{"title":"Forecasting Reading Anxiety to Promote Reading Performance Based on Annotation Behavior","authors":"Tingda Lu, Mi Lin, Chih-Ming Chen, Jhih-Hao Wu","doi":"10.1109/COMPSACW.2013.132","DOIUrl":null,"url":null,"abstract":"To reduce effectively the reading anxiety of learners while reading English articles, a C4.5 decision tree, a widely used data mining technique, was used to develop a personalized reading anxiety prediction model (PRAPM) based on individual learners' reading annotation behavior in a collaborative digital reading annotation system. In addition to forecasting immediately the reading anxiety levels of learners, the proposed PRAPM can be used to identify the key factors that cause reading anxiety based on the fired prediction rules determined by the developed decision tree. By understanding these key factors that cause reading anxiety, instructors can apply reading strategies to reduce reading anxiety, thus promoting English-language reading performance. To assess whether the proposed PRAPM can assist instructors in reducing the reading anxiety of learners, this study applies the quasi-experimental method to compare the learning performance of three learning groups, which are supported by a collaborative digital reading annotation system with different learning mechanisms to reduce reading anxiety. The control group, experimental group A and experimental group B conducted the same English reading activity. However, each group was given a collaborative digital reading annotation system with individual annotations, cooperative annotations, and cooperative annotation with the instructor's support to reduce reading anxiety by proposed PRAPM. Experimental results indicate that the average correct prediction rate of the proposed PRAPM in identifying the reading anxiety levels of learners was as high as 70%. The online instructor who applied reading assistive strategies based on the mining factors that affect reading anxiety from the proposed PRAPM can significantly reduce the reading anxiety of male learners in the experimental group B, showing that gender difference existed, and the online instructor's interaction with the male learners of the experimental group B indeed helped reduce the reading anxiety.","PeriodicalId":152957,"journal":{"name":"2013 IEEE 37th Annual Computer Software and Applications Conference Workshops","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE 37th Annual Computer Software and Applications Conference Workshops","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COMPSACW.2013.132","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
To reduce effectively the reading anxiety of learners while reading English articles, a C4.5 decision tree, a widely used data mining technique, was used to develop a personalized reading anxiety prediction model (PRAPM) based on individual learners' reading annotation behavior in a collaborative digital reading annotation system. In addition to forecasting immediately the reading anxiety levels of learners, the proposed PRAPM can be used to identify the key factors that cause reading anxiety based on the fired prediction rules determined by the developed decision tree. By understanding these key factors that cause reading anxiety, instructors can apply reading strategies to reduce reading anxiety, thus promoting English-language reading performance. To assess whether the proposed PRAPM can assist instructors in reducing the reading anxiety of learners, this study applies the quasi-experimental method to compare the learning performance of three learning groups, which are supported by a collaborative digital reading annotation system with different learning mechanisms to reduce reading anxiety. The control group, experimental group A and experimental group B conducted the same English reading activity. However, each group was given a collaborative digital reading annotation system with individual annotations, cooperative annotations, and cooperative annotation with the instructor's support to reduce reading anxiety by proposed PRAPM. Experimental results indicate that the average correct prediction rate of the proposed PRAPM in identifying the reading anxiety levels of learners was as high as 70%. The online instructor who applied reading assistive strategies based on the mining factors that affect reading anxiety from the proposed PRAPM can significantly reduce the reading anxiety of male learners in the experimental group B, showing that gender difference existed, and the online instructor's interaction with the male learners of the experimental group B indeed helped reduce the reading anxiety.