Sentiment Analysis
Sentiment analysis aims to automatically determine the emotional tone expressed in text, aiming to understand opinions and attitudes. Current research heavily focuses on leveraging large language models (LLMs) like BERT and its variants, along with other architectures such as graph neural networks, to improve accuracy and efficiency, particularly in multimodal settings and low-resource languages. This field is crucial for various applications, including market research, social media monitoring, and understanding public opinion, driving advancements in natural language processing and impacting decision-making across numerous sectors.
Papers
Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction
Kun Peng, Lei Jiang, Hao Peng, Rui Liu, Zhengtao Yu, Jiaqian Ren, Zhifeng Hao, Philip S. Yu
Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations
Jihong Ouyang, Zhiyao Yang, Silong Liang, Bing Wang, Yimeng Wang, Ximing Li
User Friendly and Adaptable Discriminative AI: Using the Lessons from the Success of LLMs and Image Generation Models
Son The Nguyen, Theja Tulabandhula, Mary Beth Watson-Manheim
Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification
Yijie Gao, Shijing Si, Hua Luo, Haixia Sun, Yugui Zhang