Codes and Datasets for our SIGIR 2021 Paper: "Understanding the Role of Affect Dimensions in Detecting Emotions from Tweets: A Multi-task Approach"

Predict how word emotions change over time using neuronal networks. Model temporal emotional trajectories for English words with accuracy and interactive visualizations.

基于 MacBERT 的中文 VAD 情绪空间回归模型

This repository contains EmoITA, the first Italian text corpus manually annotated with emotion dimensions according to the Valence-Arousal-Dominance (VAD) model. It has been obtained by translating and re-annotating the EmoBank corpus (Buechel and Hahn, 2017). You can also find files from the EmotivITA shared task at EVALITA 2023.