Abstract: Faculty professional development is known to be a key factor contributing to the effective implementation of evidence-based teaching in STEM classrooms. In this research, we developed TEACHActive, an innovative classroom analytics-driven professional development model that supports the reflective practices of engineering instructors in higher education. TEACHActive uses machine learning techniques within a camera-based classroom sensing system that tracks behavioral features of interest in classrooms. Following design-based implementation research, we rapidly enacted, tested, and revised the TEACHActive model with engineering instructors. This study reports the results of the first iteration completed in the spring semester of 2021. Specifically, we examined the TEACHActive implementation and deployment in engineering classrooms with the analysis of instructors’ perceived successes and challenges. The paper presents implications for using the classroom analytics-driven professional development with educators in higher education.

Abstract: The ultimate goal of using learning analytics dashboards is to improve teaching and learning processes. Instructors that use an analytics dashboard are presented with data about their students and/or about their teaching practices. Despite growing research in analytics dashboards, little is known about how instructors make sense of the data they receive and reflect on it. Moreover, there is limited evidence on how instructors who use these dashboards take further actions and improve their pedagogical practices. My dissertation work addresses these issues by examining instructors’ sense making, reflective practice and subsequent actions taken from classroom analytics in three phases: (a) problem analysis from systematic literature review (current), (b) implementation and examination of instructors’ sense-making and reflective practice (current) and (c) human-centered approaches to co-designing instructors’ dashboards with stakeholders (current). The findings will contribute to the conceptual basis of instructors’ change of their pedagogical practices and practical implications of human-centered principles in designing effective dashboards. 

Abstract: Computer vision has the potential to play a significant role in capacity building for classroom instructors via automated feedback. This paper describes the implementation of an automated sensing and feedback system, TEACHActive. The results of this paper can enable other campuses to replicate a similar system using open-source software and consumer-grade hardware. Some of the challenges discussed include faculty recruitment, IRB procedures, camera-based classroom footage privacy, hardware setup, software setup, and IT support. The design and implementation of the TEACHActive system is being carried out at Iowa State University and is being tested with faculty in classrooms pilots. Preliminary interviews with instructors show a desire to include more active learning methods in their classrooms and overall interest in a system that can perform automated feedback. The primary results of this paper include lessons learned from the institutional implementation process.

Abstract: TEACHActive is an automated feedback dashboard that provides instructors with visual classroom analytics about the active learning facilitation strategies they use in their classrooms. We describe TEACHActive system’s root requirement of improving pedagogical practices through reflection, the system’s process of data flow from an automated observation system, EduSense, to the feedback dashboard, and the technical design of the infrastructure. We designed the TEACHActive dashboard to visualize EduSense’s automated observation output and give instructors feedback about their active learning facilitation strategies in their classrooms with the goal of improving their pedagogical practices. We present the TEACHActive prototype development process with  three illustrative prototypes.

Abstract: Effective facilitation of active learning is key to enhancing student engagement in engineering classrooms. Instructors need opportunities for frequent observation, feedback, and reflection on the use of their active learning strategies, yet there are no validated automated approaches available. We address this need by designing a feedback dashboard, TEACHActive, that leverages classroom analytics from an automated sensing observation system. The TEACHActive dashboard provides feedback on the in-class implementation of various active learning strategies in engineering classrooms. In this poster, we present the initial phases of a human-centered dashboard design process. The human-centered design (HCD) approach includes techniques such as, creating personas, conducting user interviews, and implementing user walk-through sessions. To confirm the practicability of TEACHActive dashboard for further revisions before the actual larger scale (n=30) implementation, a small sample of engineering instructors (n=5) participated in the prototype design process to identify meaningful attributes associated with the TEACHActive dashboard and shared perspectives and expectations towards its use in their classrooms. Keywords: feedback dashboard, active learning, classroom analytics, human-centered design.