A Clustering-Based Method for Automatic Educational Video Recommendation Using Deep Face-Features of Lecturers

TL;DR

This paper introduces a face-clustering based recommendation system for educational videos that leverages lecturer face features to improve content retrieval accuracy without relying on textual data.

Contribution

It proposes an unsupervised face clustering approach to recommend videos based on lecturer presence, overcoming limitations of text-based methods.

Findings

Achieved a mean Average Precision (mAP) of 99.165%.

Effectively recommends videos with similar lecturer presence.

Improves content discovery in educational video databases.

Abstract

Discovering and accessing specific content within educational video bases is a challenging task, mainly because of the abundance of video content and its diversity. Recommender systems are often used to enhance the ability to find and select content. But, recommendation mechanisms, especially those based on textual information, exhibit some limitations, such as being error-prone to manually created keywords or due to imprecise speech recognition. This paper presents a method for generating educational video recommendation using deep face-features of lecturers without identifying them. More precisely, we use an unsupervised face clustering mechanism to create relations among the videos based on the lecturer's presence. Then, for a selected educational video taken as a reference, we recommend the ones where the presence of the same lecturers is detected. Moreover, we rank these recommended videos based on the amount of time the referenced lecturers were present. For this task, we achieved a mAP value of 99.165%.