Scaffolding Computational Thinking in Introductory Computer Science through a Conversational Agent

点击翻译按钮获取中文摘要

This project aims to serve the national interest by investigating how virtual assistants called conversational agents can help students to learn computer programming. A key challenge of teaching introductory programming lies in how to translate students' initial programming solutions that are written in informal language (also known as "pseudocode") into a form the computer can understand. The project team plans to design and evaluate a conversational agent prototype to improve students' programming skills. The conversational agent will enable students to express each step of an algorithm in natural language, then will guide students toward generating, understanding, and evolving expressions into a formal programming language. The project has the potential to change education settings so that students will get individual and contextualized attention when students learn computer programming concepts and computational thinking. The conversational agents can adapt code generations to match students’ needs. The proposed work has the potential to lower the hurdles faced by students and to provide instructors with a better understanding of students' challenges and expectations. The proposed conversational agents will help students to express their initial algorithmic thinking in natural language, and then guide students toward generating, understanding, and evolving more formal programming codes. The project will help students to produce better solutions, develop programming skills, and increasingly engage in the learning process. The project team will evaluate the effectiveness of the conversational agent in helping students to learn computer programming through a set of labs and field studies. The project intends to compare and contrast how students will produce codes with and without the agents, how students will perceive the proposed approach, and how students will learn programming concepts. The NSF IUSE: EDU Program supports research and development projects to improve the effectiveness of STEM education for all students. Through its Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.