SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision

Jan Deriu,Martin Jaggi,Fatih Uzdilli,Valeria De Luca,Aurelien Lucchi,Maurice Gonzenbach

doi:10.18653/v1/s16-1173

Jan Deriu, Martin Jaggi + Show 4 more

Open Access

https://doi.org/10.18653/v1/s16-1173

Copy DOI

Publication Date: Jan 1, 2016
Citations: 106	License type: cc-by

Affiliation: ETH Zurich, ZHAW Zurich University of Applied Sciences

Abstract

In this paper, we propose a classifier for predicting message-level sentiments of English micro-blog messages from Twitter. Our method builds upon the convolutional sentence embedding approach proposed by (Severyn and Moschitti, 2015a; Severyn and Moschitti, 2015b). We leverage large amounts of data with distant supervision to train an ensemble of 2-layer convolutional neural networks whose predictions are combined using a random forest classifier. Our approach was evaluated on the datasets of the SemEval-2016 competition (Task 4) outperforming all other approaches for the Message Polarity Classification task.

Highlights

Sentiment analysis is a fundamental problem aiming to give a machine the ability to understand the emotions and opinions expressed in a written text
∗ These authors contributed to this work. These networks typically have a large number of parameters and are especially effective when trained on large amounts of data
We train a neural network using the following three-phase procedure: i) creation of word embeddings for initialization of the first layer; ii) distant supervised phase, where the network weights and word embeddings are trained to capture aspects related to sentiment; and iii) supervised phase, where the network is trained on the provided supervised training data

Summary

Introduction

Sentiment analysis is a fundamental problem aiming to give a machine the ability to understand the emotions and opinions expressed in a written text. Successful for sentiment classification were Convolutional Neural Networks (CNN) (Kim, 2014; Kalchbrenner et al, 2014; Severyn and Moschitti, 2015a; Severyn and Moschitti, 2015b; Johnson and Zhang, 2015), on which our work builds upon. These networks typically have a large number of parameters and are especially effective when trained on large amounts of data. The proposed approach was evaluated on the datasets of the SemEval-2016 competition, Task 4 (Nakov et al, 2016) for which it reaches state-of-the-art results

Convolutional Neural Networks

Ensemble of classifiers

System I

System II

Optimization

Meta-Classifier

Computing Resources

Results

Conclusion