Incomplete Label Uncertainty Estimation for Petition Victory Prediction with Dynamic Features
Junxiang Wang, Yuyang Gao, Andreas E Züfle, Jingyuan Yang, Liang Zhao · 2018
It is important for decision-makers to effectively and proactively differentiate the significance of various public concerns, and address them with optimal strategy under the limited resources. Online Petition Platforms (OPPs) are replacing traditional social and market surveys for the advantages of low financial cost and high-fidelity social indicators. Despite benefits from OPPs, the raw information from millions of petition signers can easily overwhelm decision makers. In addition, spatio-temporal and semantic dissemination patterns increase the complexity of such OPP data. These two aspects show the necessity of a framework that learns from all available data, which is encoded by dynamic representation of features, to predict whether a petition will successfully lead to a change by decision makers. To build such framework, we need to overcome several challenges including: 1) missing values in dynamic features; 2) strong uncertainty in petition prediction; 3) unknown labels for ongoing petitions and 4) Scalability regarding increasing features and petitions. To address these difficulties simultaneously, we propose a novel chain-structure Multi-task Learning framework with Uncertainty Estimation (MLUE) to predict potentially victorious petitions, which facilitates the process of decision making. Specifically, we divide data into different Increasing Feature Blocks (IFBs) according to missing patterns. Besides, we propose a novel criterion to estimate uncertainty in order to label petitions as early as possible. To handle the challenge of scalability, we present an Expectation-Maximization (EM)-based algorithm to optimize the non-convex objective function accurately and efficiently. Various experiments on six petition datasets demonstrate that our MLUE outperformed other baselines by a large margin.