlying data, meaning they sometimes update slowly, poorly, or unpredictably---either by not incorporating user input as expected (adherence) or by making other unexpected changes (instability). While prior work exposes model internals and supports user feedback, less attention has been paid to users' reactions when transparent models limit control. Focusing on interactive topic models, we explore user perceptions of control using a study where 100 participants organize documents with one of three distinct topic modeling approaches. These approaches incorporate input differently, resulting in varied adherence, stability, update speeds, and model quality. Participants disliked slow updates most, followed by lack of adherence. Instability was polarizing: some participants liked it when it surfaced interesting information, while others did not. Across modeling approaches, participants differed only in whether they noticed adherence.
DOI: 10.1073/pnas.0307752101
发表时间: 2004-04-06
影响因子: 11.1
作者:
Griffiths, TL;Steyvers, M
通讯作者: Steyvers, M
为什么和为什么不解释可以提高上下文感知智能系统的可理解性
DOI: 10.1145/1518701.1519023
发表时间: 2009
期刊: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
影响因子: --
作者:
Brian Y. Lim;A. Dey;Daniel Avrahami
通讯作者: Daniel Avrahami
自动化精度好,但可控性高可能更好
DOI: --
发表时间: 2019
期刊: International Conference on Human Factors in Computing Systems
影响因子: --
作者:
Quentin Roy;Futian Zhang;Daniel Vogel
通讯作者: Daniel Vogel
设计显而易见的东西:Web 应用程序设计的常识方法
DOI: --
发表时间: 2002
期刊:
影响因子: --
作者:
J. Hoekman
通讯作者: J. Hoekman
评估主题表达以形成要点
DOI: --
发表时间: 2016
期刊: International Working Conference on Advanced Visual Interfaces
影响因子: --
作者:
E. Alexander;Michael Gleicher
通讯作者: Michael Gleicher