Effect of Bayesian Student Modeling on Academic Achievement in Foreign Language Teaching (University Level English Preparatory School Example)

Abstract

Considering the increasing importance of adaptive approaches in CALL systems, this study implemented a machine learning based student modeling middleware with Bayesian networks. The profiling approach of the student modeling system is based on Felder and Silverman's Learning Styles Model and Felder and Soloman's Index of Learning Styles Questionnaire. The questionnaire was adapted to Turkish for this experimental study conducted with respect to the visual/verbal and active/reflective dimensions of the model. A topic in EFL was chosen for the learning content design, which was also carried into the digital domain and remastered as separate learning scenes for different learning styles. Computer software was also implemented to carry out the experimental learning processes. A quasi-experimental pre-test, post-test design was conducted with 46 volunteers, with 23 students assigned each to a control and an experimental group to compare academic achievement between student-based learning and conventional computer-based learning. No significant difference was found in academic achievement between the control and experimental groups after the experimental treatment. The diagnostic performance of the proposed student modeling system was also compared with performances from similar studies. This student modeling system had a successful prediction rate of 41% on the visual/verbal dimension and 54% on the active/reflective dimension, respectively.

The Construct Validity of Felder-Soloman Index of Learning Styles (ILS) for the Prospective Teachers

“…Despite that, sequential/global dimension had very low internal consistency reliability in the studies conducted with Turkish students and the current study had the lowest value (.20) for this dimension. The study conducted by Atman et al (2009) reported the highest reliability of sequential/global dimension of the ILS (Cited in Aslan, Öztürk and İnceoğlu, 2014). Additionally, comparing to the other dimensions, sequential/global dimension had almost the lowest internal consistency The Construct Validity of Felder-Soloman Index of Learning Styles (ILS) for the Prospective Teachers reliabilities in all studies showed on Table 5 regardless of being conducted in Turkey or not.…”

Data mining in foreign language learning

“…However, there are some papers in which DM is used for each isolated application, for instance learner motivation (13% of papers), learning styles (8%), provide feedback for instructors (9%), detecting language anxiety (6%), predicting performance (14%), L2 orientations (8%), language reading comprehension (5%), and detecting grammar issues and assessment (7%). In this analysis, the DM applications most frequently used in the context of FLL are: Predicting performance (Linck et al, 2013;Seker, 2016;Swanson et al, 2016;Wang & Cheng, 2016;Whitehill & Movellan, 2018), learner motivation (Apple, Falout, & Hill, 2013;Li & Zhou, 2017;Saeed et al, 2014;Tajeddin & Moghadam, 2012), provide feedback for instructors (Coskun & Mutlu, 2017;Jiang & Lee, 2017;Kaoropthai, Natakuatoong, & Cooharojananone, 2016;Kieffer & Lesaux, 2012;Rodriguez & Shepard, 2013;Zhao et al, 2015), learning styles (Aslan et al, 2014;Farrington et al, 2015;Hamedi, Pishghadam, & Ghazanfari, 2016;Hsiao, Lan, Kao, & Li, 2017), detecting language anxiety (Baghaei & Ravand, 2015;Cakir & Solak, 2014;Guntzviller et al, 2016;Martin & Valdivia, 2017), and L2 orientations (Allen et al, 2014;Lou & Noels, 2017;Maqsood et al, 2016;Winke, 2013). Figures 8 and 9 show the correlation between the educational level in where the articles mentioned to have developed their proposal and the EDM methods and applications that has been used, respectively.…”

A systematic review of empirical studies on computer-assisted language learning

“…The technological learning contexts are any analogue or digital technologies, educational applications, software, or e-learning services developed for Technology Enhanced Learning. The technological tools used in the studies examined were as follows: Summary writing online tool (n=1) (Chew et al,2020), Intelligent Personal Asistants (n=2) (Chang & Hsu, 2011;Dizon, 2020), English File Pronunciation Application (n=1) (Fouz-González, 2020), Recognition Device (n=1) (Hwang et al 2019), Podcasts (n=1) (Fouz-González, 2019), E-learning Platforms (n=1) (Zibin & Altakhaineh, 2019), Outdoor U-learning Devices and Indoor Call Applications (n=2) (Chang, 2018;Chang et al, 2018), Electronic/Computer Glosses (n=2) (Bowles, 2004;Lee et al, 2016), Online Dictionary (n=1) (Karras, 2016), Instructional Streaming Videos (n=1) (Huang & Chuang, 2016), CLSDRI-A Remedial Instruction System (n=1) (Hsiao et al, 2016), Google Docs (n=1) (Bikowski & Vithanage, 2016), Laptop Computer with a Headset (n=1) (Alvarez-Marinelli et al, 2016), Online Feedback through CSCL System(n=2) (Lan et al, 2015;Yang, 2016), Instructional Lexis Software LEXISBOARD (n=1) (Mirzaei et al, 2016), Microsoft Word Office (n=1) (Zaini & Mazdayasna, 2015), Online Feedback through E-mail (n=1) (Alipanahi & Mahmoodi, 2015), Virtual World (n=1) (Luccioni et al, 2015), Captions/Eye Tracking System (n=1) (Hsu et al, 2014), Bayesian Network (n=1) (Aslan et al, 2014), LMS (n=1) (Başal & Gürol, 2014), Computer Assisted Tools (CATBI-CAFFI) (n=1) (Arslanyılmaz, 2013), Web Discussion System (n=1) (Chang et al, 2013), Captions (n=2) (Lwo & Lin, 2012;Shea, 2000), Voice over Instant Messaging System-VOIM (n=1) (Yang et al, 2012), Digital videos (n=1) (Zottmann et al, 2012), Verbal Oral Feedback systems (n= 1 (Özdener & Satar, 20...…”