arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.00201cs.CYcs.AI
收藏

用于开发和评估自动化讲座风格评估系统的集成框架

An integrated framework for developing and evaluating an automated lecture style assessment system

Cyprus University of Technology(塞浦路斯理工大学);CYENS Centre of Excellence(CYENS卓越中心)

Eleni Dimitriadou, Andreas Lanitis

AI总结:

本文提出并评估了一个利用生物特征自动评估讲座风格的系统,其性能与人类相当或更优,旨在提升教学质量。

摘要:

本文所呈现工作的目标是开发和评估一个集成系统,该系统提供自动化的讲座风格评估,使教师能够即时获得与其讲座风格优劣相关的反馈。所提出的系统旨在促进讲座质量的提升,从而可能改善学生的整体学习体验。所提出的应用利用特定的可测量生物特征,如面部表情、身体活动、语速和语调、手部动作以及面部姿态,这些特征从展示讲师在观众视角下的视频中提取。讲座期间提取的可测量生物特征被结合起来,为教师提供一个反映讲座风格质量的分数,该分数既以帧率提供,也为整个讲座提供讲座质量指标。所提出的讲座风格评估系统的接受度由首席教育官、教师和学生就应用的功能性、有用性及可能的改进进行评估。结果表明,参与者认为该应用新颖且有用,能够提供关于讲座质量的自动化反馈。此外,将所提出系统的性能评估与人类在讲座风格评估任务中的表现进行了比较。结果表明,所提出的系统不仅达到了与人类观察者相似的表现,而且在某些情况下,其表现优于人类观察者。

英文摘要:

The aim of the work presented in this paper is to develop and evaluate an integrated system that provides automated lecture style evaluation, allowing teachers to get instant feedback related to the goodness of their lecturing style. The proposed system aims to promote improvement of lecture quality, that could upgrade the overall student learning experience. The proposed application utilizes specific measurable biometric characteristics, such as facial expressions, body activity, speech rate and intonation, hand movement, and facial pose, extracted from a video showing the lecturer from the audience point of view. Measurable biometric features extracted during a lecture are combined to provide teachers with a score reflecting lecture style quality both at frame rate and by providing lecture quality metrics for the whole lecture. The acceptance of the proposed lecture style evaluation system was evaluated by chief education officers, teachers and students regarding the functionality, usefulness of the application, and possible improvements. The results indicate that participants found the application novel and useful in providing automated feedback regarding lecture quality. Furthermore, the performance evaluation of the proposed system was compared with the performance of humans in the task of lecture style evaluation. Results indicate that the proposed system not only achieves similar performance to human observers, but in some cases, it outperforms them.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