OPRA-Vis: Visual Analytics System to Assist Organization-Public Relationship Assessment with Large Language Models

2025/09/03 by Sangbong Yoo, Yoo, Sangbong, Seongbum Seo +12
Business, Management and Accounting · Computer Science · Physics and Astronomy · #Big Data and Business Intelligence #Complex Network Analysis Techniques #Data Visualization and Analytics #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · pdf · doi:10.48550/arxiv.2509.03164

openalex publication_date 2025/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Analysis of public opinions collected from digital media helps organizations maintain positive relationships with the public. Such public relations (PR) analysis often involves assessing opinions, for example, measuring how strongly people trust an organization. Pre-trained Large Language Models (LLMs) hold great promise for supporting Organization-Public Relationship Assessment (OPRA) because they can map unstructured public text to OPRA dimensions and articulate rationales through prompting. However, adapting LLMs for PR analysis typically requires fine-tuning on large labeled datasets, which is both labor-intensive and knowledge-intensive, making it difficult for PR researchers to apply these models. In this paper, we present OPRA-Vis, a visual analytics system that leverages LLMs for OPRA without requiring extensive labeled data. Our framework employs Chain-of-Thought prompting to guide LLMs in analyzing public opinion data by incorporating PR expertise directly into the reasoning process. Furthermore, OPRA-Vis provides visualizations that reveal the clues and reasoning paths used by LLMs, enabling users to explore, critique, and refine model decisions. We demonstrate the effectiveness of OPRA-Vis through two real-world use cases and evaluate it quantitatively, through comparisons with alternative LLMs and prompting strategies, and qualitatively, through assessments of usability, effectiveness, and expert feedback.

Citations

• PrompTHis: Visualizing the Process and Influence of Prompt Editing during Text-to-Image Creation
• Gemma: Open Models Based on Gemini Research and Technology
• This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models
• Explainability for Large Language Models: A Survey
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Chain of Thought Prompting Elicits Knowledge Augmentation
• Text Classification via Large Language Models
• AttentionViz: A Global View of Transformer Attention
• GPT-4 Technical Report
• Improving In-Context Few-Shot Learning via Self-Supervised Training
• UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Want To Reduce Labeling Cost? GPT-3 Can Help
• True Few-Shot Learning with Language Models
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
• Language Models are Few-Shot Learners
• A Multiscale Visualization of Attention in the Transformer Model
• Construction of the Literature Graph in Semantic Scholar
• An Empirical Evaluation of the System Usability Scale
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation
• Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy
• Can AI automatically analyze public opinion? A LLM agents-based agentic pipeline for timely public opinion analysis
• Leveraging Large Language Models for Public Opinion and Political Psychology Research: Opportunities and Challenges
• Aligning Language Models to User Opinions