The Learnalyze Six Dimensions Methodology
Understanding the Six Dimensions of Teaching Excellence
Comprehensive Guide for Teachers & School Leaders
Introduction: How Learnalyze Evaluates Lessons
Learnalyze utilizes advanced artificial intelligence to analyze video recordings of lessons across six critical dimensions of teaching excellence. Our proprietary algorithms process visual, audio, and linguistic data to provide objective, consistent, and actionable feedback for teachers and school leaders.
How Learnalyze Processes Video Lessons
When a lesson video is uploaded to Learnalyze, our multi-layered AI system begins processing immediately. Computer vision algorithms analyze visual elements including teacher positioning, student engagement cues, board usage, and technology integration. Audio processing extracts speech patterns, questioning techniques, and tonal characteristics. Natural language processing evaluates vocabulary complexity, explanation clarity, and instructional language. All these data points are synthesized to generate comprehensive dimension scores and actionable insights.
Understanding the Scoring System
Each dimension receives a score from 0 to 100, calculated through weighted analysis of multiple indicators and sub-criteria. These scores are normalized against pedagogical benchmarks and institutional standards to provide meaningful context.
Exceeds expected standards; demonstrates a high level of mastery.
Performs above expected standards in some areas; overall consistent and secure performance.
Meets expected standards; demonstrates consistent performance.
Does not yet meet expected standards; further development is required.
The Six Dimensions Overview
Learnalyze evaluates teaching performance across six interconnected dimensions that together represent the key pillars of effective instruction. Each dimension contains specific sub-criteria that provide granular insights into teaching practice.
| Dimension | Primary Focus |
|---|---|
| 1. Lesson Structure | Organization, flow, and logical progression |
| 2. Behaviour Management | Classroom environment and discipline |
| 3. Clarity | Communication and explanation effectiveness |
| 4. Formative Assessment | Checking understanding and feedback |
| 5. Engagement | Student participation and interaction |
| 6. Technology Integration | Effective use of digital tools |
1. Lesson Structure
Evaluates the logical flow and organization of the lesson, ensuring a clear beginning, middle, and end that supports effective learning progression.
Evaluation Criteria
- ○Clear learning objectives and success criteria stated at the start of the lesson
- ○Effective connection to prior knowledge
- ○Logical transition between activities and lesson segments
- ○Alignment between stated objectives and lesson activities
- ○Effective time management across all lesson sections
- ○Effective lesson closure, including a clear summary of key learning points
How Learnalyze Analyzes This Dimension
AI analyzes video timestamps to identify distinct lesson phases (introduction, instruction, guided practice, independent practice, closure). Machine learning algorithms track segment durations and transitions to assess pacing and flow. The system maps lesson activities against evidence-based pedagogical frameworks to evaluate structural integrity.
2. Behaviour Management
Assesses how effectively the teacher maintains a conducive learning environment, handles disruptions, and promotes positive classroom dynamics.
Evaluation Criteria
- ○Clarity and consistency of expectations for behaviour and learning
- ○Effectiveness of strategies used to promote calm, positive behaviour
- ○Consistency in the application of behaviour management approaches
- ○Quality of respectful and supportive teacher-student relationships
- ○Extent to which the learning environment promotes cooperation
How Learnalyze Analyzes This Dimension
Audio analysis algorithms detect tone shifts, volume changes, and emotional indicators in the teacher's voice. Computer vision tracks teacher movement patterns and spatial awareness. The system uses sentiment analysis to identify positive versus negative interaction patterns and measures the ratio of affirming to corrective statements.
3. Clarity
Drawing on cognitive load theory, working memory, and cognitive processing speed and aligned with Rosenshine's Principles of Instruction, our AI analyses how clearly concepts are explained, how instructions are delivered, and how well student understanding is checked and secured across the lesson.
Evaluation Criteria
- ○Clarity and structure of explanations, with content presented in manageable steps
- ○Effectiveness of instructional delivery in minimizing cognitive overload
- ○Appropriateness of pacing in relation to students' working memory and processing speed
- ○Use of strategies aligned with Rosenshine's Principles (e.g., modelling, guided practice, questioning)
- ○Frequency and quality of checks for understanding to secure learning throughout the lesson
How Learnalyze Analyzes This Dimension
Natural Language Processing (NLP) algorithms evaluate the clarity and structure of teacher explanations, including sentence complexity and the appropriateness of vocabulary. Speech analysis examines pace, pausing, and articulation to assess alignment with students' working memory and processing speed. The system identifies instructional practices linked to Rosenshine's Principles, such as modelling, rephrasing, and guided questioning.
