Asynchronous Video Interviews vs. Face-to-Face Interviews For Communication Skill Measurement: A Systematic Study
Asynchronous Video Interviews vs. Face-to-Face Interviews For Communication Skill Measurement: A Systematic Study
复制标题
沟通技巧测量的异步视频访谈与面对面访谈：系统研究
DOI：
10.1145/2993148.2993183
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
D. Jayagopi
中科院分区：
文献类型：
--
作者：
Sowmya Rasipuram;P. B;D. Jayagopi
沟通技巧是求职面试中一个重要的社会变量。正如最近的趋势所表明的那样，越来越多的异步或基于界面的视频采访正变得流行起来。自动招聘分析也越来越受到人们的关注，自动沟通技能预测就是其中之一。在此背景下，存在的一个研究差距，也是我们的论文所解决的问题是：当我们比较基于界面的面试和面对面的面试时，对沟通技能的感知和对所说类别的沟通者(例如，低于平均水平的人)的自动预测的准确性是否存在任何差异。为此，我们收集了106个来自研究生的访谈视频，包括基于界面的访谈和面对面的访谈。我们观察到，根据外部天真的观察者，基于界面(没有人参与)和面对面(当面试者参与)的参与者对行为的感知略有不同。在本文中，我们提出了一个在基于界面和面对面的面试中，通过自动提取参与者的音频、视觉和词汇行为的低水平特征，并使用线性回归、支持向量机和Logistic回归等机器学习算法来预测一个人的沟通技能的自动系统。我们还对参与者在通过人工转录和自动语音识别(ASR)工具获得口语反应时的言语行为进行了广泛的研究。我们最好的自动预测结果在基于界面的环境中达到了80%的准确率，在面对面的环境中达到了83%的准确率。Ccs概念·信息系统→内容分析和特征选择；语音/音频搜索；·应用计算→法、社会和行为科学；
Communication skill is an important social variable in employment interviews. As recent trends point to, increasingly asynchronous or interface-based video interviews are becoming popular. Also getting increasing interest is automatic hiring analysis, of which automatic communication skill prediction is one such task. In this context, a research gap that exists and which our paper addresses is“Are there any differences in perception of communication skill and the accuracy of automatic prediction of say classes of communicators (e.g. those below average) when we compare interface-based and face-to-face interviews”. To this end, we have collected a set of 106 interview videos from graduate students in both the settings i.e., interface-based and face-to-face. We observe that perception of behavior of participants in interface-based (when no person is involved) vs. face-to-face (when interviewer is involved) according to the external naive observers is slightly different. In this paper, we present an automatic system to predict the communication skill of a person in interface-based and face-to-face interviews by automatically extracting several low level features based on audio, visual and lexical behavior of the participants and using Machine Learning algorithms like Linear Regression, Support Vector Machine (SVM) and Logistic Regression. We also make an extensive study of the verbal behavior of the participant when the spoken response is obtained from manual transcriptions and Automatic Speech Recognition (ASR) tool. Our best automatic prediction results achieve an accuracy of 80% in interface-based and 83% in face-to-face setting. CCS Concepts •Information systems → Content analysis and feature selection; Speech / audio search; •Applied computing → Law, social and behavioral sciences;
在不同情境下使用视觉线索自动预测感知特征
DOI：
10.1109/icpr.2014.492
发表时间：
2014
期刊：
--
影响因子：
--
作者：
Joshi J
通讯作者：
Joshi J