Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts

TLDR

Sentiment analysis of short texts is difficult because limited context requires methods that combine text with prior knowledge beyond bag‑of‑words. The study proposes a deep convolutional neural network that leverages character‑to‑sentence information for sentiment analysis of short texts. The model is evaluated on the Stanford Sentiment Treebank and Stanford Twitter Sentiment corpus, covering movie review sentences and Twitter messages. The network achieves state‑of‑the‑art accuracy of 85.7 % on binary SSTb classification, 48.3 % on fine‑grained SSTb, and 86.4 % on the Twitter corpus.

Abstract

Sentiment analysis of short texts such as single sentences and Twitter messages is challenging because of the limited contextual information that they normally contain. Effectively solving this task requires strategies that combine the small text content with prior knowledge and use more than just bag-of-words. In this work we propose a new deep convolutional neural network that exploits from characterto sentence-level information to perform sentiment analysis of short texts. We apply our approach for two corpora of two different domains: the Stanford Sentiment Treebank (SSTb), which contains sentences from movie reviews; and the Stanford Twitter Sentiment corpus (STS), which contains Twitter messages. For the SSTb corpus, our approach achieves state-of-the-art results for single sentence sentiment prediction in both binary positive/negative classification, with 85.7% accuracy, and fine-grained classification, with 48.3% accuracy. For the STS corpus, our approach achieves a sentiment prediction accuracy of 86.4%.