基于语言复杂网络的口语测试评分研究

An approach of rating in Spanish speaking test based on the complex network

本研究引入"复杂网络(complex network)"理论和方法,以"依存语法"为理论基础,选取EEE-4口头作文作为研究对象,创建口头作文树库,构建各个等级的口头作文复杂网络,对这些网络的边数、节点数、节点平均度、平均路径长度、网络中心势以及度分布等特征进行对比分析,研究各个等级的考生口试表现的差异,并通过聚类分析,研究网络参数对不同等级的口试表现所具有的区分能力,为评分员分级评分提供参考。

This paper introduces the theory and methodology of the complex network and builds dependency syntactic networks based on the treebanks of speeches from EEE-4 speaking test. According to the analysis of the overall characteristics of the networks, including the number of edges, the number of the nodes, the average degree, the average path length, the network centrality and the degree distribution, this paper aims to find in the networks potential difference and similarity between various grades of speaking performance. Through clustering analysis, this research proves the network parameters＇ discriminating feature and provides potential reference for scoring speaking performance.