HotComment: A Benchmark for Evaluating Popularity of Online Comments

TL;DR

HotComment introduces a comprehensive multimodal benchmark for evaluating online comment popularity, considering content quality, trend prediction, and user engagement across diverse social media platforms.

Contribution

The paper presents HotComment, a novel benchmark integrating video and text modalities to assess comment popularity through multiple enhanced aspects and introduces StyleCmt for stylistic resonance modeling.

Findings

Benchmark effectively captures popularity factors across platforms.

Models trained on real interaction data predict engagement scores.

StyleCmt amplifies socially resonant comment styles.

Abstract

Online comments play a crucial role in shaping public sentiment and opinion dynamics on social media. However, evaluating their popularity remains challenging, not only because it depends on linguistic quality, originality, and emotional resonance, but also because stylistic preferences vary widely across platforms and user groups, causing the same comment to resonate differently in different communities. In this work, we present HotComment, a multimodal benchmark integrating video and text modalities that comprehensively quantifies popularity from three enhanced aspects: (1) Content Quality, which evaluates semantic similarity with ground-truth human comments and extends quality assessment through four interpretable dimensions; (2) Popularity Prediction, based on trends from models trained on real-world interaction data; and (3) User Behavior Simulation, which models the distribution of platform users and approximates \textbf{engagement scores} through an agent-based framework. Furthermore, we propose StyleCmt, inspired by social ripple effects, where multiple stylistic dimensions align to amplify socially resonant expressions and suppress incongruent ones.