文献类型：期刊文献

英文题名：Prediction of english scores of college students based on multi-source data fusion and social behavior analysis

作者：Zhao, Yanxia[1]; Ren, Wei[2]; Li, Zheng[3]

第一作者：Zhao, Yanxia

机构：[1] School of International Studies, Zhejiang Business College, Hangzhou, 310053, China; [2] School of E-commerce, Zhejiang Business College, Hangzhou, 310053, China; [3] College of Applied Science and Technology, Beijing Union University, Beijing, 100101, China

第一机构：School of International Studies, Zhejiang Business College, Hangzhou, 310053, China

年份：2020

卷号：34

期号：4

起止页码：465-470

外文期刊名：Revue d'Intelligence Artificielle

收录：EI(收录号：20204509469071);Scopus(收录号：2-s2.0-85095587683)

基金：This article is the research result of the project funded by Department of Education of Zhejiang Province (Grant No.: Y201942517).

语种：英文

外文关键词：Data fusion - Forecasting - Support vector machines - Turing machines

摘要：Multi-source data fusion is the premise of applying big data technology in specific fields. Inspired by the theory on multi-source data fusion, this paper fuses various data on college students, including motion trajectories, consumptions, and social behaviors, and adopts support vector machine (SVM), a machine learning (ML) classifier to predict the English scores of college students. The behavior trajectories were taken into account, because this type of data represents the social similarity between students. Specifically, the behavioral features of college students were extracted, and subject to principal component analysis (PCA). Based on these features, the correlation between student score and social relation was analyzed, and used to predict the English scores of college students. Experimental results show that our method can accurately reflect the relationship between the social behaviors and course scores of college students. ? 2020 Lavoisier. All rights reserved.