Tooee: A Novel Scratch Extension for K-12 Big Data and Artificial Intelligence Education Using Text-Based Visual Blocks

Youngki Park,Youhyun Shin

doi:10.1109/access.2021.3125060

Abstract

Many approaches have been proposed to teach the basic concepts of big data and artificial intelligence to K-12 students based on block-based programming languages, such as Scratch. Using these approaches, young students can easily experience big data and artificial intelligence through a drag-and-drop approach. However, it remains difficult for them to perform more complex tasks, such as directly collecting data from the web or exploiting custom-made machine learning algorithms. In this paper, we propose a novel Scratch extension that allows Scratch to communicate with text-based programming languages such as Python and JavaScript using WebSockets. Unlike other Scratch extensions, our extension greatly enhances the extensibility of Scratch given its use of “text-based visual blocks” so that messages can be freely exchanged through a minimum number of blocks. In order for students to use these blocks easily, the blocks are designed such that they can be used as if talking with a friend named “Tooee.” In order to show how this extension can help students create big data and artificial intelligence programs, we present eight example applications that students can easily implement. These are (1) Weather Forecast, (2) Top 5 Movies in Theaters, (3) COVID-19 Dashboard, (4) Saving Quiz Results to a CSV File, (5) Facial Image Classification, (6) Color Classification, (7) Object Classification, and (8) Handwriting Recognition. Our analyses and experimental results show that Tooee has several advantages over other educational environments.

Highlights

T HERE are many programming environments that allow K-12 students to learn the basic concepts of big data and artificial intelligence (AI) [1]–[10]
Young students can implement basic-level big data and AI programs; for example, students can (1) visualize national cabbage production data [11], (2) perform a sentiment analysis using Twitter data [2], (3) train a machine learning model that distinguishes between a dog and a cat [3], and (4) create a game program using a pre-trained model that recognizes the position of a face [1]
In this paper, we proposed a novel Scratch extension named Tooee that allows Scratch to communicate with text-based programming languages

Summary

Introduction

T HERE are many programming environments that allow K-12 students to learn the basic concepts of big data and artificial intelligence (AI) [1]–[10]. When using [1] or [2], while students can acquire Twitter data using "Twitter blocks," it’s difficult for them to crawl data from Facebook, Instagram or other websites because the corresponding visual blocks are not provided. As another example, while students can train a machine learning model using "machine learning blocks," changing the corresponding neural network structures based on these types of blocks is challenging

Objectives

Methods

Findings

Conclusion