Detecting Gamification in Breast Cancer Apps: an automatic methodology for screening purposes

TL;DR

This paper presents an automatic tool using logistic regression to detect gamification elements in breast cancer mobile apps, enabling large-scale analysis and research in health app design.

Contribution

The study introduces a novel predictive model for automatically identifying gamification in breast cancer apps based on app store descriptions.

Findings

High accuracy in detecting gamification elements

Effective screening of large app datasets

Validated model against expert assessments

Abstract

Breast cancer is the most common cancer in women both in developed and developing countries. More than half of all cancer mobile application concern breast cancer. Gamification is widely used in mobile software applications created for health-related services. Current prevalence of gamification in breast cancer apps is unknown and detection must be manually performed. The purpose of this study is to describe and produce a tool allowing automatic detection of apps which contain gamification elements and thus empowering researchers to study gamification using large data samples. Predictive logistic regression model was designed on data extracted from breast cancer apps' title and description text available in app stores. Model was validated comparing estimated and benchmark values, observed by gamification specialists. Study's outcome can be applied as a screening tool to efficiently identify gamification presence in breast cancer apps for further research.