Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

App Planner: Utilizing Generative AI in K-12 Mobile App Development Education

David Kim, Prerna Ravi, Randi Williams, Daeun Yoo

TL;DR

The paper addresses the paucity of structured, ethically-aware ideation guidance in K-12 mobile app development education. It introduces App Planner, a SPARKI-inspired, GPT-backed five-stage scaffold that supports problem framing, design, and ethical reflection via a chat interface. A pilot study with five high-school seniors suggests the tool improves ideation flow, broadens consideration of users and societal impact, and is particularly valued during design and ethics discussions, though collaboration with peers remains important. The work demonstrates AI-assisted design tooling as a promising pathway to enhance computational thinking education, with planned integration with Aptly and App Inventor to expand accessibility and enable computational action.

Abstract

App Planner is an interactive support tool for K-12 students, designed to assist in creating mobile applications. By utilizing generative AI, App Planner helps students articulate the problem and solution through guided conversations via a chat-based interface. It assists them in brainstorming and formulating new ideas for applications, provides feedback on those ideas, and stimulates creative thinking. Here we report usability tests from our preliminary study with high-school students who appreciated App Planner for aiding the app design process and providing new viewpoints on human aspects especially the potential negative impact of their creation.

App Planner: Utilizing Generative AI in K-12 Mobile App Development Education

TL;DR

The paper addresses the paucity of structured, ethically-aware ideation guidance in K-12 mobile app development education. It introduces App Planner, a SPARKI-inspired, GPT-backed five-stage scaffold that supports problem framing, design, and ethical reflection via a chat interface. A pilot study with five high-school seniors suggests the tool improves ideation flow, broadens consideration of users and societal impact, and is particularly valued during design and ethics discussions, though collaboration with peers remains important. The work demonstrates AI-assisted design tooling as a promising pathway to enhance computational thinking education, with planned integration with Aptly and App Inventor to expand accessibility and enable computational action.

Abstract

App Planner is an interactive support tool for K-12 students, designed to assist in creating mobile applications. By utilizing generative AI, App Planner helps students articulate the problem and solution through guided conversations via a chat-based interface. It assists them in brainstorming and formulating new ideas for applications, provides feedback on those ideas, and stimulates creative thinking. Here we report usability tests from our preliminary study with high-school students who appreciated App Planner for aiding the app design process and providing new viewpoints on human aspects especially the potential negative impact of their creation.
Paper Structure (9 sections, 3 figures, 1 table)

This paper contains 9 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction & Background
  2. Tool Overview
  3. Tool Design
  4. Pilot Test
  5. Participants
  6. Methodology
  7. Observation of students using App Planner
  8. Preliminary Results & Discussion from Semi-structured Interview
  9. Limitation & Future Directions

Figures (3)

  • Figure 1: App Planner's role in the creation process
  • Figure 2: The tool is structured around five key text boxes, each guiding the user through a distinct stage of app development. If students encounter difficulties while filling out any of the text boxes, they have the option to consult with a chatbot, as illustrated in the top right image. For immediate guidance, they can select one of the pre-set question bubbles to receive a rule-based response like the bottom left. Alternatively, like the bottom right students can directly input their queries, which will be processed through an API call to ChatGPT, providing them with tailored assistance and clarifications, enhancing their understanding and progress. https://www.youtube.com/watch?v=y1pxWsf2iWE
  • Figure 3: Study Design of the experiment