Aff2Vec: Affect--Enriched Distributional Word Representations

Abstract

Human communication includes information, opinions, and reactions. Reactions are often captured by the affective-messages in written as well as verbal communications. While there has been work in affect modeling and to some extent affective content generation, the area of affective word distributions in not well studied. Synsets and lexica capture semantic relationships across words. These models however lack in encoding affective or emotional word interpretations. Our proposed model, Aff2Vec provides a method for enriched word embeddings that are representative of affective interpretations of words. Aff2Vec outperforms the state--of--the--art in intrinsic word-similarity tasks. Further, the use of Aff2Vec representations outperforms baseline embeddings in downstream natural language understanding tasks including sentiment analysis, personality detection, and frustration prediction.

References in corpus (7)

• Efficient Estimation of Word Representations in Vector Space
• Enriching Word Vectors with Subword Information
• A Computational Approach to Politeness with Application to Social Factors
• A Neural Knowledge Language Model
• Joint Word Representation Learning using a Corpus and a Semantic Lexicon
• From Paraphrase Database to Compositional Paraphrase Model and Back
• Affect-LM: A Neural Language Model for Customizable Affective Text Generation