In 2017, we will also include two shared tasks on emotions as part of the workshop. New labeled training and test data will be provided and participants can test their automatic systems on this common dataset. Papers describing the systems will be presented at the WASSA workshop, either as oral presentations (top scoring systems) or as posters.
Given a tweet and an emotion X, determine the intensity or degree of emotion X felt by the speaker -- a real-valued score between 0 and 1 (0 stands for not feeling any emotion X, and 1 stands for feeling the maximum amount of emotion X). The tweet along with the emotion X will be referred to as an instance. (Note: The absolute values of these scores or not meaningful on their own. They are meant to indicate whether one tweet is associated with more emotion intensity than another.) Data: Training and test datasets will be provided for four emotions: joy, sadness, fear, and anger. For example, the anger training dataset will have tweets along with a real-valued score between 0 and 1 indicating the degree of anger felt by the speaker (0 stands for not angry at all, and 1 stands for feeling the maximum amount of anger). The test data will include only the tweet text. Gold emotion intensity scores will be released after the evaluation period. More details can be seen on the tasks page.
Task 2: Emotion Linking and Classification (EmoLinC)
Given a tweet about a topic/target, link it to a human need, motivation, objective, desire, goal and classify it according to either the emotion/emotions the author is most likely intending to convey, the lack of emotion or the fact that the text is sarcastic/ironic.