4. Formative Assessment
Evaluates how effectively the teacher gathers and responds to evidence of student understanding during the lesson to adapt instruction, address misconceptions, and secure learning.
Evaluation Criteria
- ○Regular and varied questioning techniques used
- ○Mix of question types (recall, comprehension, analysis, synthesis as well as open and closed)
- ○Adequate wait time provided for student responses
- ○Meaningful feedback given on student answers
- ○Adjustment of instruction based on assessment results
How Learnalyze Analyzes This Dimension
AI detects questioning patterns in the audio transcript, identifying question types and measuring frequency. Silence detection algorithms calculate wait time after questions. The system analyzes response quality by evaluating follow-up questioning and feedback specificity. Machine learning models assess whether instruction is adapted based on student performance indicators.
5. Engagement
Tracks and evaluates student participation levels, active involvement, and overall interaction during the learning process.
Evaluation Criteria
- ○Balanced student talk time versus teacher talk time
- ○Active student participation in activities and discussions
- ○Visual engagement and attention indicators
- ○Response rates to teacher prompts and questions
- ○Student-to-student interaction and collaboration
How Learnalyze Analyzes This Dimension
Speaker diarization technology separates and identifies teacher versus student voices throughout the lesson. Computer vision algorithms track student body language, visual attention, and movement patterns. The system measures student participation frequency and calculates the student-to-teacher interaction ratio. Engagement heat maps identify attention patterns over time.
6. Technology Integration
Assesses the effective, purposeful, and seamless use of digital tools and educational technology to enhance learning outcomes.
Evaluation Criteria
- ○Purposeful selection of technology aligned with learning objectives
- ○Seamless transition between traditional and digital instruction
- ○Students actively engaging with technology tools
- ○Technical competence and efficiency in tool operation
- ○Technology enhances rather than distracts from learning
How Learnalyze Analyzes This Dimension
Object detection and computer vision identify screens, devices, and technology tools visible in the video. Context analysis algorithms verify that technology use aligns with the lesson's instructional goals. The system measures transition time to and from digital tools and evaluates student interaction frequency with presented technology. Technical troubleshooting incidents are noted and measured.
Types of Feedback Learnalyze Provides
Learnalyze provides multiple layers of feedback to help teachers understand their performance and identify specific areas for growth.
Dimension Scores
Each dimension score is accompanied by detailed breakdowns showing which criteria contributed to the overall score and how the teacher compares to benchmarks.
Time-Stamped Comments
Specific observations linked to exact moments in the video, allowing teachers to review exactly what happened and why.
Developmental Feedback
Identifies what worked well in the lesson and offers focused, practical suggestions to make those strengths even more effective.
Comparative Analysis
How the teacher performance compares to institutional averages, peer groups, and pedagogical standards.
Trend Indicators
Historical data showing dimension scores over multiple lessons, revealing patterns and growth trajectories.
Priority Recommendations
AI-generated suggestions for professional development focus areas based on the most significant gaps identified.
For Teachers
Learnalyze empowers teachers to take ownership of their professional growth. By reviewing time-stamped feedback and dimension scores after each lesson, teachers can identify specific behaviors to improve. The platform supports goal-setting by allowing teachers to track progress over time and measure the impact of instructional changes. Teachers can use the AI insights to prepare for performance reviews with concrete evidence of their teaching practice and growth.
For Principals and Decision Makers
School leaders can leverage Learnalyze data to make informed decisions about teacher development and school improvement initiatives. Aggregate data across teachers reveals school-wide strengths and growth areas, enabling targeted professional development programs. Principals can identify teachers who excel in specific dimensions and may serve as mentors or model lessons. The platform provides objective data for resource allocation decisions, ensuring investments in teacher training address the most critical needs identified through comprehensive analysis.
Data-Driven Decision Support
Learnalyze transforms subjective observations into quantifiable data that supports strategic decision-making. School leaders can use dimension analysis to identify patterns such as a school-wide need for better formative assessment practices or inconsistent behaviour management approaches. This data enables evidence-based professional development planning, targeted coaching assignments, and resource allocation aligned with demonstrated needs. The platform supports continuous improvement cycles by measuring the impact of interventions over time.