Intelligent Exploration for User Interface Modules of Mobile App with Collective Learning

Abstract

A mobile app interface usually consists of a set of user interface modules. How to properly design these user interface modules is vital to achieving user satisfaction for a mobile app. However, there are few methods to determine design variables for user interface modules except for relying on the judgment of designers. Usually, a laborious post-processing step is necessary to verify the key change of each design variable. Therefore, there is a only very limited amount of design solutions that can be tested. It is timeconsuming and almost impossible to figure out the best design solutions as there are many modules. To this end, we introduce FEELER, a framework to fast and intelligently explore design solutions of user interface modules with a collective machine learning approach. FEELER can help designers quantitatively measure the preference score of different design solutions, aiming to facilitate the designers to conveniently and quickly adjust user interface module. We conducted extensive experimental evaluations on two real-life datasets to demonstrate its applicability in real-life cases of user interface module design in the Baidu App, which is one of the most popular mobile apps in China.

Mobile User Interface Adaptation Based on Usability Reward Model and Multi-Agent Reinforcement Learning

“…The result of the 𝟙𝟙 successi function is [0, 1]. f the agent 𝑠𝑠 for each parameter 𝑖𝑖 without considering an also be used in determining the quality of agent ac-𝑟𝑟 𝑠𝑠𝑠𝑠𝑖𝑖𝑎𝑎𝑖𝑖 = 〈𝑟𝑟 𝑠𝑠𝑖𝑖 〉, (6) trate how the reward is computed using expressions (4), a multi-agent environment of a mobile kitchen user inrics will allow expanding the reward model components ptive interface. Table 2 presents popular metrics that can model.…”

“…𝑟𝑟 𝑠𝑠𝑠𝑠𝑖𝑖𝑎𝑎𝑖𝑖 = 〈𝑟𝑟 𝑠𝑠𝑖𝑖 〉, (6 In Section 4, we will demonstrate how the reward is computed using expressions (4 (5), and (6) using the example of a multi-agent environment of a mobile kitchen user in terface. Measurable usability metrics will allow expanding the reward model component to enhance the quality of the adaptive interface.…”

“…On average, a typical user installs about 100 applications on their mobile device but uses no more than 50 of them in a month and less than 10 apps every day [3,4]. It is assumed that predictive adaptation technologies for mobile user interfaces will significantly reduce the redundancy of applications, functions, and data and greatly increase the speed of information processing by the user [5,6].…”