HotComment: A Benchmark for Evaluating Popularity of Online Comments

arXiv cs.AI / 4/29/2026

📰 NewsModels & Research

共有:

Key Points

The paper introduces HotComment, a multimodal benchmark (video + text) designed to measure the popularity of online comments more comprehensively than existing approaches.
It breaks evaluation into three enhanced components: Content Quality (semantic similarity to human ground truth with interpretable dimensions), Popularity Prediction (learning from real-world interaction trends), and User Behavior Simulation (agent-based modeling to approximate engagement scores).
To address style differences across platforms and communities, the work proposes StyleCmt, which aligns multiple stylistic dimensions to amplify socially resonant expressions and suppress incongruent ones.
The benchmark aims to better capture how linguistic quality, emotional resonance, and community-specific stylistic preferences jointly influence which comments become popular.

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.