🤖 AI Summary
This study addresses the challenge of effectively collecting student interaction data in resource-constrained classrooms of developing countries, where such limitations hinder the identification of learned helplessness behaviors in mathematics learning. To overcome this, the authors developed a web-based linear equation tutoring system featuring adaptive problem sequencing, multimodal gamification mechanisms, and cross-platform compatibility. By logging interactions such as problem skipping, hint usage, and difficulty progression, the system enables the construction of models for detecting learned helplessness. Designed specifically for low-resource educational settings, it successfully mitigates real-world constraints—including outdated devices, unstable internet connectivity, and frequent instructional interruptions—and collected high-quality interaction data from 118 students out of an initial cohort of 410. The deployment reveals critical data collection bottlenecks while offering a replicable framework for educational data gathering and behavioral modeling in similar environments.
📝 Abstract
This study investigates the challenges in designing, data collection, and implementation of a web-based Tutoring System (TS) for teaching linear equations within a developing country context. Originally designed as an Android app, the system was redeveloped as a web application to facilitate cross-platform access and data collection. This redesign enabled enhanced tracking through interaction logs and included features like problem skipping, hints, difficulty-based problem sequencing, and game modes with adaptable progression (e.g., easy-to-hard, hard-to-easy). The main objective was to document the design and data collection challenges encountered in data collection for the development of a model capable of detecting learned helplessness in students' behaviors while using a web application for solving linear equation. Challenges included outdated devices, unreliable internet, and logistical constraints such as limited session durations and delays in obtaining approvals. Environmental disruptions like class cancellations and curriculum gaps further complicated the process, with only 118 out of 410 students eligible and actively participating. These obstacles highlight the complexities of collecting interaction data for detecting learned helplessness in real-world, resource-constrained educational settings.