Follow Your Heart or Listen to Users? The Case of Mobile App Design

• 成果类型: Article
• 署名作者: Aditya, Subrahmanyam; Agarwal, Ashish; Barua, Anitesh
• 署名单位: National University of Singapore; University of Texas System; University of Texas Austin
• 刊物名称: INFORMATION SYSTEMS RESEARCH
• ISSN/ISSBN: 1047-7047
• DOI: 10.1287/isre.2023.0060
• 发表日期: 2025
• 关键词: information-technology; measurement error; product; INNOVATION; performance; strategies; imitation; MARKETS; demand; ideas

摘要

Firms strive to improve their products over time to compete effectively in the market. Typically, firms update their products by adding novel or differentiating features or by imitating competitors. With the ubiquity of social media, there is also the opportunity to obtain customer input on their preferred features for a product. In the case of mobile apps, user feedback in the form of reviews may include suggestions of novel features or those that are already present in competing apps but not in the focal app. Leveraging the information contained in reviews and version release notes of iOS apps, we develop a deep learning-based natural language processing approach to identify four types of app features: developer-initiated novel, developer-initiated imitative, user-suggested novel, and user-suggested imitative. We evaluate the impact of these feature categories on app demand. Our results demonstrate that only developer-initiated novel and user-suggested imitative features help increase app demand. We also find that the impact of user-suggested novel features is negative. However, this negative effect is limited to features that are contextually distant from user suggestions, whereas contextually close implementations have a positive effect. Although we observe that the aggregate impact of developer-initiated imitative features is statistically insignificant, features that are slightly modified from the original apps do have a positive effect on demand. The primary contribution of our study is to investigate user reviews as a source of ideas for new features and to evaluate their performance impacts relative to those of developer-initiated features.