GUT-IS: A Data-Driven Approach to Integrating Constructs and Their Relations in Information Systems

TL;DR

This paper introduces a data-driven method for integrating constructs in structural equation modeling within information systems, using text embeddings and clustering to improve construct consistency and analysis.

Contribution

It presents a novel approach combining text embeddings, clustering, and a loss function to optimize construct groupings and their relations in IS research.

Findings

Effective in producing consistent construct groupings

Allows analysis of trade-offs between semantic purity and parsimony

Evaluated on two IS datasets demonstrating practical utility

Abstract

Structural equation modeling is widely used in IS research. However, inconsistent construct definitions impede the cumulative development of knowledge. In this work, we present an approach that aims at the integration of structural equation models into a unified model: We use a combination of task-adapted text embeddings and clustering to produce a candidate set of construct groupings. Subsequently, we select the optimal solution using a loss function that explicitly trades off semantic purity and parsimony in the number of clusters. By making this trade-off explicit, our approach allows to analyze how construct groupings and their relations change as one shifts the priority from purity to parsimony. Empirically, we evaluate and explore the proposed methodology on two datasets from the IS domain.