演算法助長同溫層 多語言模型辨識網路極化言論
演算法推薦讓社群媒體使用者更有效率地接收感興趣的資訊，卻也使人長期置身資訊同溫層；情緒化言論因更容易獲得關注，使網路討論逐漸走向兩極化發展。
由智能系統研究所李龍豪副教授領軍的自然語言處理研究團隊（NYCU-NLP）成員林鼎翔、褚柏均運用三個開源大型語言模型，開發出可辨識22種語言的網路極化言論模型，這套模型在國際語意評測競賽任務9奪下第二名佳績，第一名為日本東京大學。
nlplab
DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis
Lung-Hao Lee, Liang-Chih Yu, …
NYCU-NLP at SemEval-2026 Task 9: Stacking Small Language Models for Multilingual, Multicultural and Multievent Polarization Detection
Ding-Xiang Lin, Po-Chun Chu, …
SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA)
Liang-Chih Yu, Jonas Becker, Shamsuddee…
ROCLING-2025 Shared Task: Chinese Dimensional Sentiment Analysis for Medical Self-Reflection Texts
Lung-Hao Lee, Tzu-Mi Lin, Hsiu-Min Shih, Kuo-Kai Shyu, Anna S. Hsu, and Peih-Ying Lu.
NYCU-NLP at SemEval-2025 Task 11: Assembling Small Language Models for Multilabel Emotion Detection and Intensity Prediction
Zhe-Yu Xu, Yu-Hsin Wu, and Lung-Hao Lee*
NYCU-NLP 奪國際競賽雙料第二
恭喜智能所自然語言處理研究團隊（NYCU-NLP）在頂尖語言學國際賽事 SemEval-2025 Task 11 勇奪雙料亞軍！
在李龍豪副教授指導下，博士生許哲瑜與碩士生吳昱昕整合 Gemma-2、Mistral-small-3 與 Phi-4 三款大型語言模型，於英文多標籤情緒偵測及情緒強度預測賽道中，擊敗哈佛、史丹福等全球名校團隊，拿下雙項第二名佳績！
Filtering Objectionable Information Access Based on Click-Through Behaviors with Deep Learning Methods
Lung-Hao Lee, Jian-Hong Li, Szu-Wei Ku, and Yuan-Hsien Tseng*
Chinese Psychological Counseling Corpus Construction for Valence-Arousal Sentiment Intensity Prediction
Hsiu-Min Shih, Tzu-Mi Lin, Yu-Wen Tzeng, Jung-Ying Chang, Kuo-Kai Shyu, and Lung-Hao Lee
NYCU-NLP at PAN 2024: Integrating Transformers with Similarity Adjustments for Multi-Author Writing Style Analysis
Tzu-Mi Lin, Yu-Hsin Wu and Lung-Hao Lee