CrossWeave: Bridging Perspectives Across Online Communities with a Dual-Pane Design

📅 2026-10-07
📈 Citations: 0
✨ Influential: 0
📄 PDF
🤖 AI Summary
This study addresses how echo chambers on social media exacerbate societal polarization and impede cross-group dialogue. We propose an AI-driven dual-pane interactive system that integrates natural language processing with community detection techniques. Through a sidebar interface, the system recommends diverse perspectives in real time, simulates user reactions, and provides writing assistance to guide users beyond information cocoons toward constructive engagement. The core innovation lies in transforming passive content presentation into proactive conversational intervention, achieving synergy between contextual recommendation and expression guidance. Experimental results demonstrate that the proposed system effectively fosters cross-community participation and significantly enhances the quality of public discourse.
📝 Abstract
Social media systems typically display conversations among already familiar contributors, which can be predictable and one-sided. In civic discourse, this design narrows discussion, reinforces divides, and distorts the perception of public opinion. To encourage cross-community engagement, we present CrossWeave, an AI-powered bridging system that augments the standard social media feed. As the user reads a post, CrossWeave surfaces diverse relevant posts from other threads in a side pane and highlights the connections. Users are invited to venture out of their echo chamber, explore a broader range of views and arguments, and ``click across'' to engage with their authors. When they do, CrossWeave facilitates constructive posting, not only by showcasing relevant past content but also by simulating possible reactions as the user drafts a post.
Problem

Research questions and friction points this paper is trying to address.

echo chamber
cross-community engagement
civic discourse
social media polarization
public opinion distortion
Innovation

Methods, ideas, or system contributions that make the work stand out.

Cross-community bridging
AI-powered system
Dual-pane design
Echo chamber
Reaction simulation
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
F
Fei Fang
Johns Hopkins University, Baltimore, Maryland, USA
R
Reva Hirave
Princeton University, Princeton, New Jersey, USA
William Jurayj
William Jurayj
Johns Hopkins University
Natural Language ProcessingReinforcement LearningProgram Synthesis
Y
Yuqi Li
Johns Hopkins University, Baltimore, Maryland, USA
B
Brian Lu
Johns Hopkins University, Baltimore, Maryland, USA
T
Tarik Metin
Johns Hopkins University, Baltimore, Maryland, USA
T
Tsugunobu Miyake
Georgia Institute of Technology, Atlanta, Georgia, USA
K
Kateryna Morhun
Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
Y
Yash Permalla
Johns Hopkins University, Baltimore, Maryland, USA
K
Kenan Rustamov
Johns Hopkins University, Baltimore, Maryland, USA
A
Allen Shen
Johns Hopkins University, Baltimore, Maryland, USA
H
Haojun Shi
Johns Hopkins University, Baltimore, Maryland, USA
P
Prabhav Singh
Johns Hopkins University, Baltimore, Maryland, USA
X
Xiheng Tom Wang
Johns Hopkins University, Baltimore, Maryland, USA
K
Kevin Xu
Johns Hopkins University, Baltimore, Maryland, USA
Qingcheng Zeng
Qingcheng Zeng
PhD Student in NLP, Northwestern University
Computational Social ScienceNLPComputational Linguistics
J
Jiayi Zhang
Johns Hopkins University, Baltimore, Maryland, USA
Daniel Khashabi
Daniel Khashabi
Johns Hopkins University
Natural Language ProcessingArtificial IntelligenceMachine Learning
A
Andrew Perrin
Johns Hopkins University, Baltimore, Maryland, USA
Tiziano Piccardi
Tiziano Piccardi
Stanford University
AIHCISocial computing
Ziang Xiao
Ziang Xiao
Computer Science, Johns Hopkins University
AI4SocialScienceConversational AIHuman-centered EvaluationInformation Seeking
Jason Eisner
Jason Eisner
Professor of Computer Science, Johns Hopkins University
Natural Language ProcessingMachine LearningDeclarative Programming Languages