Laugh, Relate, Engage: Stylized Comment Generation for Short Videos

• URL: http://arxiv.org/abs/2511.03757v1
• Date: Wed, 05 Nov 2025 07:00:22 GMT
• Title: Laugh, Relate, Engage: Stylized Comment Generation for Short Videos
• Authors: Xuan Ouyang, Senan Wang, Bouzhou Wang, Siyuan Xiahou, Jinrong Zhou, Yuekang Li,
• Abstract summary: We introduce LOLGORITHM, a modular multi-agent system (MAS) designed for controllable short-video comment generation.<n>The system integrates video segmentation, contextual and affective analysis, and style-aware prompt construction.<n>It supports six distinct comment styles: puns (homophones), rhyming, meme application, sarcasm (irony), plain humor, and content extraction.
• Score: 7.225213386393225
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Short-video platforms have become a central medium in the modern Internet landscape, where efficient information delivery and strong interactivity are reshaping user engagement and cultural dissemination. Among the various forms of user interaction, comments play a vital role in fostering community participation and enabling content re-creation. However, generating comments that are both compliant with platform guidelines and capable of exhibiting stylistic diversity and contextual awareness remains a significant challenge. We introduce LOLGORITHM, a modular multi-agent system (MAS) designed for controllable short-video comment generation. The system integrates video segmentation, contextual and affective analysis, and style-aware prompt construction. It supports six distinct comment styles: puns (homophones), rhyming, meme application, sarcasm (irony), plain humor, and content extraction. Powered by a multimodal large language model (MLLM), LOLGORITHM directly processes video inputs and achieves fine-grained style control through explicit prompt markers and few-shot examples. To support development and evaluation, we construct a bilingual dataset using official APIs from Douyin (Chinese) and YouTube (English), covering five popular video genres: comedy skits, daily life jokes, funny animal clips, humorous commentary, and talk shows. Evaluation combines automated metrics originality, relevance, and style conformity with a large-scale human preference study involving 40 videos and 105 participants. Results show that LOLGORITHM significantly outperforms baseline models, achieving preference rates of over 90% on Douyin and 87.55% on YouTube. This work presents a scalable and culturally adaptive framework for stylized comment generation on short-video platforms, offering a promising path to enhance user engagement and creative interaction.

Related papers

• Semantic Frame Aggregation-based Transformer for Live Video Comment Generation [10.604889675520925]
  We present a novel model for generating contextually appropriate video comments on live video streams.<n>We use CLIP's visual-text multimodal knowledge to assign weights to video frames based on their semantic relevance to ongoing viewer conversation.<n>Our comment decoder with a cross-attention mechanism ensures that the generated comment reflects contextual cues from both chats and video.
  arXiv  Detail & Related papers  (2025-10-30T20:01:04Z)
• TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation [76.48551690189406]
  We present TalkCuts, a large-scale dataset designed to facilitate the study of multi-shot human speech video generation.<n>TalkCuts offers 164k clips totaling over 500 hours of high-quality human speech videos with diverse camera shots, including close-up, half-body, and full-body views.<n>The dataset includes detailed textual descriptions, 2D keypoints and 3D SMPL-X motion annotations, covering over 10k identities, enabling multimodal learning and evaluation.
  arXiv  Detail & Related papers  (2025-10-08T17:16:09Z)
• V-HUB: A Visual-Centric Humor Understanding Benchmark for Video LLMs [72.59885036868499]
  v-HUB is a visual-centric video humor understanding benchmark.<n>Each video clip is paired with rich annotations, including captions, descriptions, and explanations.<n>We evaluate a diverse set of MLLMs, from specialized Video-LLMs to versatile OmniLLMs that can process audio.
  arXiv  Detail & Related papers  (2025-09-30T04:33:52Z)
• From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding [16.83482677439144]
  We propose a human-inspired automatic video editing framework (HIVE)<n>Our approach incorporates character extraction, dialogue analysis, and narrative summarization through multimodal large language models.<n>Our framework consistently outperforms existing baselines across both general and advertisement-oriented editing tasks.
  arXiv  Detail & Related papers  (2025-07-03T16:54:32Z)
• HOTVCOM: Generating Buzzworthy Comments for Videos [49.39846630199698]
  This study introduces textscHotVCom, the largest Chinese video hot-comment dataset, comprising 94k diverse videos and 137 million comments. We also present the textttComHeat framework, which synergistically integrates visual, auditory, and textual data to generate influential hot-comments on the Chinese video dataset.
  arXiv  Detail & Related papers  (2024-09-23T16:45:13Z)
• LiveChat: Video Comment Generation from Audio-Visual Multimodal Contexts [8.070778830276275]
  We create a large-scale audio-visual multimodal dialogue dataset to facilitate the development of live commenting technologies. The data is collected from Twitch, with 11 different categories and 575 streamers for a total of 438 hours of video and 3.2 million comments. We propose a novel multimodal generation model capable of generating live comments that align with the temporal and spatial events within the video.
  arXiv  Detail & Related papers  (2023-10-01T02:35:58Z)
• A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot [67.00455874279383]
  We propose verbalizing long videos to generate descriptions in natural language, then performing video-understanding tasks on the generated story as opposed to the original video. Our method, despite being zero-shot, achieves significantly better results than supervised baselines for video understanding. To alleviate a lack of story understanding benchmarks, we publicly release the first dataset on a crucial task in computational social science on persuasion strategy identification.
  arXiv  Detail & Related papers  (2023-05-16T19:13:11Z)
• 3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos [72.69052180249598]
  We present 3MASSIV, a multilingual, multimodal and multi-aspect, expertly-annotated dataset of diverse short videos extracted from short-video social media platform - Moj. 3MASSIV comprises of 50k short videos (20 seconds average duration) and 100K unlabeled videos in 11 different languages. We show how the social media content in 3MASSIV is dynamic and temporal in nature, which can be used for semantic understanding tasks and cross-lingual analysis.
  arXiv  Detail & Related papers  (2022-03-28T02:47:01Z)
• CLUE: Contextualised Unified Explainable Learning of User Engagement in Video Lectures [6.25256391074865]
  We propose a new unified model, CLUE, which learns from the features extracted from public online teaching videos. Our model exploits various multi-modal features to model the complexity of language, context information, textual emotion of the delivered content.
  arXiv  Detail & Related papers  (2022-01-14T19:51:06Z)
• Multimodal Matching Transformer for Live Commenting [97.06576354830736]
  Automatic live commenting aims to provide real-time comments on videos for viewers. Recent work on this task adopts encoder-decoder models to generate comments. We propose a multimodal matching transformer to capture the relationships among comments, vision, and audio.
  arXiv  Detail & Related papers  (2020-02-07T07:19:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.