Conceptual Overview and Visualization of Video Resources Supporting Video-based Knowledge Exploration and Learning

Overview

In today's digital landscape, a wealth of video resources allows individuals to explore topics of interest. However, it's crucial for users to invest cognitive and intellectual effort in this process, to construct their knowledge framework, to connect with fellow learners, to enrich their learning and exploration experiences. Presently, most automatic recommender systems do not provide adequate active learning opportunities for users beyond passive video watching, nor do they consider the semantic connections of information resources when displaying results. This project aims to bridge this gap by exploring different conceptual overviews, visualizations, and interactions within video navigation systems. By doing so, we seek to understand how users might better facilitated with a balance between automated support and active learning actions. The project comprises two main initiatives: ConceptGuide and ConceptCombo. ConceptGuide is a prototype system that generates concept-map-based visual recommendations, offering links between concepts and videos to provide diverse learning pathways. On the other hand, ConceptCombo captures the conceptual structures and themes present in social comments and videos, supporting a more cohesive exploration of the topic domain. Through these efforts, we aim to enhance the user experience in navigating video resources and empower users in online knowledge exploration.

ConceptCombo: Assisting Online Video Access with Concept Mapping and Social Commenting Visualizations

Demo published in the Computer Supported Cooperative Work and Social Computing, October 14--18, 2023, Minneapolis, MN, USA

Abstract

As access to educational video resources has been enhanced through search tools, recommender systems, and social channeling, users often encounter challenges in integrating diverse videos systematically, particularly when they possess a limited understanding of the topics at hand (e.g., novice learners). To address this challenge, we present ConceptCombo, a video navigating interface facilitating user explorations of unstructured video collections with conceptual structures and themes of social comments extracted from videos and visualized by the system. To help novices identify a series of quality videos to watch, ConceptCombo aims to deliver a structured overview of the video collection by systematically extracting a concept map from the video content, coupled with automatic summarization of user comments across the videos, as a treemap visualization. With ConceptCombo, novice users may adopt a synergistic approach to video exploration, underpinned by the semantic structure of the video content, social comments, and additional video metadata.

Demo

Demo video of ConceptCombo

ConceptGuide: Supporting Online Video Learning with ConceptMap-based Recommendation of Learning Path

Published in the Proceedings of the Web Conference 2021 (WWW '21), April 19--23, 2021, Ljubljana, Slovenia

Abstract

People increasingly use online video platforms, e.g., YouTube, to locate educational videos to acquire knowledge or skills to meet personal learning needs. However, most of existing video platforms display video search results in generic ranked lists based on relevance to queries. The design of relevance-oriented information display does not take into account the inner structure of the knowledge domain, and may not suit the need of online learners. In this paper, we present ConceptGuide, a prototype system for learning orientations to support ad hoc online learning from unorganized video materials. ConceptGuide features a computational pipeline that performs content analysis on the transcripts of YouTube videos retrieved for a topic, and generates concept-map-based visual recommendations of inter-concept and inter-video links, forming learning pathways as structures for learners to consume. We evaluated ConceptGuide by comparing the design to the general-purpose interface of YouTube in learning experiences and behaviors. ConceptuGuide was found to improve the efficiency of video learning and helped learners explore the knowledge of interest in many constructive ways.

Demo

Demo video of ConceptGuide

Paper and Presentation

ACM DL paper link

Presentation video in WWW2021 conference by Jingxian Liao video link.

ConceptGuide system

The ConceptGuide is opensourced in the following repo: ConceptGuide_code.

Experiment questionnaire

Here are some example questions in our experiment questionnaire which covers 7 aspects of learning experiences. The questionnaire consists of a set of 7-point Likert scales. And the full questionnaire is here.

1. Learning Concentration
   • My mind wanders during the learning task.
2. Usability of System
   • It is easy to capture the information given by the learning system / YouTube.
3. Learning Motivation
   • I like the learning system / YouTube in this learning trial.
4. Scope of Videos
   • The learning system / YouTube could help me learn the contents from a new perspective.
5. Quality of Videos Watched
   • I am satisfied with the videos I found by using the learning system / YouTube.
6. Learning Guidance
   • I usually have no idea what I should search or learn during the task.
7. Perceived Learning Performance
   • I learned core concepts of the topic and their connections after the learning task.

Acknowledgments

This work was supported in part by the Ministry of Science and Technology of Taiwan under grant No. 109-2221-E-009-123-MY3 and 109-2221-E-009-119-MY3, and by UC Davis through Hao-Chuan Wang's startup grant. We thank Yun-Rou Lin for making the demo video.

Contact

Jingxian Liao - jxliao@ucdavis.edu