Collaborative AI in Sentiment Analysis: System Architecture, Data Prediction and Deployment Strategies

TL;DR

This study introduces a collaborative AI framework designed to efficiently distribute and resolve tasks across various AI systems to address challenges of integrating diverse AI models for processing complex multimodal data and the associated high costs of feature extraction.

Abstract

The advancement of large language model (LLM) based artificial intelligence technologies has been a game-changer, particularly in sentiment analysis. This progress has enabled a shift from highly specialized research environments to practical, widespread applications within the industry. However, integrating diverse AI models for processing complex multimodal data and the associated high costs of feature extraction presents significant challenges. Motivated by the marketing oriented software development +needs, our study introduces a collaborative AI framework designed to efficiently distribute and resolve tasks across various AI systems to address these issues. Initially, we elucidate the key solutions derived from our development process, highlighting the role of generative AI models like \emph{chatgpt}, \emph{google gemini} in simplifying intricate sentiment analysis tasks into manageable, phased objectives. Furthermore, we present a detailed case study utilizing our collaborative AI system in edge and cloud, showcasing its effectiveness in analyzing sentiments across diverse online media channels.

Figures (7)

• Figure 1: Sentiment analysis is highly valued in today's market. People utilize diverse media channels to interpret multimodal data for the analysis of market acceptance of products or services.
• Figure 2: Cutting-edge sentiment analysis solutions employing diverse AI technologies to analyze text, images, and sound, then computing sentiment-related scores to realize public opinion analysis or AI-based consulting.
• Figure 3: The proposed architecture of the Co-AI sentiment analysis system, featuring components such as a chatbot interface, report writing agent, record databases, and a crawler agent, designed to compile sentiment analysis reports on past, present, and future events.
• Figure 4: Interface for Configuring and Reviewing Sentiment Analysis Reports.
• Figure 5: Development of LLM Thinking Algorithm Flowchart. Adhering to this logic yields more acceptable sentiment analysis reports.