A RULE-BASED APPROACH USING THE ROUGH SET ON COVID-19 DATA

Rasim Çekik

Makale detayları

A RULE-BASED APPROACH USING THE ROUGH SET ON COVID-19 DATA

Yazarlar:

Rasim Çekik

Yayıncı:

Eskişehir Osmangazi University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 2, pp.1363-1375

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001324132

pISSN:

2630-5712

Anahtar kelimeler:

Özet:

 The COVID-19 pandemic has not only caused loss of life but also significantly affected peoples emotional state. These emotional impacts have had serious consequences on societies and economies around the world. In order to repair these devastations in society, it is important to analyse these emotional effects in depth. In this study, the effects of the pandemic on human emotions are analysed using soft computing techniques. A rule-based approach is proposed for the analysis with the help of a rough set. The proposed method is based on two main components. The first one is the process of selecting the optimal subset OFS from the whole feature set with the help of k best known feature selection approaches. The second component involves the use of rough clustering methods to generate rules on the selected feature subset OFS. In the study, the first real data set called  Real World Concern Dataset, which is obtained from emotional responses to COVID-19, was used. The dataset consists of 5,000 items 2,500 short  2,500 long. In the experimental studies, the proposed approach was tested with both labelled and unlabelled data, and it was observed that effective results were obtained with an accuracy rate of over 85. It was also found that people were highly concerned about the future due to the pandemic.

 The COVID-19 pandemic has not only caused loss of life but also significantly affected peoples emotional state. These emotional impacts have had serious consequences on societies and economies around the world. In order to repair these devastations in society, it is important to analyse these emotional effects in depth. In this study, the effects of the pandemic on human emotions are analysed using soft computing techniques. A rule-based approach is proposed for the analysis with the help of a rough set. The proposed method is based on two main components. The first one is the process of selecting the optimal subset OFS from the whole feature set with the help of k best known feature selection approaches. The second component involves the use of rough clustering methods to generate rules on the selected feature subset OFS. In the study, the first real data set called  Real World Concern Dataset, which is obtained from emotional responses to COVID-19, was used. The dataset consists of 5,000 items 2,500 short  2,500 long. In the experimental studies, the proposed approach was tested with both labelled and unlabelled data, and it was observed that effective results were obtained with an accuracy rate of over 85. It was also found that people were highly concerned about the future due to the pandemic.

 The COVID-19 pandemic has not only caused loss of life but also significantly affected peoples emotional state. These emotional impacts have had serious consequences on societies and economies around the world. In order to repair these devastations in society, it is important to analyse these emotional effects in depth. In this study, the effects of the pandemic on human emotions are analysed using soft computing techniques. A rule-based approach is proposed for the analysis with the help of a rough set. The proposed method is based on two main components. The first one is the process of selecting the optimal subset OFS from the whole feature set with the help of k best known feature selection approaches. The second component involves the use of rough clustering methods to generate rules on the selected feature subset OFS. In the study, the first real data set called  Real World Concern Dataset, which is obtained from emotional responses to COVID-19, was used. The dataset consists of 5,000 items 2,500 short  2,500 long. In the experimental studies, the proposed approach was tested with both labelled and unlabelled data, and it was observed that effective results were obtained with an accuracy rate of over 85. It was also found that people were highly concerned about the future due to the pandemic.

 COVID-19 salgını, sadece can kaybına neden olmakla kalmayıp aynı zamanda insanların duygusal durumlarını da önemli ölçüde etkilemiştir. Bu duygusal etkiler, dünya çapındaki toplumlar ve ekonomiler üzerinde ciddi sonuçlar doğurmuştur. Toplumda meydana gelen bu yıkımların onarılabilmesi için, bu duygusal etkilerin derinlemesine incelenmesi önemlidir. Bu çalışmada, salgının insan duyguları üzerindeki etkileri, yumuşak hesaplama teknikleri kullanılarak analiz edilmiştir. Analiz için kaba küme yardımıyla kural tabanlı bir yaklaşım önerilmiştir. Önerilen yöntem, iki temel bileşen üzerine kurulmuştur. Birincisi, k tane en iyi bilinen öznitelik seçme yaklaşımı yardımı ile tüm özellik kümesinden en uygun alt küme OFS seçme işlemdir. İkinci bileşen ise, seçilen özellik alt kümesi OFS üzerinde kurallar oluşturmak için kaba kümeleme yöntemlerinin kullanılmasını içermektedir. Çalışmada, COVID-19a verilen duygusal tepkilerden elde edilen Gerçek Dünya Endişe Veri Kümesi adlı ilk elverişli gerçek veri kümesi kullanılmıştır. Veri kümesi 5.000 parçadan 2.500 kısa  2.500 uzun oluşmaktadır. Deneysel çalışmalarda, önerilen yaklaşımın hem etiketli hem de etiketsiz verilerle test edildiği ve 85in üzerinde bir doğruluk oranıyla etkili sonuçlar elde edildiği gözlemlenmiştir. Ayrıca, insanların salgın nedeniyle geleceğe yönelik yüksek oranda endişe duydukları belirlenmiştir.

Makale detayları

A RULE-BASED APPROACH USING THE ROUGH SET ON COVID-19 DATA

Yazarlar:

Rasim Çekik

Yayıncı:

Eskişehir Osmangazi University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 2, pp.1363-1375

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001324132

pISSN:

2630-5712

COVID-19

Sentiment Analysis

Rough Set

Text MiningCOVID-19

Sentiment Analysis

Rough Set

Text Mining

Sayı

Makale detayları

Yazarlar: Rasim Çekik

Yayıncı: Eskişehir Osmangazi University

Ana Başlıklar: Bilgisayar Yazılımı

Dergi: Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 2, pp.1363-1375

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001324132

pISSN: 2630-5712

Sayı

Yazarlar:

Rasim Çekik

Yayıncı:

Eskişehir Osmangazi University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 2, pp.1363-1375

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001324132

pISSN:

2630-5712