A three-tiered semi supervised MTL mechanism and its application in dating apps

Abstract

A thorough understanding of the purpose of dating applications is crucial for service providers in order to optimize the design and user experience of the application. Despite the fact that many APPs prompt users to provide their usage purpose, many do not reveal this attribute. In this study, a three-module framework with semi-supervised and multitask learning mechanisms is proposed (T-SSMTL). Using the T-SSMTL mechanism, the purpose of the dating APP usage can be automatically inferred from the publicly available heterogeneous data of the user. The heterogeneous feature extraction module employs a number of techniques to extract semantic representations, maximizing the use of heterogeneous dating APP data. The multi-task module extracts task-specific knowledge for learning and solves the classification problem involving multiple labels. To alleviate the problem of label insufficiency, the semi-supervised module utilizes a large quantity of unlabeled data generated by users who do not report their usage purpose. A large-scale dataset containing 34,364 active dating APP users with their self-reported usage purpose, portrait image, profile, and posts was collected to evaluate the T-SSMTL framework. In the context of this dataset, simulation experiments have confirmed the efficacy of all three modules of the T-SSMTL framework, demonstrating its substantial theoretical significance as well as its excellent application value.