Comments Analysis in Social Media based on LLM Agents

Comments Analysis in Social Media based on LLM Agents

David Ramamonjisoa and Shuma Suzuki, Iwate Prefectural University, Japan

Abstract

This paper presents an online tool that automatically filters comments on YouTube based on agents built with Large Language Models (LLMs). We designed and built agent-based comment filtering system driven by the Langchain framework and LLMs to allow users a better interface for comments reading and discussions. Specialized agents can detect spam, toxic or constructive comments. Agents are constructed as modular Langchain object with memory components and reasoning tools to make a chain of thought by interacting with LLMs. In this paper, we provide a comprehensive detail of the agent architecture and workflow to fulfil its task. Additionally, we compare the generated result by the agents to our previous tool available online. We discuss our expectations regarding the future of the comment system.

Keywords

YouTube comments, Large Language Model, Agents, Filtering and Visualization

Full Text : https://aircconline.com/csit/papers/vol14/csit141003.pdf
Abstract URL : https://aircconline.com/csit/abstract/v14n10/csit141003.html
Volume URL : https://airccse.org/csit/V14N10.html

#youtubecomments #largelanguagemodel #agents #filtering #visualization #naturallanguageprocessing

Видео Comments Analysis in Social Media based on LLM Agents канала Computer Science & IT Conference Proceedings