Proceedings of the Annual Conference of JSAI
Online ISSN : 2758-7347
36th (2022)
Session ID : 4N1-GS-3-03
Conference information

A Large Scale Web-Based Study of Japanese Vocabulary Size Estimation Test
Based on Word Familiarity Database, Reiwa edition
*Sanae FUJITATessei KOBAYASHI
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract

We investigated word familiarity and constructed a Word Familiarity Database Reiwa edition, which consists of about 163,000 words. By selecting test words based on word familiarity, we can estimate the approximate number of vocabulary, simply by asking people to indicate whether or not they know a small number of words. Then, we created a vocabulary-size estimation test based on the Word Familiarity Database Reiwa edition, and have made it available on the Web since June 4, 2020. Nearly two years have passed since its release, and the total number of users has exceeded 70,000. In this paper, we introduce a method for selecting test words and propose a new method for vocabulary-size estimation. In addition, we analyze the results of vocabulary-size estimation using Web logs. In particular, we show how the vocabulary-size changes with age and how the released three tests differ.

Content from these authors
© 2022 The Japanese Society for Artificial Intelligence
Previous article Next article
feedback
Top