Samin Khan


2018

pdf bib
Is Nike female? Exploring the role of sound symbolism in predicting brand name gender
Sridhar Moorthy | Ruth Pogacar | Samin Khan | Yang Xu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Are brand names such as Nike female or male? Previous research suggests that the sound of a person’s first name is associated with the person’s gender, but no research has tried to use this knowledge to assess the gender of brand names. We present a simple computational approach that uses sound symbolism to address this open issue. Consistent with previous research, a model trained on various linguistic features of name endings predicts human gender with high accuracy. Applying this model to a data set of over a thousand commercially-traded brands in 17 product categories, our results reveal an overall bias toward male names, cutting across both male-oriented product categories as well as female-oriented categories. In addition, we find variation within categories, suggesting that firms might be seeking to imbue their brands with differentiating characteristics as part of their competitive strategy.