Crowdsourced exploration of mobile app features: a case study of the fort mcmurray wildfire

The ubiquity of mobile devices has led to unprecedented growth in not only the usage of apps, but also their capacity to meet people's needs. Smart phones take on a heightened role in emergency situations, as they may suddenly be among their owner's only possessions and resources. The 2016 wildfire in Fort McMurray, Canada, intrigued us to study the functionality of the existing apps by analyzing social media information. We investigated a method to suggest features that are useful for emergency apps. Our proposed method called MAPFEAT, combines various machine learning techniques to analyze tweets in conjunction with crowdsourcing and guides an extended search in app stores to find currently missing features in emergency apps based on the needs stated in social media. MAPFEAT is evaluated by a real-world case study of the Fort McMurray wildfire, where we analyzed 69,680 unique tweets recorded over a period from May 2 nd to May 7 th , 2016. We found that (i) existing wildfire apps covered a range of 28 features with not all of them being considered helpful or essential, (ii) a large range of needs articulated in tweets can be mapped to features existing in non-emergency related apps, and (iii) MAPFEAT's suggested feature set is better aligned with the needs expressed by general public. Only six of the features existing in wildfire apps is among top 40 crowdsourced features explored by MAPFEAT, with the most important one just ranked 13 th . By using MAPFEAT, we proactively understand victims' needs and suggest mobile software support to the people impacted. MAPFEAT looks beyond the current functionality of apps in the same domain and extracts features using variety of crowdsourced data.