Complexity in declarative process models: Metrics and multi-modal assessment of cognitive load

作     者：Abbad-Andaloussi, Amine Burattin, Andrea Slaats, Tijs Kindler, Ekkart Weber, Barbara 

作者机构：Univ St Gallen Inst Comp Sci CH-9000 St Gallen Switzerland Tech Univ Denmark Software Syst Engn DK-2800 Lyngby Denmark Univ Copenhagen Dept Comp Sci DK-2100 Copenhagen Denmark 

出 版 物：《EXPERT SYSTEMS WITH APPLICATIONS》 (专家系统及其应用)

年 卷 期：2023年第233卷第1期

核心收录：

学科分类：1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Innovation Fund Denmark project Eco-Know [7050-00034A] International Postdoctoral Fellowship (IPF) from the University of St. Gallen, Switzerland 

主　　题：Complexity metrics Process model comprehension Declarative process model Cognitive load Eye-tracking Electrodermal activity 

摘      要：Complex process models can hinder the comprehension of the underlying business processes. While several metrics have been suggested in the literature to evaluate the complexity of imperative process models, little is known about their declarative counterparts. In this paper, we address this gap through a suite of metrics that we propose to capture the complexity of declarative process models. Following this, we empirically investigate the impact of complexity, as measured by the suggested metrics, on users cognitive load when comprehending declarative process models. Therein, we use a multi-modal approach including eye-tracking and electrodermal activity. The findings of the empirical study provide evidence about the cognitive load emerging as a result of increased model complexity. Overall, the outcome of this paper presents empirically validated metrics to evaluate the complexity of declarative process models. Implementing these metrics and incorporating them in intelligent modeling tools would help assessing the complexity of declarative process models before being deployed. Furthermore, our empirical approach can be adopted by researchers in upcoming empirical studies to provide a multi-perspective assessment of users cognitive load when engaging with process models.