# LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts

arXiv: https://arxiv.org/abs/1809.04938 · HTML: https://mlsanity.com/paper/1809.04938/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2018.

## Built on by (most cited first, 14 of 14)

- [Spatial-Semantic Collaborative Cropping for User Generated Content](https://mlsanity.com/paper/2401.08086/) (2024)
- [ViCo: Engaging Video Comment Generation with Human Preference Rewards](https://mlsanity.com/paper/2308.11171/) (2023)
- [Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting](https://mlsanity.com/paper/2404.12782/) (2024)
- [TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World](https://mlsanity.com/paper/2301.05880/) (2023)
- [HOTVCOM: Generating Buzzworthy Comments for Videos](https://mlsanity.com/paper/2409.15196/) (2024)
- [Knowledge Enhanced Model for Live Video Comment Generation](https://mlsanity.com/paper/2304.14657/) (2023)
- [VTC: Improving Video-Text Retrieval with User Comments](https://mlsanity.com/paper/2210.10820/) (2022)
- [HotComment: A Benchmark for Evaluating Popularity of Online Comments](https://mlsanity.com/paper/2604.25614/) (2026)
- [LiveChat: Video Comment Generation from Audio-Visual Multimodal Contexts](https://mlsanity.com/paper/2311.12826/) (2023)
- [InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos](https://mlsanity.com/paper/2608.01157/) (2026)
- [Enhancing Multimodal Affective Analysis with Learned Live Comment Features](https://mlsanity.com/paper/2410.16407/) (2024)
- [Semantic Frame Aggregation-based Transformer for Live Video Comment Generation](https://mlsanity.com/paper/2510.26978/) (2025)
- [Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms](https://mlsanity.com/paper/2606.04701/) (2026)
- [Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams](https://mlsanity.com/paper/2609.27303/) (2026)

## Abstract (arXiv)

We introduce the task of automatic live commenting. Live commenting, which is also called `video barrage', is an emerging feature on online video sites that allows real-time comments from viewers to fly across the screen like bullets or roll at the right side of the screen. The live comments are a mixture of opinions for the video and the chit chats with other comments. Automatic live commenting requires AI agents to comprehend the videos and interact with human viewers who also make the comments, so it is a good testbed of an AI agent's ability of dealing with both dynamic vision and language. In this work, we construct a large-scale live comment dataset with 2,361 videos and 895,929 live comments. Then, we introduce two neural models to generate live comments based on the visual and textual contexts, which achieve better performance than previous neural baselines such as the sequence-to-sequence model. Finally, we provide a retrieval-based evaluation protocol for automatic live commenting where the model is asked to sort a set of candidate comments based on the log-likelihood score, and evaluated on metrics such as mean-reciprocal-rank. Putting it all together, we demonstrate the first `LiveBot'.