Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2 
基于评论的推荐系统能够吸纳用户的意见,提供高质量、多样化、个性化的推荐结果,在政企服务中起着关键作用。现有方法主要依赖历史评论提取用户偏好,但难以历全面反映目标物品的特点和用户的实际需求,导致推荐结果的准确性和解释性不足。本项目拟围绕用户评价机制开展研究,构建大语言模型增强的基于评论的推荐系统。首先,研究用户在物品方面选择中的关注机制,提出融合方面术语与方面类别的偏 好建模方法,以缓解术语稀疏问题并有效刻画用户的显式偏好特征;其次,研究评论中的讽刺表达机制,提出大语言模型驱动的讽刺检测与语义还原方法,以缓解评论与评分不一致带来的偏差,挖掘用户真实意图;最后,研究用户评论的生成过程,提出结合方面信息与隐含语义的大模型评论生成方法,从生成评论中提取用户对目标物品的需求与物品特征匹配关系。通过上述研究,项目旨在提升基 于评论的推荐系统的准确性、可解释性和鲁棒性。
在面对各类文化资源快速增长、用户需求个性化以及文化价值深度开发需求时,传统文化资源存在资源关联不足、传播精准性不足和服务模式相对固化等问题。如何利用人工智能技术重构文化资源组织、传播和服务体系,成为推动文化行业高质量发展的重要课题。本研究围绕“智能出版”,系统分析智能出版发展的技术基础、作用机制及应用路径。研究指出,智能出版依托知识图谱、智能推荐、数字版权保护等关键技术,推动文化资源向“智能知识体系”、 “精准传播”、 “智能服务”转变,并进一步促进文化资源价值由一次性传播向持续性运营演进。面向北京全国文化中心建设需求,研究提出以文化数据新基建为基础,构建智能文化资源底座、智慧文化服务体系和文化价值运营模式,推动北京特色文化资源的智能化开发利用,提升公共文化服务能力和文化产业创新能力。同时,结合北京印刷学院特色优势,提出通过学科交叉融合、复合型人才培养、科研组织创新和社会服务体系建设,形成支撑智能出版发展的高校创新路径。
This project investigates personalized knowledge organization and intelligent publishing, including demand-driven knowledge selection, adaptive content recommendation, and trustworthy copyright management.
Journal 1
This paper is about the number 1. The number 2 is left for future work.
Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1).
Paper
Recommended citation: Zhen Yang, **Junrui Liu**, Tong Li, Di Wu, Shiqiu Yang, Huan Liu. (2023). Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2023: 2928-2938.
Paper | Code
Recommended citation: **Junrui Liu**, Tong Li, Di Wu, Zifang Tang, Yuan Fang, Zhen Yang (2025). An aspect performance-aware hypergraph neural network for review-based recommendation; Proceedings of the 18th ACM International Conference on Web Search and Data Mining. 2025.
Paper | Code
Recommended citation: **Junrui Liu**, Tong Li, Mingliang Yu, Shiqiu Yang, Zifang Tang, Zhen Yang (2025). A Multi-Factor Collaborative Prediction for Review-based Recommendation; Proceedings of the 19th ACM RecSys. 2025, 12-20.
Paper | Code
Recommended citation: Le Liu, **Junrui Liu✉**, Yunhan Gao, Ziheng Wang, Tong Li (2025). LSA: A Long-Short-Term Aspect Interest Transformer for Aspect-Based Recommendation; Proceedings of the WISE 2025. Lecture Notes in Computer Science, vol 16368.
Paper
Recommended citation: Jinglin Zhang, **Junrui Liu✉**, Tong Li, Bo Gao, Zichen Li (2026). ICAM: Inconsistency-aware Compensation and Adaptive Modeling for Review-Based Recommendation; Proceedings of the DependSys 2026.
Paper
Recommended citation: **Junrui Liu**, Zhen Yang, Tong Li, Di Wu, Ruiyi Wang. (2022). "SPR:Similarity pairwise ranking for personalized recommendation." Knowledge-Based Systems. 239:107828.
Paper
Recommended citation: Wette Feng, **Junrui Liu**, Tong Li, Zhen Yang, Di Wu. (2024). "FAC: A Music Recommendation Model Based on FusingAudio and Chord Features (115." International Journal of Software Engineeringand Knowledge Engineer. Vol. 32, Nos. 11 & 12 (2022) 1753–1770.
Paper
Recommended citation: **Junrui Liu**, Tong Li, Zhen Yang, Di Wu, Huan Liu. (2024). "Fusion learning of preference and bias from ratings and reviews foritem recommendation." Data & Knowledge Engineering. 150:102283.
Paper | Code
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Undergraduate course, BIGC, 2025
Undergraduate course, BIGC, 2026