Analyzing User Reviews on Digital Detox Apps: A Text Mining and Sentiment Analysis Approach

Abstract

Due to the growing concerns around problematic smartphone use and its negative impact, there is a rising interest in digital detox. While many digital detox apps have been developed in recent years, there is still limited understanding of the long-term effectiveness of digital detox applications and the attitude of people towards these apps. This study fills this gap by identifying the topics that people post in their reviews on the Google Play Store about digital detox apps and the emotion-based sentiment of those reviews. A total of 3500 reviews of 25 digital detox apps were collected from the Google Play Store using a scraping tool called “Parsehub.” Data was analyzed using R studio. Sentiment analysis results suggest that positive sentiments dominated the data frame. “Trust” and “anticipation” were the two most expressed emotions in the reviews. Regression analysis confirmed that sentiment scores could explain the ratings of the apps. Through LDA topic modeling four major topics of the reviews were identified and are discussed in detail in the later section of the research paper. The findings of this study may help app developers and marketers improve digital detox apps so that people can learn and practice mindful smartphone use with the help of these apps. This study fills a gap in digital detox research by adopting a new methodological approach and procedure since it combines text mining, sentiment analysis (NRC Lexicon using Syuzhet package), regression analysis, and LDA topic modeling. To the best of our knowledge, this is the first study which uses this research approach in the context of digital detox apps.