Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Is the Lecture Engaging for Learning? Lecture Voice Sentiment Analysis for Knowledge Graph-Supported Intelligent Lecturing Assistant (ILA) System

Yuan An, Samarth Kolanupaka, Jacob An, Matthew Ma, Unnat Chhatwal, Alex Kalinowski, Michelle Rogers, Brian Smith

TL;DR

An intelligent lecturing assistant system that utilizes a knowledge graph to represent course content and optimal pedagogical strategies is introduced, designed to support instructors in enhancing student learning through real-time analysis of voice, content, and teaching methods.

Abstract

This paper introduces an intelligent lecturing assistant (ILA) system that utilizes a knowledge graph to represent course content and optimal pedagogical strategies. The system is designed to support instructors in enhancing student learning through real-time analysis of voice, content, and teaching methods. As an initial investigation, we present a case study on lecture voice sentiment analysis, in which we developed a training set comprising over 3,000 one-minute lecture voice clips. Each clip was manually labeled as either engaging or non-engaging. Utilizing this dataset, we constructed and evaluated several classification models based on a variety of features extracted from the voice clips. The results demonstrate promising performance, achieving an F1-score of 90% for boring lectures on an independent set of over 800 test voice clips. This case study lays the groundwork for the development of a more sophisticated model that will integrate content analysis and pedagogical practices. Our ultimate goal is to aid instructors in teaching more engagingly and effectively by leveraging modern artificial intelligence techniques.

Is the Lecture Engaging for Learning? Lecture Voice Sentiment Analysis for Knowledge Graph-Supported Intelligent Lecturing Assistant (ILA) System

TL;DR

An intelligent lecturing assistant system that utilizes a knowledge graph to represent course content and optimal pedagogical strategies is introduced, designed to support instructors in enhancing student learning through real-time analysis of voice, content, and teaching methods.

Abstract

This paper introduces an intelligent lecturing assistant (ILA) system that utilizes a knowledge graph to represent course content and optimal pedagogical strategies. The system is designed to support instructors in enhancing student learning through real-time analysis of voice, content, and teaching methods. As an initial investigation, we present a case study on lecture voice sentiment analysis, in which we developed a training set comprising over 3,000 one-minute lecture voice clips. Each clip was manually labeled as either engaging or non-engaging. Utilizing this dataset, we constructed and evaluated several classification models based on a variety of features extracted from the voice clips. The results demonstrate promising performance, achieving an F1-score of 90% for boring lectures on an independent set of over 800 test voice clips. This case study lays the groundwork for the development of a more sophisticated model that will integrate content analysis and pedagogical practices. Our ultimate goal is to aid instructors in teaching more engagingly and effectively by leveraging modern artificial intelligence techniques.
Paper Structure (12 sections, 6 equations, 6 figures, 4 tables)

This paper contains 12 sections, 6 equations, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Background
  4. The Problem of Lecture Voice Sentiment Analysis
  5. Building Data Sets for Lecture Voice Sentiment Analysis
  6. Training Data
  7. Independent Validation Data
  8. Extracting Features from Raw Voice Signals
  9. Building Models for Lecture Voice Sentiment Analysis
  10. Experimental Results
  11. Discussion
  12. Conclusion

Figures (6)

  • Figure 1: Overview of Intelligent Lecturing Assistant (ILA) System. A knowledge graph that compiles course content, schedule, and learning objectives forms the system's foundation. The system constantly analyzes input from both the lecturer and students, including the lecturer's voice for sentiment, the actual content being delivered, and student responses through various means. In the context of teaching and learning, the system applies the analysis results to assist the teacher to implement the evidence-based learning strategies like retrieval practice, spaced practice, interleaving, and feedback-driven metacognition.
  • Figure 2: Label Distribution in the Data Set for Training
  • Figure 3: Label Distribution in the Independent Validation Data Set
  • Figure 4: The Waveform Representation of an Example Lecture Voice Clip
  • Figure 5: The Visualization of the Clips Based on Their MFCC Features
  • ...and 1 more figures