Ryang Heo

I’m a Ph.D. student in the Data & Language Intelligence (DLI) Lab at Yonsei University, advised by Prof. Dongha Lee.

If you're interested in collaborating on research or exploring new ideas together, please feel free to connect with me anytime!

[ E-mail / Google Scholar / LinkedIn / GitHub / X ]

🔎 Research Interest

My research focuses on advancing data mining in web environments. Specifically, I aim to collect and process large-scale user behavior data from online communities, social networks, video platforms, and content streaming services to uncover contextual patterns in user interests and engagement. Recently, I have also been exploring the development of user simulators that generate realistic responses and exploration behaviors using large language models (LLMs).

📚 Publications

{ }: denotes equal contribution.

	AgenticShop: Benchmarking Agentic Product Curation for Personalized Web Shopping {Sunghwan Kim, Ryang Heo}, Yongsik Seo, Jinyoung Yeo, Dongha Lee WWW, 2026 Paper / Code
	Personalized Reward Modeling for Text-to-Image Generation Jeongeun Lee, Ryang Heo, Dongha Lee arXiv, 2025 Paper / Code
	Can Large Language Models be Effective Online Opinion Miners? Ryang Heo, Yongsik Seo, Junseong Lee, Dongha Lee EMNLP Main, 2025 Paper / Code
	Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval Sangam Lee, Ryang Heo, SeongKu Kang, Dongha Lee COLM, 2025 Paper / Code
	Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths Sangam Lee, Ryang Heo, SeongKu Kang, Susik Yoon, Jinyoung Yeo, Dongha Lee arXiv, 2024 Paper / Code
	Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis {Yongsik Seo, Sungwon Song, Ryang Heo}, Jieyong Kim, Dongha Lee EMNLP Findings, 2024 Paper / Code
	Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy {Jieyong Kim, Ryang Heo}, Yongsik Seo, SeongKu Kang, Jinyoung Yeo, Dongha Lee ACL Findings, 2024 Paper / Code