Knowledge-Aware Learning Framework Based on Schema Theory to Complement Large Learning Models

ABSTRACT

Despite tremendous recent progress, extant artificial intelligence (AI) still falls short of matching human learning in effectiveness and efficiency. One fundamental disparity is that humans possess a wealth of prior knowledge, while AI lacks the essential commonsense knowledge required for learning tasks. Guided by schema theory, we employ the design science research methodology to introduce a novel knowledge-aware learning framework to harness the knowledge-based processes in human learning. Unlike existing pre-trained large language models (LLMs) and knowledge-aware approaches that treat knowledge in considerably different ways from humans, our theoretically grounded framework closely mimics how humans acquire, represent, activate, and utilize knowledge. The extensive evaluations in the context of text analytics tasks demonstrate that our design achieves comparable performance to the state-of-the-art LLMs and enhances model generalizability and learning efficiency. This study takes a step forward by bringing cognitive science into building cognitively plausible AI and human-AI collaboration research.

KEYWORDS:

• Knowledge-aware models
• schema theory
• knowledge graph
• text analytics
• deep learning
• design science
• artificial intelligence

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/07421222.2024.2340827.

Disclosure statement

The authors have no conflicts of interest to disclose.

Notes

ⁱ We are using the term “learning,” which is an encompassing process that includes both knowledge and skills acquisition and applications, is a broader term and contains problem-solving. While problem-solving is to use prior acquired knowledge and skills to address a particular challenge or obstacle. This application of existing knowledge and skills to solve a specific problem is a subset of the overall learning process. In essence, problem-solving is a manifestation of learning in action.

Additional information

Notes on contributors

Long Xia

Long Xia ([email protected]) is an Assistant Professor of Management Information Systems at the Love School of Business at Elon University. He received his PhD in Business Analytics from Virginia Tech. Dr. Xia’s research interests include deep learning, data science, design science, tourism and hospitality management, sharing economy, health IT, and social media analytics. His work has been published in such journals as Tourism Management, Decision Support Systems, Journal of Electronic Commerce Research, and Information Discovery and Delivery.

Wenqi Shen

Wenqi Shen ([email protected]) is an Assistant Professor at the Pamplin College of Business at Virginia Tech. She received her PhD in Management Information Systems from Purdue University. Dr. Shen’s research interests include online virtual communities, social media and social dynamics, user-generated content, the economics of information technologies, and firm information security. Her research has been published in such journals as MIS Quarterly, Management Science, Information Systems Journal, Journal of the Association for Information Systems, and Expert Systems with Applications, among others.

Weiguo Fan

Weiguo Fan ([email protected]) is a Henry B. Tippie Chair Professor in Business Analytics at the Tippie College of Business, University of Iowa. He received his PhD from the Ross School of Business, University of Michigan. His research interests focus on the design and development of novel information technologies—information retrieval, data mining, text analytics, social media analytics, and business intelligence techniques—to support better business information management and decision-making. Dr. Fan has published more than 280 refereed journal and conference papers. His research has appeared in many premier journals such as Information Systems Research, Journal of Management Information Systems, MIS Quarterly, Productions and Operations Management, IEEE Transactions on Knowledge and Data Engineering, and others.

G. Alan Wang

G. Alan Wang ([email protected]; corresponding author) is the Andersen Professor of Business Information Technology at the Pamplin College of Business at Virginia Tech. He received a PhD in Management Information Systems from the University of Arizona, Dr. Wang’s research interests include text mining, data mining, web and social media analytics, service computing, and quality engineering. He has published in Information Systems Research, Journal of Management Information Systems, MIS Quarterly Productions and Operations Management, Journal of Business Ethics, and Communications of the ACM, among others.