One-Model-Connects-All: A Unified Graph Pre-Training Model for Online Community Modeling

Ruoxue Ma, Jiarong Xu, Xinnong Zhang, Haozhe Zhang, Zuyu Zhao, Qi Zhang, Xuanjing Huang, zhongyu wei

Submission Type: Regular Long Paper

Submission Track: Computational Social Science and Cultural Analytics

Submission Track 2: NLP Applications

Keywords: community, pre-train, graph

Abstract: Online community is composed of communities, users, and user-generated textual content, with rich information that can help us solve social problems. Previous research hasn't fully utilized these three components and the relationship among them. What's more, they can't adapt to a wide range of downstream tasks. To solve these problems, we focus on a framework that simultaneously considers communities, users, and texts. And it can easily connect with a variety of downstream tasks related to social media. Specifically, we use a ternary heterogeneous graph to model online communities. Text reconstruction and edge generation are used to learn structural and semantic knowledge among communities, users, and texts. By leveraging this pre-trained model, we achieve promising results across multiple downstream tasks, such as violation detection, sentiment analysis, and community recommendation. Our exploration will improve online community modeling.

Submission Number: 5035