The Open UniversitySkip to content
 

Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis

Huynh, Trung; He, Yulan and Rüger, Stefan (2015). Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis. In: Advances in Information Retrieval (Hanbury, Allan; Kazai, Gabriella; Rauber, Andreas and Fuhr, Norbert eds.), Lecture Notes in Computer Science, Springer International Publishing, pp. 447–452.

Full text available as:
Full text not publicly available
Due to copyright restrictions, this file is not available for public download
DOI (Digital Object Identifier) Link: https://doi.org/10.1007/978-3-319-16354-3_49
Google Scholar: Look up in Google Scholar

Abstract

In recent years, learning word vector representations has attracted much interest in Natural Language Processing. Word representations or embeddings learned using unsupervised methods help addressing the problem of traditional bag-of-word approaches which fail to capture contextual semantics. In this paper we go beyond the vector representations at the word level and propose a novel framework that learns higher-level feature representations of n-grams, phrases and sentences using a deep neural network built from stacked Convolutional Restricted Boltzmann Machines (CRBMs). These representations have been shown to map syntactically and semantically related n-grams to closeby locations in the hidden feature space. We have experimented to additionally incorporate these higher-level features into supervised classifier training for two sentiment analysis tasks: subjectivity classification and sentiment classification. Our results have demonstrated the success of our proposed framework with 4% improvement in accuracy observed for subjectivity classification and improved the results achieved for sentiment classification over models trained without our higher level features.

Item Type: Conference or Workshop Item
Copyright Holders: 2015 Springer International Publishing Switzerland
ISBN: 3-319-16353-1, 978-3-319-16353-6
ISSN: 0302-9743
Keywords: sentiment analysis; word embeddings
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi)
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 43265
Depositing User: Stefan Rüger
Date Deposited: 28 May 2015 08:48
Last Modified: 06 Oct 2016 14:30
URI: http://oro.open.ac.uk/id/eprint/43265
Share this page:

Altmetrics

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU