An Algorithm to Evaluate Appropriateness of Still Images for Learning Concrete Nouns of a New Foreign Language

Mohammad Nehal HASNINE  Masatoshi ISHIKAWA  Yuki HIRAI  Haruko MIYAKODA  Keiichi KANEKO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.9   pp.2156-2164
Publication Date: 2017/09/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDP7463
Type of Manuscript: PAPER
Category: Educational Technology
Keyword: 
appropriate image,  concrete noun,  on-demand learning system,  AIVAS,  AIVAS-IRA,  

Full Text: PDF>>
Buy this Article




Summary: 
Vocabulary acquisition based on the traditional pen-and-paper approach is outdated, and has been superseded by the multimedia-supported approach. In a multimedia-supported foreign language learning environment, a learning material comprised of a still-image, a text, and the corresponding sound data is considered to be the most effective way to memorize a noun. However, extraction of an appropriate still image for a noun has always been a challenging and time-consuming process for learners. Learners' burden would be reduced if a system could extract an appropriate image for representing a noun. Therefore, the present study purposed to extract an appropriate image for each noun in order to assist foreign language learners in acquisition of foreign vocabulary. This study presumed that, a learning material created with the help of an appropriate image would be more effective in recalling memory compared to the one created with an inappropriate image. As the first step to finding appropriate images for nouns, concrete nouns have been considered as the subject of investigation. Therefore, this study, at first proposed a definition of an appropriate image for a concrete noun. After that, an image re-ranking algorithm has been designed and implemented that is able to extract an appropriate image from a finite set of corresponding images for each concrete noun. Finally, immediate-after, short- and long-term learning effects of those images with regard to learners' memory retention rates have been examined by conducting immediate-after, delayed and extended delayed posttests. The experimental result revealed that participants in the experimental group significantly outperformed the control group in their long-term memory retention, while no significant differences have been observed in immediate-after and in short-term memory retention. This result indicates that our algorithm could extract images that have a higher learning effect. Furthermore, this paper briefly discusses an on-demand learning system that has been developed to assist foreign language learners in creation of vocabulary learning materials.