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


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.

Publication DOI: https://doi.org/10.1007/978-3-319-16354-3_49
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
?? 50811700Jl ??
Event Title: 37th European Conference on Information Retrieval Research
Event Type: Other
Event Dates: 2015-03-29 - 2015-04-02
Uncontrolled Keywords: convolutional restricted Boltzmann machines,sentiment analysis,stacked restricted Boltzmann Machine,word embedding,General Computer Science,Theoretical Computer Science
ISBN: 978-3-319-16353-6, 978-3-319-16354-3
Last Modified: 08 Jul 2024 08:36
Date Deposited: 22 Apr 2015 10:55
Full Text Link: http://link.spr ... -319-16354-3_49
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2015
Authors: Huynh, Trung
He, Yulan (ORCID Profile 0000-0003-3948-5845)
Rüger, Stefan



Version: Accepted Version

Export / Share Citation


Additional statistics for this record