LOLGORITHM: Funny Comment Generation Agent For Short Videos

TL;DR

LOLGORITHM is a modular multi-agent framework that generates culturally and linguistically appropriate comments for short videos, enhancing engagement on platforms like YouTube and Douyin.

Contribution

It introduces a novel multi-agent system supporting six comment styles, with a bilingual dataset and evaluation demonstrating superior human preference over baselines.

Findings

Outperforms baseline methods in human preference tests with over 80% approval.

Supports six controllable comment styles for diverse engagement.

Constructed a bilingual dataset of over 16,000 comments across five categories.

Abstract

Short-form video platforms have become central to multimedia information dissemination, where comments play a critical role in driving engagement, propagation, and algorithmic feedback. However, existing approaches -- including video summarization and live-streaming danmaku generation -- fail to produce authentic comments that conform to platform-specific cultural and linguistic norms. In this paper, we present LOLGORITHM, a novel modular multi-agent framework for stylized short-form video comment generation. LOLGORITHM supports six controllable comment styles and comprises three core modules: video content summarization, video classification, and comment generation with semantic retrieval and hot meme augmentation. We further construct a bilingual dataset of 3,267 videos and 16,335 comments spanning five high-engagement categories across YouTube and Douyin. Evaluation combining automatic scoring and large-scale human preference analysis demonstrates that LOLGORITHM consistently outperforms baseline methods, achieving human preference selection rates of 80.46\% on YouTube and 84.29\% on Douyin across 107 respondents. Ablation studies confirm that these gains are attributable to the framework architecture rather than the choice of backbone LLM, underscoring the robustness and generalizability of our approach.