Building Personalized Readability Equation and English Vocabulary List for Continued Reading Study in Comparison among Differently Proposed Algorithms
Abstract
The authors have developed REX, a web application for facilitating English reading study, for non-native speakers of English. REX has a function that personalizes their individual readability equations based on their study logs and that predicts the ease or difficulty of the texts provided. For a parameter of such equations, the rate of difficult words, which does not appear in the specified vocabulary list, is often used, as in some of the well-known readability formulas. On the other hand, we believe that the use of a static vocabulary list to produce its rate does not contribute to personalization, because each learner has different vocabularies. This triggered the authors to incorporate a new function to let learners click their unknown words while they are reading texts, play “English Word Game”, and further predict the status of known/unknown of the wordsin the designated vocabulary list. In this study, we will focus on new labeling algorithms and an experiment to evaluate whether the quality of labeling has been improved. Among the devised several algorithms (A to E), making comparisons is also attempted.
References
R. Flesch, “A new readability yardstick,” Journal of Applied Psychology, vol. 32, 1948, pp. 221-233.
E. Dale and J. Chall, “A formula for predicting reliability: instructions,” Educational Research Bulletin, vol. 27, 1948, pp. 37-54.
K. Norizuki, “In search of new dimensions for readability for Japanese learners of English,” Bulletin of Shizuoka Sangyo University, vol. 6, 2004, pp. 167-180.
H. Kiyokawa, “Development of a readability formula for high school and university students,” Studies of Language and Literature, Wayo Women’s University, 1988, vol. 21, pp. 43-63.
Y. Miyagishi, Y. Miyazaki, Y. Hasegawa, and T. Oshiro, “Effect of Continuous Language Learning and Personalization with the Use of Gamification,” 77th IPSJ Annual Conference, 2015, pp. (4)-847-848.
Y. Ehara, T. Ninomiya, N. Shimizu, and H. Nakagawa, “A reading support tool with prediction capability and its extension to readability measurement,” IPSJ 2010-NL-196(18), 2010, pp. 1-7.
M. Fukui and T. Ozawa, “Methodology for Developing an English Readability Index with Word and Idiom Difficulty Variables,” Journal of Japan Society of Educational Information, vol. 24, no. 3, 2009, pp. 15-22.
A.L. Uitdenbogerd, “Web readability and computer-assisted language learning,” Proc. of the 2006 Australasian Language Technology Workshop (ALTW2006), 2006, pp. 99-106.
Y. Miyazaki, T. Oshiro, and Y. Hasegawa, “Strategy toward Personalization with REX – Extracting Articles Suitable for Individual Learners,” 52nd LET Annual Conference, 2012, OP46.
SVL12000: http://www.alc.co.jp/vocgram/article/svl/ (date of access: May 20th, 2019)
T. Oshiro and Y. Miyazaki, “Proposing a Method to Personalize Readability Equations with REX - Development of a Parameter Estimation Method Suitable for Individual Learners and Its Effects –,” LET Chubu Bulletin, vol.24, 2013, pp.25-34.
TreeTagger: http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html (date of access: May 20th, 2019)
Weblio Dictionary: http://ejje.weblio.jp/ (date of access: May 20th, 2019)
H. N. Tra My, S. Suzuki, Y. Miyazaki, Building Personalized Readability Equation and Personalized English Vocabulary List for Continued Study, Proceedings of 6th IIAI International Congress on Advanced Applied Informatics, Learning Technologies and Learning Environments (LTLE2017), 2017, pp. 789-793.
