What are Public Concerns about ChatGPT? A Novel Self-Supervised Neural Topic Model Tells You

TL;DR

This paper introduces a novel self-supervised neural topic model to analyze social media and user queries, effectively extracting high-quality public concerns about ChatGPT with improved interpretability and diversity.

Contribution

The paper proposes a new self-supervised neural topic model that outperforms existing methods in extracting public concerns from social media and user queries about ChatGPT.

Findings

The model achieves higher quality concern extraction.

It demonstrates improved interpretability and diversity.

Outperforms state-of-the-art approaches.

Abstract

The recently released artificial intelligence conversational agent, ChatGPT, has gained significant attention in academia and real life. A multitude of early ChatGPT users eagerly explore its capabilities and share their opinions on it via social media. Both user queries and social media posts express public concerns regarding this advanced dialogue system. To mine public concerns about ChatGPT, a novel Self-Supervised neural Topic Model (SSTM), which formalizes topic modeling as a representation learning procedure, is proposed in this paper. Extensive experiments have been conducted on Twitter posts about ChatGPT and queries asked by ChatGPT users. And experimental results demonstrate that the proposed approach could extract higher quality public concerns with improved interpretability and diversity, surpassing the performance of state-of-the-art approaches.