A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators
The increase in the amount of content shared on social media makes it difficult to extract meaningful information from scientific studies. Accordingly, in recent years, researchers have been working extensively on sentiment analysis studies for the automatic evaluation of social media data. One of t...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
North Atlantic University Union
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/20.500.12294/1944 |
id |
ftistanbularelun:oai:arelarsiv.arel.edu.tr:20.500.12294/1944 |
---|---|
record_format |
openpolar |
spelling |
ftistanbularelun:oai:arelarsiv.arel.edu.tr:20.500.12294/1944 2023-07-02T03:33:07+02:00 A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators Yelmen, İlkay Zontul, Metin Kaynar, Oğuz Sönmez, Ferdi 2018 application/pdf https://hdl.handle.net/20.500.12294/1944 eng eng North Atlantic University Union International Journal of Circuits, Systems and Signal Processing Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı 1998-4464 https://hdl.handle.net/20.500.12294/1944 12 637 645 info:eu-repo/semantics/openAccess Classification Algorithms Feature Extraction Genetic Algorithms Sentiment Analysis Text Mining article 2018 ftistanbularelun https://doi.org/20.500.12294/1944 2023-06-13T16:08:07Z The increase in the amount of content shared on social media makes it difficult to extract meaningful information from scientific studies. Accordingly, in recent years, researchers have been working extensively on sentiment analysis studies for the automatic evaluation of social media data. One of the focuses of these studies is sentiment analysis on tweets. The more tweets are available, the more features in terms of words exist. This leads to the curse of dimensionality and sparsity, resulting in a decrease in the success of the classification. In this study, Gini Index, Information Gain and Genetic Algorithm (GA) are used for feature selection and Support Vector Machines (SVMs), Artificial Neural Networks (ANN) and Centroid Based classification algorithms are used for the classification of Turkish tweets obtained from 3 different GSM operators. The feature selection methods are combined with the classification methods to investigate the effect on the success rate of analysis. Especially, when the SVMs are used with the GA as a hybrid, 96.8% success has been achieved for the classification of the tweets as positive or negative. © 2018, North Atlantic University Union. All rights reserved. We would like to express our special appreciation and thanks to Turkish Airlines for the financial support. Article in Journal/Newspaper North Atlantic İstanbul Arel Üniversitesi Kurumsal Arşiv Sistemi: Arel eArsiv (AREL Open Archive System) |
institution |
Open Polar |
collection |
İstanbul Arel Üniversitesi Kurumsal Arşiv Sistemi: Arel eArsiv (AREL Open Archive System) |
op_collection_id |
ftistanbularelun |
language |
English |
topic |
Classification Algorithms Feature Extraction Genetic Algorithms Sentiment Analysis Text Mining |
spellingShingle |
Classification Algorithms Feature Extraction Genetic Algorithms Sentiment Analysis Text Mining Yelmen, İlkay Zontul, Metin Kaynar, Oğuz Sönmez, Ferdi A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators |
topic_facet |
Classification Algorithms Feature Extraction Genetic Algorithms Sentiment Analysis Text Mining |
description |
The increase in the amount of content shared on social media makes it difficult to extract meaningful information from scientific studies. Accordingly, in recent years, researchers have been working extensively on sentiment analysis studies for the automatic evaluation of social media data. One of the focuses of these studies is sentiment analysis on tweets. The more tweets are available, the more features in terms of words exist. This leads to the curse of dimensionality and sparsity, resulting in a decrease in the success of the classification. In this study, Gini Index, Information Gain and Genetic Algorithm (GA) are used for feature selection and Support Vector Machines (SVMs), Artificial Neural Networks (ANN) and Centroid Based classification algorithms are used for the classification of Turkish tweets obtained from 3 different GSM operators. The feature selection methods are combined with the classification methods to investigate the effect on the success rate of analysis. Especially, when the SVMs are used with the GA as a hybrid, 96.8% success has been achieved for the classification of the tweets as positive or negative. © 2018, North Atlantic University Union. All rights reserved. We would like to express our special appreciation and thanks to Turkish Airlines for the financial support. |
format |
Article in Journal/Newspaper |
author |
Yelmen, İlkay Zontul, Metin Kaynar, Oğuz Sönmez, Ferdi |
author_facet |
Yelmen, İlkay Zontul, Metin Kaynar, Oğuz Sönmez, Ferdi |
author_sort |
Yelmen, İlkay |
title |
A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators |
title_short |
A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators |
title_full |
A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators |
title_fullStr |
A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators |
title_full_unstemmed |
A novel hybrid approach for sentiment classification of Turkish tweets for GSM operators |
title_sort |
novel hybrid approach for sentiment classification of turkish tweets for gsm operators |
publisher |
North Atlantic University Union |
publishDate |
2018 |
url |
https://hdl.handle.net/20.500.12294/1944 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
International Journal of Circuits, Systems and Signal Processing Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı 1998-4464 https://hdl.handle.net/20.500.12294/1944 12 637 645 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/20.500.12294/1944 |
_version_ |
1770272930056372224 |