Xia Sun, S. Guo, Yi Gao, Jun Zhang, Xiaolin Xiao, Jun Feng
{"title":"Identification of urgent posts in MOOC discussion forums using an improved RCNN","authors":"Xia Sun, S. Guo, Yi Gao, Jun Zhang, Xiaolin Xiao, Jun Feng","doi":"10.1109/EDUNINE.2019.8875845","DOIUrl":null,"url":null,"abstract":"Although massive open online courses (MOOC) have successfully attracted a large number of learners, the low completion rate has severely hindered the development of MOOC. The complex and diverse information on the forum often makes many students' urgent problems unable to be solved in time. Therefore, how to identify the students' urgent posts from a large number of posts becomes a critical problem to be solved. This paper presents a model for identifying “urgent” posts that require immediate attention from the instructors. It is the first time deep learning methods have been applied to this task. We investigated different deep learning methods and proposed an improved recurrent convolutional neural networks to solve the problems of identifying posts. The experimental results show that our method outperforms state-of-the-art methods. The work has potential application across a range of platforms and can help teachers efficiently navigate their discussion forums so that timely intervention can support learning and potentially reduce dropout rates.","PeriodicalId":211092,"journal":{"name":"2019 IEEE World Conference on Engineering Education (EDUNINE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE World Conference on Engineering Education (EDUNINE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EDUNINE.2019.8875845","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12
Abstract
Although massive open online courses (MOOC) have successfully attracted a large number of learners, the low completion rate has severely hindered the development of MOOC. The complex and diverse information on the forum often makes many students' urgent problems unable to be solved in time. Therefore, how to identify the students' urgent posts from a large number of posts becomes a critical problem to be solved. This paper presents a model for identifying “urgent” posts that require immediate attention from the instructors. It is the first time deep learning methods have been applied to this task. We investigated different deep learning methods and proposed an improved recurrent convolutional neural networks to solve the problems of identifying posts. The experimental results show that our method outperforms state-of-the-art methods. The work has potential application across a range of platforms and can help teachers efficiently navigate their discussion forums so that timely intervention can support learning and potentially reduce dropout rates.