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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations Save citation

Open

Authors

Research units

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.

Documents

Details

Publication date2015
Publication titleAdvances in information retrieval : 37th European conference on IR research, ECIR 2015, Vienna, Austria, March 29 - April 2, 2015. Proceedings
EditorsAllan Hanbury, Gabriella Kazai, Andreas Rauber, Norbert Fuhr
Place of PublicationCham (CH)
PublisherSpringer
Pages447-452
Number of pages6
ISBN (Electronic)978-3-319-16354-3
ISBN (Print)978-3-319-16353-6
Original languageEnglish
Event37th European Conference on Information Retrieval Research - Vienna, Austria

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume9022
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference37th European Conference on Information Retrieval Research
Abbreviated titleECIR 2015
CountryAustria
CityVienna
Period29/03/152/04/15

Keywords

  • convolutional restricted Boltzmann machines, sentiment analysis, stacked restricted Boltzmann Machine, word embedding

DOI

Download statistics

No data available

Employable Graduates; Exploitable Research

Copy the text from this field...