This paper develops a novel unsupervised algorithm for belief representation learning in polarized networks that (i) uncovers the latent dimensions of the underlying belief space and (ii) jointly embeds users and content items (that they interact with) into that space in a manner that facilitates a number of downstream tasks, such as stance detection, stance prediction, and ideology mapping. Inspired by total correlation in information theory, we propose a novel Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e.g., posts that represent user views) into an appropriate disentangled latent space. In order to better disentangle orthogonal latent variables in that space, we develop total correlation regularization, PI control module, and adopt rectified Gaussian Distribution for the latent space. The latent representation of users and content can then be used to quantify their ideological leaning and detect/predict their stances on issues. We evaluate the performance of the proposed InfoVGAE on three real-world datasets, of which two are collected from Twitter and one from U.S. Congress voting records. The evaluation results show that our model outperforms state-of-the-art unsupervised models and produce comparable result with supervised models. We also discuss stance prediction and user ranking within ideological groups.

本论文提出了一个新颖的针对极化网络的无监督算法，能够识别潜在维度、将用户和内容项目结合到一个合适的解缠结的潜在空间中，并且能够定量权衡他们在意识形态上的倾向，探究他们在问题上的立场，是一个在用户聚类错误降低10.5％，提高12.1％的F1得分，同时与监督模型产生可比较的结果的模型。

无监督信息论变分图自编码器的信念表示学习