Data-Driven Interaction Review of an Ed-Tech Application

Abstract

Smile and Learn is an Ed-Tech company that runs a smart library with more that100 applications, games and interactive stories, aimed at children aged two to 10 and their families.The platform gathers thousands of data points from the interaction with the system to subsequentlyoffer reports and recommendations. Given the complexity of navigating all the content, the libraryimplements a recommender system. The purpose of this paper is to evaluate two aspects of such systemfocused on children: the influence of the order of recommendations on user exploratory behavior, andthe impact of the choice of the recommendation algorithm on engagement. The assessment, based ondata collected between 15 October 2018 and 1 December 2018, required the analysis of the number ofclicks performed on the recommendations depending on their ordering, and an A/B/C testing wheretwo standard recommendation algorithmswere comparedwith a randomrecommendation that servedas baseline. The results suggest a direct connection between the order of the recommendation and theinterest raised, and the superiority of recommendations based on popularity against other alternatives.