(554e) Exploring the Use of Natural Language Processing in Developing Problem-Based Learning Scenarios for Social Responsibility in the Curriculum. | AIChE

(554e) Exploring the Use of Natural Language Processing in Developing Problem-Based Learning Scenarios for Social Responsibility in the Curriculum.

Authors 

Fernandez, K. - Presenter, University of Florida
Rivera-Jiménez, S. M., University of Florida
Social responsibility in engineering refers to the ethical obligation of engineers to consider the broader impacts of their work on society and the environment. Incorporating social responsibility themes into the engineering curriculum can encourage students to think critically about the societal implications of their work, including environmental sustainability and social justice. However, creating new problem-based learning (PBL) scenarios that incorporate social responsibility themes can be challenging for many faculty due to limited time and resources, lack of training and support, limited access to diverse perspectives, and balancing social responsibility with technical content.

This work explores the use of Natural Language Processing (NLP) as an instructional tool to develop PBL scenarios using social responsibility themes in an introductory chemical engineering course. NLP-based topic analysis tools can analyze large amounts of text from various sources to identify key topics and subtopics related to social responsibility, helping faculty to identify important themes to incorporate into PBL scenarios. Additionally, NLP-based text clustering tools can group similar texts related to social responsibility, allowing faculty to identify patterns and develop PBL scenarios that are relevant to current social issues. These NLP-based tools can aid in the development of PBL scenarios that encourage critical thinking and engagement among students in social responsibility themes, preparing them to be more responsible engineers. The effectiveness of the PBL statements in promoting critical thinking skills among chemical engineering students will be evaluated and compared to traditional PBL statements. Pedagogical strategies, challenges and ethical considerations for using AI tools and techniques in engineering education will also be presented.