BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs
This work addresses sentiment analysis on Twitter, a key task for social media analytics, but it is incremental as it combines existing methods like CNNs and LSTMs with standard techniques.
The paper tackled Twitter sentiment analysis by developing a classifier using CNNs and LSTMs with pre-trained and fine-tuned word embeddings, achieving first rank in all five English subtasks among 40 teams at SemEval-2017.
In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings. We then use a subset of the unlabeled data to fine tune the embeddings using distant supervision. The final CNNs and LSTMs are trained on the SemEval-2017 Twitter dataset where the embeddings are fined tuned again. To boost performances we ensemble several CNNs and LSTMs together. Our approach achieved first rank on all of the five English subtasks amongst 40 teams.