More Than Sentiment-Infused Word Embedding
SentiVec is novel method for distributional analysis, which is used to produce vector representations for words (also known as word embeddings). The method extends and outperforms popular Word2Vec by optimizing an auxiliary lexical objective. The lexical objective takes advantage of word classes, such as positive and negative opinion words, and enforces word embeddings of the same class to be closer to each other.
|Binary Classification Task||Amazon
|Rotten Tomatoes Sentiment||77.9%||75.8%|
Updated: 5 June 2018