User Factor Adaptation for User Embedding via Multitask Learning

TL;DR

This paper introduces a multitask learning approach to adapt user embeddings by modeling language variation across different user interests, improving the representation's effectiveness in social media analysis.

Contribution

It proposes a novel user embedding model that captures interest-based language variability without supervision, addressing a gap in existing methods.

Findings

The model outperforms baselines in intrinsic clustering evaluations.

It improves performance on extrinsic text classification tasks.

User interest as a domain enhances user embedding quality.

Abstract

Language varies across users and their interested fields in social media data: words authored by a user across his/her interests may have different meanings (e.g., cool) or sentiments (e.g., fast). However, most of the existing methods to train user embeddings ignore the variations across user interests, such as product and movie categories (e.g., drama vs. action). In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets. We then propose a user embedding model to account for the language variability of user interests via a multitask learning framework. The model learns user language and its variations without human supervision. While existing work mainly evaluated the user embedding by extrinsic tasks, we propose an intrinsic evaluation via clustering and evaluate user embeddings by an extrinsic task, text classification. The experiments on the three English-language social media datasets show that our proposed approach can generally outperform baselines via adapting the user factor.