Bayesian deep convolution belief networks for subjectivity detection

Chaturvedi, Iti, Cambria, Erik, Poria, Soujanya, and Bajpai, Rajiv (2016) Bayesian deep convolution belief networks for subjectivity detection. In: Proceedings of the IEEE International Conference on Data Mining Workshops. 7836765. pp. 916-923. From: ICDMW 2016: 16th International Conference on Data Mining Workshops, 12-15 December 2015, Barcelona, Spain.

[img] PDF (Accepted Publisher Version) - Accepted Version
Restricted to Repository staff only

View at Publisher Website:


Subjectivity detection aims to distinguish natural language as either opinionated (positive or negative) or neutral. In word vector based convolutional neural network models, a word meaning is simply a signal that helps to classify larger entities such as a document. Previous works do not usually consider prior distribution when using sliding windows to learn word embedding's and, hence, they are unable to capture higher-order and long-range features in text. In this paper, we employ dynamic Gaussian Bayesian networks to learn significant network motifs of words and concepts. These motifs are used to pre-Train the convolutional neural network and capture the dynamics of discourse across several sentences.

Item ID: 63354
Item Type: Conference Item (Research - E1)
ISBN: 978-1-5090-5910-2
ISSN: 2375-9259
Keywords: Bayesian Networks, Deep Convolutional Neural Networks, Sentiment Analysis
Copyright Information: © 2016 IEEE.
Date Deposited: 08 Jul 2020 23:39
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460208 Natural language processing @ 100%
SEO Codes: 95 CULTURAL UNDERSTANDING > 9501 Arts and Leisure > 950199 Arts and Leisure not elsewhere classified @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page