User Sentiment
User sentiment analysis focuses on automatically identifying and interpreting the emotional tone expressed in text or multimedia data, aiming to understand user opinions and preferences. Current research emphasizes the use of large language models (LLMs) like GPT-4 and others, along with techniques like sentiment lexicons and multimodal analysis incorporating images and emojis, to improve accuracy and address challenges such as sarcasm and nuanced language. This field is crucial for various applications, including marketing, product development, political analysis, and mental health monitoring, providing valuable insights into human behavior and societal trends.
Papers
MARS: Multilingual Aspect-centric Review Summarisation
Sandeep Sricharan Mukku, Abinesh Kanagarajan, Chetan Aggarwal, Promod Yenigalla
Single Ground Truth Is Not Enough: Add Linguistic Variability to Aspect-based Sentiment Analysis Evaluation
Soyoung Yang, Hojun Cho, Jiyoung Lee, Sohee Yoon, Edward Choi, Jaegul Choo, Won Ik Cho