Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter

  title={Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter},
  author={Boaz Shmueli and Soumya Ray and Lun-Wei Ku},
Datasets with induced emotion labels are scarce but of utmost importance for many NLP tasks. We present a new, automated method for collecting texts along with their induced reaction labels. The method exploits the online use of reaction GIFs, which capture complex affective states. We show how to augment the data with induced emotions and induced sentiment labels. We use our method to create and publish ReactionGIF, a first-of-its-kind affective dataset of 30K tweets. We provide baselines for… Expand

Figures and Tables from this paper


Distant supervision for emotion detection using Facebook reactions
The Facebook reaction feature is exploited in a distant supervised fashion to train a support vector machine classifier for emotion detection, using several feature combinations and combining different Facebook pages to achieve competitive results. Expand
SocialNLP 2018 EmotionX Challenge Overview: Recognizing Emotions in Dialogues
An overview of the Dialogue Emotion Recognition Challenge, EmotionX, at the Sixth SocialNLP Workshop, which recognizes the emotion of each utterance in dialogues, is described, which offers the EmotionLines dataset as the experimental materials. Expand
Recognizing induced emotions of movie audiences: Are induced and perceived emotions the same?
This study extends the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and shows that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. Expand
Modelling Valence and Arousal in Facebook posts
A new data set of 2895 Social Media posts rated by two psychologicallytrained annotators on two separate ordinal nine-point scales, which defines each post’s position on the circumplex model of affect, a well-established system for describing emotional states. Expand
An Analysis of Annotated Corpora for Emotion Classification in Text
A survey of the datasets is carried out, and a subset of corpora is better classified with models trained on a different corpus, which simplifies the choice of the most appropriate resources for developing a model for a novel domain. Expand
Emotion Detection in Text: a Review
It is argued that although many techniques, methodologies, and models have been created to detect emotion in text, there are various reasons that make these methods insufficient and it is important to pay attention to the linguistic intricacies of emotion expression. Expand
Predicting Viewer Perceived Emotions in Animated GIFs
One of the objectives is to systematically compare different types of content features for emotion prediction, including low-level, aesthetics, semantic and face features, and formulate a multi-task regression problem to evaluate whether viewer perceived emotion prediction can benefit from jointly learning across emotion classes compared to disjoint, independent learning. Expand
Readers vs. Writers vs. Texts: Coping with Different Perspectives of Text Understanding in Emotion Annotation
We here examine how different perspectives of understanding written discourse, like the reader’s, the writer’s or the text’s point of view, affect the quality of emotion annotations. We conducted aExpand
A new way of using normative databases as a way of processing text with a dimensional model and compare it with different categorical approaches is introduced and shows that the categorical model using NMF and the dimensional model tend to perform best. Expand
Learning to identify emotions in text
The construction of a large data set annotated for six basic emotions, ANGER, DISGUST, FEAR, JOY, SADNESS and SURPRISE, and several knowledge-based and corpusbased methods for the automatic identification of these emotions in text are proposed. Expand