{"title":"Early Warning Model for Learning based on Bidirectional LSTM","authors":"Yufan Li, Huifu Zhang","doi":"10.1109/ISCSIC54682.2021.00051","DOIUrl":null,"url":null,"abstract":"In this paper, we proposed a methodology and a model for identifying at-risk students. Our model is based on a deep bidirectional long short-term memory network(deep BiLSTM) and we applied it to the data from 2032 students. We carried out 2 experiments to predict students achievement at different steps of the semester, to test three data balancing techniques and to compare our model versus two classical classification algorithms. Results showed that our model was capable of identifying at-risk students at the middle of the semester and trustworthy to be an early warning model.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCSIC54682.2021.00051","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we proposed a methodology and a model for identifying at-risk students. Our model is based on a deep bidirectional long short-term memory network(deep BiLSTM) and we applied it to the data from 2032 students. We carried out 2 experiments to predict students achievement at different steps of the semester, to test three data balancing techniques and to compare our model versus two classical classification algorithms. Results showed that our model was capable of identifying at-risk students at the middle of the semester and trustworthy to be an early warning model.