Gender and User Feedback: An Exploratory Study
Emitzá Guzmán, Andres Paredes Rojas · 2019
Through app stores, users can submit feedback in the form of user reviews. Previous work has found that these reviews contain useful information such as user requirements and bug reports; and has presented approaches for automatically extracting this information. However, the differences in the feedback submitted by female and male users and its consequences with respect to algorithm bias have not been studied so far. In this paper, we take a step in this direction and report on an exploratory study that investigates 919 reviews from eight countries written by users with usernames identified by manual analysis as female or male. We contribute initial evidence of a possible imbalance in the number of female and males users writing app reviews. Additionally, while this disproportion exists, the analyzed feedback between female and male users is similar in terms of the expressed sentiment, content, rating, timing and length. These variables are commonly used when prioritizing user feedback for their later use during software evolution. Although we need a larger sample size to generalize our results, the similarities we report hint that gender bias is not a threat for feedback processing algorithms which exclusively take into account the characteristics studied in this work.