Open Access

ARTICLE

OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation

Jinzheng Yu¹, Yang Xu², Haozhen Li², Junqi Li³, Ligu Zhu¹, Hao Shen^1,*, Lei Shi^1,*

1 State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, 100024, China
2 Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, 150001, China
3 Scientific and Information Technical Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing, 100081, China

* Corresponding Authors: Hao Shen. Email: ; Lei Shi. Email:

(This article belongs to the Special Issue: Big Data and Artificial Intelligence in Control and Information System)

Computers, Materials & Continua 2026, 87(1), 58 https://doi.org/10.32604/cmc.2025.073771

Received 25 September 2025; Accepted 24 November 2025; Issue published 10 February 2026

Abstract

Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises. While large language models (LLMs) enable automated report generation, this specific domain lacks formal task definitions and corresponding benchmarks. To bridge this gap, we define the Automated Online Public Opinion Report Generation (OPOR-Gen) task and construct OPOR-Bench, an event-centric dataset with 463 crisis events across 108 countries (comprising 8.8 K news articles and 185 K tweets). To evaluate report quality, we propose OPOR-Eval, a novel agent-based framework that simulates human expert evaluation. Validation experiments show OPOR-Eval achieves a high Spearman’s correlation (ρ = 0.70) with human judgments, though challenges in temporal reasoning persist. This work establishes an initial foundation for advancing automated public opinion reporting research.

---

Keywords

---