The rising adoption of generative AI/ML technologies increases the need to support teens in developing AI/ML literacies. Child-computer interaction research argues that construction activities can support young people in understanding these systems and their implications. Recent exploratory studies demonstrate the feasibility of engaging teens in the construction of very small generative language models (LMs). However, it is unclear how constructing such models may foster the development of teens’ understanding of these systems from technical and socio-ethical perspectives. We conducted a week-long participatory design workshop in which sixteen teenagers constructed very small LMs to generate recipes, screenplays, and songs. Using thematic analysis, we identified technical and socio-ethical pieces of understandings that teens exhibited while designing generative LMs. This paper contributes (a) evidence of the kinds of pieces of understandings that teens have when constructing LMs and (b) a theory-backed framing to study novices’ understandings of AI/ML systems.

Despite growing calls to foster AI literacy, there are few available survey instruments designed for children and youth that study computational empowerment alongside construction and deconstruction activities. In such activities, learners’ beliefs about their abilities and attributes can impact their engagement. In this paper, we introduce and validate a survey instrument with constructs related to construction (creative expression and problem-solving self-beliefs) and deconstruction (auditing self-efficacy and fascination with auditing), along with more general self-beliefs related to design justice and the value of learning about AI/ML. We administered the instrument to 124 teenagers and assessed the six-factor structure of the instrument using confirmatory factor analysis. In addition to confirming the structure, we found that design justice beliefs strongly correlated with problem-solving, auditing self-efficacy, and creative expression.

While there is widespread interest in supporting young people to critically evaluate machine learning-powered systems, there is little research on how we can support them in inquiring about how these systems work and what their limitations and implications may be. Outside of K-12 education, an effective strategy in evaluating black-boxed systems is algorithm auditing—a method for understanding algorithmic systems’ opaque inner workings and external impacts from the outside in. In this paper, we review how expert researchers conduct algorithm audits and how end users engage in auditing practices to propose five steps that, when incorporated into learning activities, can support young people in auditing algorithms. We present a case study of a team of teenagers engaging with each step during an out-of-school workshop in which they audited peer-designed generative AI TikTok filters. We discuss the kind of scaffolds we provided to support youth in algorithm auditing and directions and challenges for integrating algorithm auditing into classroom activities. This paper contributes: (a) a conceptualization of five steps to scaffold algorithm auditing learning activities, and (b) examples of how youth engaged with each step during our pilot study.

The prominence of artificial intelligence and machine learning in everyday life has led to efforts to foster AI literacy for all K–12 students. In this paper, we review how Hour of Code activities engage with the five big ideas of AI, in particular with machine learning and societal impact. We found that a large majority of activities focus on perception and machine learning, with little attention paid to representation and other topics. A surprising finding was the increased attention paid to critical aspects of computing. However, we also observed a limited engagement with hands-on activities. In the discussion, we address how future introductory activities could be designed to offer a broader array of topics, including the development of tools to introduce novices to artificial intelligence and machine learning and the design of more unplugged and collaborative activities.

As generative language models (GLMs) have gained popularity, youth are increasingly using them in their everyday lives.As such, most research has centered on supporting youth as users of GLMpowered systems.However, we know little of how to engage youth in the design of these models.Building on the rich legacy of childcomputer interaction research that positions youth as designers of computing systems, we explore how to support young people in designing GLMs.Through a case study of three teenagers (ages 14-15) building a babyGPT screenplay generator, we illustrate how the team developed a model while engaging in artificial intelligence/machine learning-relevant data practices and addressing ethical issues.This paper contributes a case study that demonstrates the feasibility of engaging youth in building GLMs.

The widespread adoption of generative artificial intelligence/machine learning (AI/ML) technologies has increased the need to support youth in developing AI/ML literacies.However, most work has centered on preparing young people to use these systems, with less attention to how they can participate in designing and evaluating them.This study investigates how engaging young people in the design and auditing of generative language models (GLMs) may foster the development of their understanding of how these systems work from both technical and ethical perspectives.The study takes an in-pieces approach to investigate novices' conceptions of GLMs.Such an approach supports the analysis of how technical and ethical conceptions evolve and relate to each other.I am currently conducting a series of participatory design workshops with sixteen ninth graders (ages 14-15) in which they will (a) build GLMs from a data-driven perspective that glassboxes how data shapes model performance and (b) audit commercial GLMs by repeatedly and systematically querying them to draw inferences about their behaviors.I will analyze participants' interactions to identify ethical and technical conceptions they may exhibit while designing and auditing GLMs.Then I will investigate the contexts in which these conceptions emerge and how participants' personal interests and prior experiences may relate to their conceptions.I will also conduct clinical interviews and use microgenetic knowledge analysis and ordered network analysis to investigate how participants' ethical and technical conceptions of GLMs relate to each other and change after the workshop.The study will contribute (a) evidence of how engaging youth in design and auditing activities may support the development of ethical and technical understanding of GLMs and (b) an inventory of novice design and auditing practices that may support youth's technical and ethical understanding of GLMs.

Research on children and youth's participation in different roles in the design of technologies is one of the core contributions in child-computer interaction studies.Building on this work, we situate youth as advisors to a group of high school computer science teacher-and researcher-designers creating learning activities in the context of emerging technologies.Specifically, we explore algorithm auditing as a potential entry point for youth and adults to critically evaluate generative AI algorithmic systems, with the goal of designing classroom lessons.Through a two-hour session where three teenagers (16-18 years) served as advisors, we (1) examine the types of expertise the teens shared and (2) identify back stage design elements that fostered their agency and voice in this advisory role.Our discussion considers opportunities and challenges in situating youth as advisors, providing recommendations for actions that researchers, facilitators, and teachers can take to make this unusual arrangement feasible and productive.

