Our paper SentiVec Learning Sentiment-Context Vector via Kernel Optimization Function for Sentiment Analysis gets published in IEEE TNNLS!

We propose SentiVec, a kernel optimization function system for sentiment word embedding. SentiVec is aimed at:

• integrating the statistical information and sentiment orientation into sentiment word vectors.
• propagating and updating the semantic information to all the word representations in a corpus.

For more detailed information, please visist SentiVec: Learning Sentiment-Context Vector via Kernel Optimization Function for Sentiment Analysis.