Aspect based sentiment analysis aims to identify the sentimental tendency towards a given aspect in text.
Aspect-based sentiment analysis (ABSA) task is a multi-grained task of natural language processing and consists of two subtasks: aspect term extraction (ATE) and aspect polarity classification (APC).
Ranked #2 on Aspect-Based Sentiment Analysis on SemEval 2014 Task 4 Sub Task 2 (using extra training data)
Most of the previous approaches model context and target words with RNN and attention.
Ranked #1 on Sentiment Analysis on Twitter