Aff2Vec: Affect--Enriched Distributional Word Representations
This addresses the need for better affective word representations in natural language processing, though it appears incremental as it builds on existing embedding methods.
The authors tackled the problem of modeling affective interpretations of words by proposing Aff2Vec, a method for enriched word embeddings, which outperformed state-of-the-art in word-similarity tasks and improved performance in downstream NLP tasks like sentiment analysis.
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.