Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods

Sentiment classification of financial news deals with the identification of positive and negative news so that they can be applied in decision support system to perform stock trend predictions. This paper explores several types of feature space as different datasets for sentiment classification of t...

Full description

Bibliographic Details
Main Authors: Yazdani, Sepideh Foroozan, Azmi Murad, Masrah Azrifah, Mohd Sharef, Nurfadhlina, Abdul Latiff, Ahmed Razman
Format: Conference or Workshop Item
Language:English
Published: IEEE 2015
Online Access:http://psasir.upm.edu.my/id/eprint/14342/
http://psasir.upm.edu.my/id/eprint/14342/1/Improving%20sentiment%20classification%20accuracy%20of%20financial%20news%20using%20n-gram%20approach%20and%20feature%20weighting%20methods.pdf
_version_ 1848842366421565440
author Yazdani, Sepideh Foroozan
Azmi Murad, Masrah Azrifah
Mohd Sharef, Nurfadhlina
Abdul Latiff, Ahmed Razman
author_facet Yazdani, Sepideh Foroozan
Azmi Murad, Masrah Azrifah
Mohd Sharef, Nurfadhlina
Abdul Latiff, Ahmed Razman
author_sort Yazdani, Sepideh Foroozan
building UPM Institutional Repository
collection Online Access
description Sentiment classification of financial news deals with the identification of positive and negative news so that they can be applied in decision support system to perform stock trend predictions. This paper explores several types of feature space as different datasets for sentiment classification of the news article. Experiments are conducted based on n-gram approach (unigram, bigram and the combination of unigram and bigram) used as feature extraction with different feature weighting methods, while, document frequency (DF) is used as feature selection method. We performed experiments to measure the classification accuracy of support vector machine (SVM) with two kernel methods of linear and Radial Basis Function (RBF). Results showed that an efficient feature extraction increased classification accuracy when it is used as a combination of unigram and bigram. Moreover, we also found that DF can be applied as a dimension reduction method to reduce the feature space without loss of accuracy.
first_indexed 2025-11-15T07:57:59Z
format Conference or Workshop Item
id upm-14342
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T07:57:59Z
publishDate 2015
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling upm-143422019-04-08T08:32:02Z http://psasir.upm.edu.my/id/eprint/14342/ Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods Yazdani, Sepideh Foroozan Azmi Murad, Masrah Azrifah Mohd Sharef, Nurfadhlina Abdul Latiff, Ahmed Razman Sentiment classification of financial news deals with the identification of positive and negative news so that they can be applied in decision support system to perform stock trend predictions. This paper explores several types of feature space as different datasets for sentiment classification of the news article. Experiments are conducted based on n-gram approach (unigram, bigram and the combination of unigram and bigram) used as feature extraction with different feature weighting methods, while, document frequency (DF) is used as feature selection method. We performed experiments to measure the classification accuracy of support vector machine (SVM) with two kernel methods of linear and Radial Basis Function (RBF). Results showed that an efficient feature extraction increased classification accuracy when it is used as a combination of unigram and bigram. Moreover, we also found that DF can be applied as a dimension reduction method to reduce the feature space without loss of accuracy. IEEE 2015 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/14342/1/Improving%20sentiment%20classification%20accuracy%20of%20financial%20news%20using%20n-gram%20approach%20and%20feature%20weighting%20methods.pdf Yazdani, Sepideh Foroozan and Azmi Murad, Masrah Azrifah and Mohd Sharef, Nurfadhlina and Abdul Latiff, Ahmed Razman (2015) Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods. In: 2nd International Conference on Information Science and Security (ICISS 2015), 14-16 Dec. 2015, Seoul, South Korea. . 10.1109/ICISSEC.2015.7371008
spellingShingle Yazdani, Sepideh Foroozan
Azmi Murad, Masrah Azrifah
Mohd Sharef, Nurfadhlina
Abdul Latiff, Ahmed Razman
Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
title Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
title_full Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
title_fullStr Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
title_full_unstemmed Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
title_short Improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
title_sort improving sentiment classification accuracy of financial news using n-gram approach and feature weighting methods
url http://psasir.upm.edu.my/id/eprint/14342/
http://psasir.upm.edu.my/id/eprint/14342/
http://psasir.upm.edu.my/id/eprint/14342/1/Improving%20sentiment%20classification%20accuracy%20of%20financial%20news%20using%20n-gram%20approach%20and%20feature%20weighting%20methods.pdf