JNET: Learning User Representations via Joint Network Embedding and Topic Embedding

TL;DR

JNET introduces a joint embedding framework that captures user preferences by integrating social connections and content across multiple modalities into a shared latent space, improving prediction and recommendation tasks.

Contribution

The paper proposes a novel probabilistic model that jointly embeds users and topics into a shared latent space, effectively capturing complex user preferences from multi-modal data.

Findings

Outperforms state-of-the-art topic models in predicting unseen documents.

Improves link prediction accuracy for unseen nodes in social networks.

Enhances content recommendation, such as expert finding in StackOverflow.

Abstract

User representation learning is vital to capture diverse user preferences, while it is also challenging as user intents are latent and scattered among complex and different modalities of user-generated data, thus, not directly measurable. Inspired by the concept of user schema in social psychology, we take a new perspective to perform user representation learning by constructing a shared latent space to capture the dependency among different modalities of user-generated data. Both users and topics are embedded to the same space to encode users' social connections and text content, to facilitate joint modeling of different modalities, via a probabilistic generative framework. We evaluated the proposed solution on large collections of Yelp reviews and StackOverflow discussion posts, with their associated network structures. The proposed model outperformed several state-of-the-art topic modeling based user models with better predictive power in unseen documents, and state-of-the-art network embedding based user models with improved link prediction quality in unseen nodes. The learnt user representations are also proved to be useful in content recommendation, e.g., expert finding in StackOverflow.