Cover Image

An improved deep learning-based approach for sentiment mining

The sentiment mining approaches can typically be divided into lexicon and machine learning approaches. Recently there are an increasing number of approaches which combine both to improve the performance when used separately. However, this still lacks contextual understanding which led to the introdu...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Sharef, Nurfadhlina, Shafazand, Mohammad Yaser
Format: Conference or Workshop Item
Language:English
Published: IEEE 2014
Online Access:http://psasir.upm.edu.my/id/eprint/56111/1/An%20improved%20deep%20learning-based%20approach%20for%20sentiment%20mining.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:psasir.upm.edu.my:56111
record_format eprints
spelling oai:psasir.upm.edu.my:56111 http://psasir.upm.edu.my/id/eprint/56111/ An improved deep learning-based approach for sentiment mining Mohd Sharef, Nurfadhlina Shafazand, Mohammad Yaser The sentiment mining approaches can typically be divided into lexicon and machine learning approaches. Recently there are an increasing number of approaches which combine both to improve the performance when used separately. However, this still lacks contextual understanding which led to the introduction of deep learning approaches which allows for semantic compositionality over a sentiment treebank. This paper enhances the deep learning approach with semantic lexicon so that scores can be computed in-stead merely nominal classification. Besides, neutral classification is also improved. Results suggest that the approach outperforms its original. IEEE 2014 Conference or Workshop Item PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/56111/1/An%20improved%20deep%20learning-based%20approach%20for%20sentiment%20mining.pdf Mohd Sharef, Nurfadhlina and Shafazand, Mohammad Yaser (2014) An improved deep learning-based approach for sentiment mining. In: 2014 4th World Congress on Information and Communication Technologies (WICT 2014), 8-11 Dec. 2014, Melaka, Malaysia. (pp. 344-348). 10.1109/WICT.2014.7077291
institution UPM IR
collection UPM IR
language English
description The sentiment mining approaches can typically be divided into lexicon and machine learning approaches. Recently there are an increasing number of approaches which combine both to improve the performance when used separately. However, this still lacks contextual understanding which led to the introduction of deep learning approaches which allows for semantic compositionality over a sentiment treebank. This paper enhances the deep learning approach with semantic lexicon so that scores can be computed in-stead merely nominal classification. Besides, neutral classification is also improved. Results suggest that the approach outperforms its original.
format Conference or Workshop Item
author Mohd Sharef, Nurfadhlina
Shafazand, Mohammad Yaser
spellingShingle Mohd Sharef, Nurfadhlina
Shafazand, Mohammad Yaser
An improved deep learning-based approach for sentiment mining
author_facet Mohd Sharef, Nurfadhlina
Shafazand, Mohammad Yaser
author_sort Mohd Sharef, Nurfadhlina
title An improved deep learning-based approach for sentiment mining
title_short An improved deep learning-based approach for sentiment mining
title_full An improved deep learning-based approach for sentiment mining
title_fullStr An improved deep learning-based approach for sentiment mining
title_full_unstemmed An improved deep learning-based approach for sentiment mining
title_sort improved deep learning-based approach for sentiment mining
publisher IEEE
publishDate 2014
url http://psasir.upm.edu.my/id/eprint/56111/1/An%20improved%20deep%20learning-based%20approach%20for%20sentiment%20mining.pdf
_version_ 1819297613309018112
score 13.4562235

Similar Items