Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection

TL;DR

This paper introduces a dynamic deep graph convolutional network (D-DGCN) that automatically learns connections between online posts for more accurate personality trait prediction, avoiding unwarranted order assumptions of previous methods.

Contribution

The paper proposes a novel learn-to-connect approach with a dynamic multi-hop structure integrated into a DGCN for improved personality detection from online posts.

Findings

D-DGCN outperforms state-of-the-art baselines on Kaggle and Pandora datasets.

The dynamic multi-hop structure effectively captures relevant post connections.

End-to-end training enhances model performance and robustness.

Abstract

Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis. One of the challenges of this task is assembling information from various posts into an overall profile for each user. While many previous solutions simply concatenate the posts into a long document and then encode the document by sequential or hierarchical models, they introduce unwarranted orders for the posts, which may mislead the models. In this paper, we propose a dynamic deep graph convolutional network (D-DGCN) to overcome the above limitation. Specifically, we design a learn-to-connect approach that adopts a dynamic multi-hop structure instead of a deterministic structure, and combine it with a DGCN module to automatically learn the connections between posts. The modules of post encoder, learn-to-connect, and DGCN are jointly trained in an end-to-end manner. Experimental results on the Kaggle and Pandora datasets show the superior performance of D-DGCN to state-of-the-art baselines. Our code is available at https://github.com/djz233/D-DGCN.