This study investigates how high school-aged youth engage in algorithm auditing to identify and understand biases in artificial intelligence and machine learning (AI/ML) tools they encounter daily. With AI/ML technologies being increasingly integrated into young people's lives, there is an urgent need to equip teenagers with AI literacies that build both technical knowledge and awareness of social impacts. Algorithm audits (also called AI audits) have traditionally been employed by experts to assess potential harmful biases, but recent research suggests that non-expert users can also participate productively in auditing. We conducted a two-week participatory design workshop with 14 teenagers (ages 14-15), where they audited the generative AI model behind TikTok's Effect House, a tool for creating interactive TikTok filters. We present a case study describing how teenagers approached the audit, from deciding what to audit to analyzing data using diverse strategies and communicating their results. Our findings show that participants were engaged and creative throughout the activities, independently raising and exploring new considerations, such as age-related biases, that are uncommon in professional audits. We drew on our expertise in algorithm auditing to triangulate their findings as a way to examine if the workshop supported participants to reach coherent conclusions in their audit. Although the resulting number of changes in race, gender, and age representation uncovered by the teens were slightly different from ours, we reached similar conclusions. This study highlights the potential for auditing to inspire learning activities to foster AI literacies, empower teenagers to critically examine AI systems, and contribute fresh perspectives to the study of algorithmic harms.

As artificial intelligence/machine learning (AI/ML) applications become more pervasive in youth lives, supporting them to interact, design, and evaluate applications is crucial. This paper positions youth as auditors of their peers’ ML-powered applications to better understand algorithmic systems’ opaque inner workings and external impacts. In a two-week workshop, 13 youth (ages 14-15) designed and audited ML-powered applications. We analyzed pre/post clinical interviews in which youth were presented with auditing tasks. The analyses show that after the workshop all youth identified algorithmic biases and inferred dataset and model design issues. Youth also discussed algorithmic justice issues and ML model improvements. Furthermore, youth reflected that auditing provided them new perspectives on model functionality and ideas to improve their own models. This work contributes (1) a conceptualization of algorithm auditing for youth; and (2) empirical evidence of the potential benefits of auditing. We discuss potential uses of algorithm auditing in learning and child-computer interaction research.

Debugging physical computing projects provides a rich context to understand cross-disciplinary problem solving that integrates multiple domains of computing and engineering. Yet understanding and assessing students' learning of debugging remains a challenge, particularly in understudied areas such as physical computing, since finding and fixing hardware and software bugs is a deeply contextual practice. In this paper we draw on the rich history of clinical interviews to develop and pilot "failure artifact scenarios" in order to study changes in students' approaches to debugging and troubleshooting electronic textiles (e-textiles). We applied this clinical interview protocol before and after an eight-week-long e-textiles unit. We analyzed pre/post clinical interviews from 18 students at four different schools. The analysis revealed that students improved in identifying bugs with greater specificity, and across domains, and in considering multiple causes for bugs. We discuss implications for developing tools to assess students' debugging abilities through contextualized debugging scenarios in physical computing.

Most attention in K-12 artificial intelligence and machine learning (AI/ML) education has been given to having youths train models, with much less attention to the equally important testing of models when creating machine learning applications. Testing ML applications allows for the evaluation of models against predictions and can help creators of applications identify and address failure and edge cases that could negatively impact user experiences. We investigate how testing each other's projects supported youths to take perspective about functionality, performance, and potential issues in their own projects. We analyzed testing worksheets, audio and video recordings collected during a two week workshop in which 11 high school youths created physical computing projects that included (audio, pose, and image) ML classifiers. We found that through peer-testing youths reflected on the size of their training datasets, the diversity of their training data, the design of their classes and the contexts in which they produced training data. We discuss future directions for research on peer-testing in AI/ML education and current limitations for these kinds of activities.

In this paper, we examine a co-design workshop in which youth redesigned a learning activity for critical engagement with computing for the Hour of Code, an annual event that offers hour-long introductory computing activities to youth. We conducted co-design workshops during summer 2021 in two cities with 12 youth of Color (ages 11-15 years), in which we employed different reflective, collaborative and making activities to investigate youths’ critical perceptions of computing and address the following research questions: (1) What are the perspectives of youth from groups historically marginalized in computing on critical issues in computing? (2) What kinds of projects do youth create in Scratch to address critical issues in computing? and (3) How do youth reflect on the learning activity and make changes to implement it with their peers? In the discussion, we address what we learned about co-designing a critical computing learning activity with youth.

As one of the largest initiatives to introduce K-12 youth to computing, the Hour of Code has reached hundreds of millions of students around the globe. While Hour of Code activities have been immensely successful, they have also been criticized for their focus on puzzle-like close-ended guided activities leaving out more creative and critical engagement with computing. In this paper, we report on efforts to design CodeQuilt, an Hour-of-Code-style activity in which middle and high school youth were asked to design Scratch projects that engage with issues on who and what is computing. We analyzed over 100 Scratch projects posted on the public CodeQuilt site in addition to reflective responses provided by participating youth. We found that a wide array of Scratch projects engaged creatively by integrating popular media but only a small number of projects focused on critical issues. In the discussion, we outline next steps for better supporting more critical and creative engagement with computing in Hour of Code activities.