The COVID-19 pandemic has forced the transition of workflows across sectors to digital platforms. In education settings, stakeholders previously reluctant to integrate computing technology in the classroom now find themselves with little choice but to embrace it. This move to the digital brings additional challenges in underserved contexts with limited, intermittent, and shared access to mobile or computing devices and the internet. In this rapidly evolving digital landscape, we investigate how educational institutions (schools and non-profit organizations) working with underserved populations in India are managing the transition to online or remote learning. We conducted twenty remote interviews with students, teachers, and administrators from underserved contexts across India. We found that online learning efforts in this setting relied on a resilient human infrastructure comprised of students, teachers, parents, administrators, and non-profit organizations to help navigate and overcome the limitations of available technical infrastructure. Our research aims to articulate lessons for educational technology design in the post-COVID period, outlining areas for improvement in the design of online learning platforms in resource-constrained settings, and identifying elements of online learning that could be retained to strengthen the education system overall.

Deaf children born to hearing parents lack continuous access to language, leading to weaker working memory compared to hearing children and deaf children born to Deaf parents. CopyCat is a game where children communicate with the computer via American Sign Language (ASL), and it has been shown to improve language skills and working memory. Previously, CopyCat depended on unscalable hardware such as custom gloves for sign verifcation, but modern 4K cameras and pose estimators present new opportunities. Before re-creating the CopyCat game for deaf children using of-the-shelf hardware, we evaluate whether current ASL recognition is sufcient.Using Hidden Markov Models (HMMs), user independent word accuracies were 90.6%, 90.5%, and 90.4% for AlphaPose, Kinect, and MediaPipe, respectively. Transformers, a state-of-the-art model in natural language processing, performed 17.0% worse on average.Given these results, we believe our current HMM-based recognizer can be successfully adapted to verify children's signing while playing CopyCat. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing systems and tools; Accessibility technologies; • Applied computing → Computer-managed instruction; • Computing methodologies → Machine learning; Feature selection.

No abstract