Namrata Srivastava

Supporting academically at-risk students has attracted much attention in the field of learning analytics. However, much of the research in this area has focused on developing advanced machine learning models to predict students' academic performance, which alone is insufficient to improve student learning without the implementation of timely interventions. Among the studies that attempted to mitigate this limitation by deploying intervention feedback to enhance learning, few created their feedback based on established theories of effective feedback. This theoretical oversight may limit students' uptake of the provided intervention. In response to these gaps, we conducted a study that aimed at supporting at-risk students at the early stage of an undergraduate-level course. Specifically, we developed predictive machine learning models using trace and academic data from the previous offering of a course, and applied these models to identify at-risk students in the subsequent semester's offering of the same course. For the identified at-risk students, we sent intervention emails designed by feedback experts based on a relational feedback framework designed to enhance feedback effectiveness by strengthening student-instructor relationships. We evaluated the effectiveness of the proposed approach by assessing the performance of the predictive models in terms of generalisability, and measuring the impact of the feedback intervention on students' learning engagement. Results showed that i) our predictive models demonstrated a high prediction accuracy (with AUC scores above 0.8) when applied to a new cohort of students; ii) more than 30% of the identified at-risk students visited previously unengaged learning activities within two weeks following the intervention; and iii) survey responses from 9.27% of at-risk students indicated general satisfaction with the provided feedback intervention, and 60\% of the respondents expressed a preference for receiving the intervention more frequently than the twice-per-semester frequency implemented in the present study.

Exploratory learning environments (ELEs), such as simulation-based platforms and open-ended science curricula, promote hands-on exploration and problem-solving but make it difficult for teachers to gain timely insights into students' conceptual understanding. This paper presents LearnLens, a generative AI (GenAI)-enhanced teacher-facing dashboard designed to support problem-based instruction in middle school science. LearnLens processes students' open-ended responses from digital assessments to provide various insights, including sample responses, word clouds, bar charts, and AI-generated summaries. These features elucidate students' thinking, enabling teachers to adjust their instruction based on emerging patterns of understanding. The dashboard was informed by teacher input during professional development sessions and implemented within a middle school Earth science curriculum. We report insights from teacher interviews that highlight the dashboard's usability and potential to guide teachers' instruction in the classroom.

Eye-tracking offers rich insights into student cognition and engagement, but remains underutilized in classroom-facing educational technology due to challenges in data interpretation and accessibility. In this paper, we present the iterative design and evaluation of a gaze-based learning analytics dashboard for English Language Arts (ELA), developed through five studies involving teachers and students. Guided by user-centered design and data storytelling principles, we explored how gaze data can support reflection, formative assessment, and instructional decision-making. Our findings demonstrate that gaze analytics can be approachable and pedagogically valuable when supported by familiar visualizations, layered explanations, and narrative scaffolds. We further show how a conversational agent, powered by a large language model (LLM), can lower cognitive barriers to interpreting gaze data by enabling natural language interactions with multimodal learning analytics. We conclude with design implications for future EdTech systems that aim to integrate novel data modalities in classroom contexts.

With advancements in AI, new gaze estimation methods are exceeding state-of-the-art (SOTA) benchmarks, but their real-world application reveals a gap with commercial eye-tracking solutions. Factors like model size, inference time, and privacy often go unaddressed. Meanwhile, webcam-based eye-tracking methods lack sufficient accuracy, in particular due to head movement. To tackle these issues, we introduce We bEyeTrack, a framework that integrates lightweight SOTA gaze estimation models directly in the browser. It incorporates model-based head pose estimation and on-device few-shot learning with as few as nine calibration samples (k < 9). WebEyeTrack adapts to new users, achieving SOTA performance with an error margin of 2.32 cm on GazeCapture and real-time inference speeds of 2.4 milliseconds on an iPhone 14. Our open-source code is available at https://github.com/RedForestAi/WebEyeTrack.