Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Balancing Information Perception with Yin-Yang: Agent-Based Information Neutrality Model for Recommendation Systems

Mengyan Wang, Yuxuan Hu, Shiqing Wu, Weihua Li, Quan Bai, Verica Rupar

TL;DR

Balancing Information Perception with Yin-Yang presents AbIN, an agent-based Information Neutrality framework that can be integrated with existing preference-based recommender systems to counter filter bubbles. The model relies on three agents—OPA, UA, and INA—where INA applies Yin-Yang Neutralization Control to balance sentiments for topics using the neutralization function $f(o)$, thereby expanding information diversity without altering core algorithms. Formal definitions establish sentiment labeling into $Y_-$ and $Y_+$ and the neutralization objective across topics, while DCIA and clustering enable targeted, memory-informed balancing. Empirical evaluation on real-world datasets demonstrates improved sentiment diversity and neutralization with acceptable accuracy, indicating AbIN’s potential to mitigate information bias in practical recommendations.

Abstract

While preference-based recommendation algorithms effectively enhance user engagement by recommending personalized content, they often result in the creation of ``filter bubbles''. These bubbles restrict the range of information users interact with, inadvertently reinforcing their existing viewpoints. Previous research has focused on modifying these underlying algorithms to tackle this issue. Yet, approaches that maintain the integrity of the original algorithms remain largely unexplored. This paper introduces an Agent-based Information Neutrality model grounded in the Yin-Yang theory, namely, AbIN. This innovative approach targets the imbalance in information perception within existing recommendation systems. It is designed to integrate with these preference-based systems, ensuring the delivery of recommendations with neutral information. Our empirical evaluation of this model proved its efficacy, showcasing its capacity to expand information diversity while respecting user preferences. Consequently, AbIN emerges as an instrumental tool in mitigating the negative impact of filter bubbles on information consumption.

Balancing Information Perception with Yin-Yang: Agent-Based Information Neutrality Model for Recommendation Systems

TL;DR

Balancing Information Perception with Yin-Yang presents AbIN, an agent-based Information Neutrality framework that can be integrated with existing preference-based recommender systems to counter filter bubbles. The model relies on three agents—OPA, UA, and INA—where INA applies Yin-Yang Neutralization Control to balance sentiments for topics using the neutralization function , thereby expanding information diversity without altering core algorithms. Formal definitions establish sentiment labeling into and and the neutralization objective across topics, while DCIA and clustering enable targeted, memory-informed balancing. Empirical evaluation on real-world datasets demonstrates improved sentiment diversity and neutralization with acceptable accuracy, indicating AbIN’s potential to mitigate information bias in practical recommendations.

Abstract

While preference-based recommendation algorithms effectively enhance user engagement by recommending personalized content, they often result in the creation of ``filter bubbles''. These bubbles restrict the range of information users interact with, inadvertently reinforcing their existing viewpoints. Previous research has focused on modifying these underlying algorithms to tackle this issue. Yet, approaches that maintain the integrity of the original algorithms remain largely unexplored. This paper introduces an Agent-based Information Neutrality model grounded in the Yin-Yang theory, namely, AbIN. This innovative approach targets the imbalance in information perception within existing recommendation systems. It is designed to integrate with these preference-based systems, ensuring the delivery of recommendations with neutral information. Our empirical evaluation of this model proved its efficacy, showcasing its capacity to expand information diversity while respecting user preferences. Consequently, AbIN emerges as an instrumental tool in mitigating the negative impact of filter bubbles on information consumption.
Paper Structure (23 sections, 11 equations, 4 figures, 2 tables, 1 algorithm)

This paper contains 23 sections, 11 equations, 4 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Framework and Formal Definitions
  4. Overall Framework
  5. Formal Definitions
  6. Yin-Yang Neutralization Definition
  7. Agent-Based Information Neutrality Model
  8. Original Preference-based Agent
  9. Information Neutrality Agent
  10. Message Clustering
  11. Dominant Cluster Identification Algorithm (DCIA)
  12. Yin-Yang Neutralization Control Method
  13. Searching
  14. User Agent
  15. Experiments and Analysis
  16. ...and 8 more sections

Figures (4)

  • Figure 1: The Framework of Agent-based Model for Information Neutrality (AbIN).
  • Figure 2: The Chinese Yin-Yang ($Y_-\&Y_+$) Symbol.
  • Figure 3: The searching process in INA.
  • Figure 4: An analysis of the efficacy of the AbIN model in the context of a single-instance Yin-Yang neutralization task on two datasets. (a) Yin-Yang neutralization evaluation on MIND dataset. (b) Yin-Yang neutralization evaluation on IMDB dataset.