Dimensional sentiment analysis aims to predict continuous affective values across multiple dimensions, such as the valence–arousal (VA) space. Compared with categorical approaches that focus on discrete sentiment labels (e.g., binary classification of positive vs. negative), dimensional modeling provides a more fine-grained and expressive representation of sentiment. This capability has enabled a wide range of applications, including stance detection, misinformation identification, dialogue generation, hate speech detection, and emotion dynamics analysis. In this talk, we’ll give an overview of the main resources, methods, and applications of dimensional sentiment analysis, along with some intuitive examples to illustrate how it works in practice.