Sound symbolism in Japanese names: Machine learning approaches to gender classification

Abstract

This study investigates the sound symbolic expressions of gender in Japanese names with machine learning algorithms. The main goal of this study is to explore how gender is expressed in the phonemes that make up Japanese names and whether systematic sound-meaning mappings, observed in Indo-European languages, extend to Japanese. In addition to this, this study compares the performance of machine learning algorithms. Random Forest and XGBoost algorithms are trained using the sounds of names and the typical gender of the referents as the dependent variable. Each algorithm is cross-validated using k-fold cross-validation (28 folds) and tested on samples not included in the training cycle. Both algorithms are shown to be reasonably accurate at classifying names into gender categories; however, the XGBoost model performs significantly better than the Random Forest algorithm. Feature importance scores reveal that certain sounds carry gender information. Namely, the voiced bilabial nasal /m/ and voiceless velar consonant /k/ were associated with femininity, and the high front vowel /i/ were associated with masculinity. The association observed for /i/ and /k/ stand contrary to typical patterns found in other languages, suggesting that Japanese is unique in the sound symbolic expression of gender. This study highlights the importance of considering cultural and linguistic nuances in sound symbolism research and underscores the advantage of XGBoost in capturing complex relationships within the data for improved classification accuracy. These findings contribute to the understanding of sound symbolism and gender associations in language.

Fig 1. Vowel inventory of Japanese [56].