arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09664cs.LGcs.AIcs.HC
收藏

Tribe or Not?使用TribalGram对组差异进行严格检验

Tribe or Not? Critical Inspection of Group Differences Using TribalGram

University of Pittsburgh(匹兹堡大学)

Yongsu Ahn, Muheng Yan, Yu-Ru Lin, Wen-Ting Chung, Rebecca Hwa

摘要:

随着人工智能和数据采掘技术的兴起,群体分析和群体层面的分析越来越多地应用于包括政策制定和直接营销在内的许多领域。在某些情况下,从数据中提取的统计数据可能有助于了解一个群体的共同特征;在另一些情况下,群体一级的分析可能导致包括陈规定型观念和系统压迫在内的问题。在群体分析中,分析工具如何促进一个更认真的过程?在这项工作中,我们确定了一套负责任的组分析设计准则,以阐明组的差异化和防止一组的过度泛化的需要。根据设计指南,我们开发了TribalGram,这是一个可视化分析套件,它利用可解释的机器学习算法和可视化来提供推理评估,模型解释,数据确证和意义。通过与领域专家的访谈,我们展示了我们的设计和工具如何能够更丰富地理解从数据中挖掘出来的“组”。

英文摘要:

With the rise of AI and data mining techniques, group profiling and group-level analysis have been increasingly used in many domains including policy making and direct marketing. In some cases, the statistics extracted from data may provide insights to a group's shared characteristics; in others, the group-level analysis can lead to problems including stereotyping and systematic oppression. How can analytic tools facilitate a more conscientious process in group analysis? In this work, we identify a set of accountable group analytics design guidelines to explicate the needs for group differentiation and preventing overgeneralization of a group. Following the design guidelines, we develop TribalGram, a visual analytic suite that leverages interpretable machine learning algorithms and visualization to offer inference assessment, model explanation, data corroboration, and sense-making. Through the interviews with domain experts, we showcase how our design and tools can bring a richer understanding of "groups" mined from the data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