Journal of Computer Information Systems ( IF 2.5 ) Pub Date : 2021-06-11 , DOI: 10.1080/08874417.2021.1924092 Natalie Gerhart 1 , Obi Ogbanufe 2 , Russell Torres 2 , Anna Sidorova 2 , Nicholas Evangelopoulos 2
ABSTRACT
While there is an explosion in data analytic activity, certain behavioral aspects of a data analyst’s modeling efforts are not well understood. Through the lens of effort minimization theory, this research considers how data analysts make decisions to engage with more data as a part of their modeling process, and the effects that modeling tools have on these decisions. Previous research found that decision aids have no effect on reducing effort in terms of the amount of information referenced and processed. However, our results indicate that there are indeed significant differences in the amount of data analyzed with less effort-intensive modeling methods, and increasing amounts of available data. These results offer new implications for effort minimization research and organizations engaged in data analytics.
中文翻译:
数据分析时代的努力最小化理论
摘要
虽然数据分析活动呈爆炸式增长,但数据分析师建模工作的某些行为方面并未得到很好的理解。通过工作量最小化理论,本研究考虑了数据分析师如何做出决策以将更多数据作为其建模过程的一部分,以及建模工具对这些决策的影响。先前的研究发现,就参考和处理的信息量而言,决策辅助对减少工作量没有影响。然而,我们的结果表明,使用较少工作量的建模方法分析的数据量确实存在显着差异,并且可用数据量的增加。这些结果为最小化工作量研究和从事数据分析的组织提供了新的启示。