Human-machine dialogue modality of English Language oral skills testing among Chinese EFL students

Abstract

With the development of computer technology and the development and application of interactive software, more and more second language oral examinations begin to adopt the form of "human-machine dialogue" as the main way of oral examination. However, the results of these experiments have not been validated in the Chinese context. Therefore, this study aims to identify the affecting factors of students’ performance in different English oral tests among Chinese EFL learners. The study used an experimental design. This paper designs and implements a simulated spoken English test of human-machine dialogue modality. 5 Chinese undergraduates students majoring in English language studies and 5 non-English majors are recruited to participate in the experiment. Also, in addition, the experiment also recruited 6 teachers with rich experience in teaching English as a second language as examiners. The results show that there are significant differences in the effective speech frequency in the two tests. Pearson value is.004, and reliability r value is R = 0.04, indicating significant reliability. In terms of hesitation, the duration of all subjects in Q1 and Q2 is significantly different (p<.01). Lexical errors and semantic errors were the most occurred mistakes among students. Finally, the subjects showed high level of anxiety. In terms of self-evaluation of speaking ability, only the group of intermediate English learners show significant differences in the self-evaluation of the two experiments test can truly reflect their oral English ability. This study recommends more research on the human-machine dialogue as the subjects in human-machine dialogue modality cannot get real-time feedback from the communication object, so the subjects are seldom able to notice and self-correct grammatical errors during the expression process. Fourth, the author analyzes and raises research questions about the mistakes made by the subjects in their oral expressions. The human-machine dialogue modality cannot guide the examinees through real-time communication and stimulate the examinees to express the examinee's grasp of relevant second language knowledge which the examiner wants to test.