Toward Automated Classroom Observation: Multimodal Machine Learning to Estimate CLASS Positive Climate and Negative Climate

Ramakrishnan, Anand; Zylich, Brian; Ottmar, Erin; LoCasale-Crouch, Jennifer; Whitehill, Jacob

doi:10.1109/taffc.2021.3059209

Cited by 16 publications

(7 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, evaluation is just one use of observation protocols. As policy shifts from summative evaluation to more formative uses, another important development in teacher observation is occurring on the research side-the emerging possibility of automated methods of classroom observation (see e.g., Franklin et al, 2018;Jacobs et al, 2022;Jacoby et al, 2018;Jensen et al, 2021;Kelly et al, 2018;Liu & Cohen, 2021;McCoy et al, 2018;Ramakrishnan et al, 2021;Watson et al, 2021). For example, the TalkMoves system (Jacobs et al, 2022) records data with an iPad and a Swivl robotic camera base, along with five linked microphones arrayed around the classroom.…”

Section: Teacher Observation In Educational Policy and Researchmentioning

confidence: 99%

Agnosticism in instructional observation systems

Kelly

2023

EPAA

View full text Add to dashboard Cite

Many instructional observation systems are designed to provide rough, qualitative, highly-evaluative assessments on numerous core dimensions of teaching. Such systems achieve comprehensive overviews of teaching but are poorly suited to answering many discovery-oriented research questions. In contrast, fine-grained agnostic systems are needed to pose and answer causal questions about instruction, and to fully understand instructional variation and change. More speculatively, I argue that the agnostic quality of fine-grained systems may also be useful in promoting teacher learning. Agnostic systems offer choice, withhold judgement, make room for locally-compensatory practices, and promote a greater locus of control. Instructional observation systems that carefully and agnostically quantify instructional processes may best help teachers leverage their professional judgment and invigorate their professional practice.

show abstract

Section: Teacher Observation In Educational Policy and Researchmentioning

confidence: 99%

Agnosticism in instructional observation systems

Kelly

2023

EPAA

View full text Add to dashboard Cite

show abstract

“…Up to now, enactivist CACs per se do not exist yet, even though recent apparatus like mobile eye trackers [36,37], electrodermal response trackers [31] or other types of sensors capturing various individual data, like pulsimeters, body temperature [38], as well as multimodal learning analytics capturing emotion and gaze recognition systems [39], can help gather and analyze instructional situations in an enactivist way: firstperson-based and accounting for context more fully. As a promising example of what an enactivist CAC could be, researchers [40] developed ACORN, a multimodal machine learning system that analyzes audio and video features of instructional events footages to infer classroom climate, as modeled in the Classroom Assessment Scoring System (CLASS) [41], a reliable and well-studied classroom observation system. The results showed medium correlations between human and machine coding on two CLASS dimensions (positive and negative climate).…”

Section: Enactivist Cacsmentioning

confidence: 99%

Context-Aware Classrooms as Places for an Automated Analysis of Instructional Events

Dessus

2022

Polyphonic Construction of Smart Learning Ecosystems

View full text Add to dashboard Cite

Context-Aware Classrooms (CACs), or ambient classrooms, are places in which instructional events can be captured and analyzed, thanks to advanced signal processing techniques. For CACs to be used for a better understanding of the educational events (teaching or learning), theoretically grounded approaches have to be reviewed and their main variables of interest presented. In this paper, three types of approaches to study the use of CACs (behavioral, ecological, and enactivist) are discussed, first theoretically, then about what each approach brings to the research on educational research. Some implications to build more ecologically-sound in presence or hybrid instructional sessions after the COVID-19 are drawn.

show abstract

“…Holistic Observation? Related Features [a] Affectiva [9] Wrist-worn (5,10,11) CERT [6] Ready videos (5,7,10) EngageMeter [10] Headsets (12) Sensei [4] A radio net (8) EduSense [5] 2 RGB cams (1,2,5,7,8,9) EmotionCues [7] Ready videos (10) Zheng et al [12] 1 RGB cam (1,2,3) Ahuja et al [8] 2 RGB cams (6) ACORN [13] Multimodel (13) StuArt 1 RGB cam (1,2,3,4,5,8) [a] (1) hand-raising, (2) standing, (3) sleeping, (4) yawning, (5) smiling, (6) eye gaze, (7) head pose, (8) position, (9) speech, (10) emotion, (11) electrodermal activity, ( 12) electroencephalography (EEG), ( 13) overall classroom climate record the learning status of each student during the course are rarely presented. It is not only an import indicator of teaching quality, but also empowers instructors to know each student for providing personalized instruction.…”

Section: Literaturementioning

confidence: 99%

StuArt: Individualized Classroom Observation of Students with Automatic Behavior Recognition and Tracking

Zhou¹,

Jiang²,

Si³

et al. 2022

Preprint

View full text Add to dashboard Cite

Each student matters, but it is hardly for instructors to observe all the students during the courses and provide helps to the needed ones immediately. In this paper, we present StuArt, a novel automatic system designed for the individualized classroom observation, which empowers instructors to concern the learning status of each student. StuArt can recognize five representative student behaviors (hand-raising, standing, sleeping, yawning, and smiling) that are highly related to the engagement and track their variation trends during the course. To protect the privacy of students, all the variation trends are indexed by the seat numbers without any personal identification information. Furthermore, StuArt adopts various user-friendly visualization designs to help instructors quickly understand the individual and whole learning status. Experimental results on real classroom videos have demonstrated the superiority and robustness of the embedded algorithms. We expect our system promoting the development of large-scale individualized guidance of students.

show abstract

Toward Automated Classroom Observation: Multimodal Machine Learning to Estimate CLASS Positive Climate and Negative Climate

Cited by 16 publications

References 49 publications

Agnosticism in instructional observation systems

Agnosticism in instructional observation systems

Context-Aware Classrooms as Places for an Automated Analysis of Instructional Events

StuArt: Individualized Classroom Observation of Students with Automatic Behavior Recognition and Tracking

Contact Info

Product

Resources

About