Sen Yan's Personal Website

about me

I’m currently a Ph.D candidate of Information Systems in the Division of Organizational Leadership and Information Analytics, Leeds School of Business, University of Colorado Boulder. Prior joining my Ph.D program, I received my Bachelor from Shanghai University of Finance and Economics.

My research adopts the computational design science approach in Information Systems to develop AI-based systems for construct validity assessment and theory development. I also apply the most advanced AI methods including large language models, multimodal deep learning, and graph neural networks, together with domain expertise to build intelligent artifacts for knowledge discovery and socially impactful applications such as AI-generated content detection.

“The most thought-provoking thing in our thought-provoking time is that we are still not thinking.” – Martin Heidegger

education

University of Colorado Boulder, Boulder, CO, USA.

Ph.D Student of Information Systems, 2021 - Present
Shanghai University of Finance and Economics, Shanghai, China.

Bachelor of Finance Management, 2017 - 2021

teaching experiences

BAIM3220 - Introduction to Python Programming University of Colorado Boulder, Spring 2025
BAIM3200/MKGT3201 - Business Analytics University of Colorado Boulder, Spring 2022

news

Jun 30, 2025	Our paper *An explainable framework for assisting the detection of AI-generated textual content* has been accepted by DSS

selected publications

DSS

An explainable framework for assisting the detection of AI-generated textual content

Sen Yan, Zhiyi Wang, and David Dobolyi

Decision Support Systems, 2025
ICIS 2024

Integrating LLMs and Psychometrics: Global Construct Validity

Kai Larsen, Sen Yan, and Lukyanenko Roman

In Proceedings of the International Conference on Information Systems 2024, Bangkok, Thailand, Dec 2024

Abs PDF

The psychometric approach in IS offers a foundational framework for a broad spectrum of research endeavors, which typically rely on construct validation to confirm that a series of indicators accurately measures the intended construct. However, a longstanding issue with construct validity, unaddressed since its introduction by Cronbach and Meehl in 1955, is that it is evaluated using study-specific response data without comparison to constructs outside the study. This oversight (or, rather, incapability) has significant implications. We introduce a large language model combined with principal components analysis (PCA) and develop the Validity Lodestar application. This approach lays the groundwork for developing more accurate and reliable theoretical models, marking a significant leap forward in the IS discipline’s methodological capabilities, making IS the first psychometric discipline with the capability to properly evaluate construct validity.