BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs

SEMEVAL 2017  ·  Mathieu Cliche ·

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. read more

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sentiment Analysis SemEval LSTMs+CNNs ensemble with multiple conv. ops F1-score 0.685 # 1
Sentiment Analysis SemEval 2017 Task 4-A LSTMs+CNNs ensemble with multiple conv. ops Average Recall 0.685 # 1

Methods


No methods listed for this paper. Add relevant methods here