Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection

Keito Inoshita

TL;DR

This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide, for supporting calm information reception of consumers without restricting access to the original text.

Abstract

In the attention economy, sensational content exposes consumers to excessive emotional stimulation, hindering calm decision-making. This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide. The Emotion Analysis Agent quantifies stimulus intensity using a 6-emotion BERT classifier, and the Emotion Adjustment Agent rewrites texts into two presentation modes, BALANCED (neutralized text) and COOL (neutralized text + supplementary text), using an LLM. The Balance Monitoring Agent aggregates weekly information consumption patterns and generates personalized advice, while the Personal Guide Agent recommends a presentation mode according to consumer sensitivity. Experiments on 800 AG News articles demonstrated significant stimulus score reduction (up to 19.3%) and improved emotion balance while maintaining semantic preservation. Near-zero correlation between stimulus reduction and semantic preservation confirmed that the two are independently controllable. Category-level analysis revealed substantial reduction (17.8-33.8%) in Sports, Business, and Sci/Tech, whereas the effect was limited in the World category, where facts themselves are inherently high-stimulus. The proposed system provides a framework for supporting calm information reception of consumers without restricting access to the original text.

Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection

TL;DR

This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide, for supporting calm information reception of consumers without restricting access to the original text.

Abstract

In the attention economy, sensational content exposes consumers to excessive emotional stimulation, hindering calm decision-making. This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide. The Emotion Analysis Agent quantifies stimulus intensity using a 6-emotion BERT classifier, and the Emotion Adjustment Agent rewrites texts into two presentation modes, BALANCED (neutralized text) and COOL (neutralized text + supplementary text), using an LLM. The Balance Monitoring Agent aggregates weekly information consumption patterns and generates personalized advice, while the Personal Guide Agent recommends a presentation mode according to consumer sensitivity. Experiments on 800 AG News articles demonstrated significant stimulus score reduction (up to 19.3%) and improved emotion balance while maintaining semantic preservation. Near-zero correlation between stimulus reduction and semantic preservation confirmed that the two are independently controllable. Category-level analysis revealed substantial reduction (17.8-33.8%) in Sports, Business, and Sci/Tech, whereas the effect was limited in the World category, where facts themselves are inherently high-stimulus. The proposed system provides a framework for supporting calm information reception of consumers without restricting access to the original text.
Paper Structure (16 sections, 3 equations, 3 figures, 7 tables)

This paper contains 16 sections, 3 equations, 3 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Multi-Agent LLM-Based Emotional Detoxification
  3. System Overview
  4. Emotion Analysis Agent
  5. Emotion Adjustment Agent
  6. Balance Monitoring Agent
  7. Personal Guide Agent
  8. Experiments and Results
  9. Experimental Design
  10. Evaluation of Stimulus Reduction
  11. Evaluation of Emotion Distribution Changes
  12. Evaluation of Semantic Preservation
  13. Evaluation of Weekly Aggregation and Personalized Advice
  14. Evaluation of Mode Recommendation
  15. Discussion
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Overview of the MALLET System.
  • Figure 2: Mean Probability Distribution of the Six Emotions across the Three Conditions.
  • Figure 3: Scatter Plot of Stimulus Reduction Magnitude and SBERT Similarity.