Sentimen Analisis Terkait Lockdown pada Sosial Media Twitter

Abstract: Covid-19 has been set as a Pandemic by the World Health Organization (WHO). The very large impact and the infection that is fast enough are the reasons for making Covid-19 as a pandemic and efforts to overcome. One anticipation that can be done is to do lockdown. Making the decision to carry out a lockdown is intended to reduce the spread that occurs. Lockdown is certainly not a 100% good solution for all of individual. There are individual who agree that the lockdown will be implemented, also there are those who think that the lockdown is better not to be carried out considering the negative impacts that can occur. Therefore in this study will be presented the predictive modeling for sentiment analysis related to "lockdown" specially on social media Twitter. The method used to labeled was using Vader then the tweets are extracted using TF-IDF, and modeling is made for the prediction of sentiment using Naïve Bayes and Support Vector Machine. The results obtained from the two algorithms are more than 80%. Keywords: Covid-19, lockdown, TF-IDF, Naïve Bayes, Support Vector Machine Abstrak: Covid-19 telah ditetapkan sebagia Pandemi oleh World Health Organization (WHO). Dampak yang sangat besar dan penyebaran yang cukup cepat menjadi alsan untuk menjadikan Covid-19 sebagai Pandemi dan perlu dilakukan upaya penanggulangan. Salah satu upaya yang bisa dilakukan adalah dengan melakukan lockdown. Pengambilan keputusan untuk melakukan lockdown diperuntukan guna mengurangi penyebaran yang terjadi. Lockdown tentunya bukanlah solusi yang 100% baik bagi segala pihak. Terdapat pihak - pihak yang menyetujui akan dilaksanakannya lockdown, ada pula yang beranggapan bahwa lockdown lebih baik tidak dilaksanakan dengan pertimbangan dampak negatif yang bisa terjadi. Oleh karena itu, pada penelitian ini akan disampaikan mengenai pembuatan pemodelan prediksi terkait analisa sentimen terkait “Lockdown” yang dikhususkan pada media sosial Twitter. Metode yang digunakan adalah dengan melakukan labeling menggunakan Vader dan selanjutnya tweet tersebut dilakukan ekstraksi menggunakan TF-IDF, dan dibuatkan pemodelan untuk prediksi sentimen menggunakan Naïve Bayes dan Support Vector Machine. Hasil evaluasi yang didapat dari kedua algoritma tersebut ialah mencapai lebih dari 80%. Kata kunci: Covid-19, lockdown, TF-IDF, Naïve Bayes, Support Vector Machine Abstract: Covid-19 has been set as a Pandemic by the World Health Organization (WHO). The very large impact and the infection that is fast enough are the reasons for making Covid-19 as a pandemic and efforts to overcome. One anticipation that can be done is to do lockdown. Making the decision to carry out a lockdown is intended to reduce the spread that occurs. Lockdown is certainly not a 100% good solution for all of individual. There are individual who agree that the lockdown will be implemented, also there are those who think that the lockdown is better not to be carried out considering the negative impacts that can occur. Therefore in this study will be presented the predictive modeling for sentiment analysis related to "lockdown" specially on social media Twitter. The method used to labeled was using Vader then the tweets are extracted using TF-IDF, and modeling is made for the prediction of sentiment using Naïve Bayes and Support Vector Machine. The results obtained from the two algorithms are more than 80%. Keywords:Covid-19, lockdown, TF-IDF, Naïve Bayes, Support Vector Machine Abstrak: Covid-19 telah ditetapkan sebagia Pandemi oleh World Health Organization (WHO). Dampak yang sangat besar dan penyebaran yang cukup cepat menjadi alsan untuk menjadikan Covid-19 sebagai Pandemi dan perlu dilakukan upaya penanggulangan. Salah satu upaya yang bisa dilakukan adalah dengan melakukan lockdown. Pengambilan keputusan untuk melakukan lockdown diperuntukan guna mengurangi penyebaran yang terjadi. Lockdown tentunya bukanlah solusi yang 100% baik bagi segala pihak. Terdapat pihak - pihak yang menyetujui akan dilaksanakannya lockdown, ada pula yang beranggapan bahwa lockdown lebih baik tidak dilaksanakan dengan pertimbangan dampak negatif yang bisa terjadi. Oleh karena itu, pada penelitian ini akan disampaikan mengenai pembuatan pemodelan prediksi terkait analisa sentimen terkait “Lockdown” yang dikhususkan pada media sosial Twitter. Metode yang digunakan adalah dengan melakukan labeling menggunakan Vader dan selanjutnya tweet tersebut dilakukan ekstraksi menggunakan TF-IDF, dan dibuatkan pemodelan untuk prediksi sentimen menggunakan Naïve Bayes dan Support Vector Machine. Hasil evaluasi yang didapat dari kedua algoritma tersebut ialah mencapai lebih dari 80%. Kata kunci: Covid-19, lockdown, TF-IDF, Naïve Bayes, Support Vector Machine

Download Full-text

Sentimen Analisis Terkait “Lockdown” pada Sosial Media Twitter

CSRID (Computer Science Research and Its Development Journal) ◽

10.22303/csrid.12.3.2020.143-149 ◽

2021 ◽

Vol 12 (3) ◽

pp. 143

Author(s):

Muhammad Dwison Alizah ◽

Arifin Nugroho ◽

Ummu Radiyah ◽

Windu Gata

Keyword(s):

Support Vector Machine ◽

World Health Organization ◽

Naive Bayes ◽

Naïve Bayes ◽

World Health ◽

Support Vector ◽

Health Organization

<em>Covid-19 telah ditetapkan sebagia Pandemi oleh World Health Organization (WHO). Salah satu antisipasi yang bisa dilakukan adalah dengan melakukan lockdown. Pada penelitian ini, akan disampaikan mengenai pembuatan pemodelan prediksi terkait analisa sentimen terkait “Lockdown” pada media sosial Twitter. Metode yang digunakan adalah dengan melakukan labeling menggunakan Vader dan selanjutnya tweet dilakukan ekstraksi menggunakan TF-IDF, dan dibuatkan pemodelan untuk prediksi sentimen menggunakan Naïve Bayes dan Support Vector Machine. Hasilnya yang didapat dari kedua algoritma tersebut ialah lebih dari 80%.</em><em> </em>

Download Full-text

Prediksi Penyakit Diabetes Melitus Menggunakan Metode Support Vector Machine dan Naive Bayes

Indonesian Journal on Software Engineering (IJSE) ◽

10.31294/ijse.v7i1.10279 ◽

2021 ◽

Vol 7 (1) ◽

pp. 63-68

Author(s):

Nurlaelatul Maulidah ◽

Riki Supriyadi ◽

Dwi Yuni Utami ◽

Fuad Nur Hasan ◽

Ahmad Fauzi ◽

...

Keyword(s):

Support Vector Machine ◽

World Health Organization ◽

American Diabetes Association ◽

Naive Bayes ◽

Naïve Bayes ◽

World Health ◽

Support Vector ◽

Health Organization ◽

Diabetes Melitus

Diabetes melitus adalah penyakit metabolik yang ditandai terjadinya kenaikan gula darah yang disebabkan oleh terganggunya hormon insulin yang memiliki fungsi sebagai hormon dalam menjaga homeostatis tubuh menggunakan cara penurunan kadar gula darah (American Diabetes Association, 2017). World Health Organization (WHO) memperkirakan jumlah penderita diabetes melitus orang dewasa diatas 18 tahun dalam tahun 2014 berjumlah 422 juta (WHO, 2016:25). Prevalensi diabetes melitus Asia Tenggara sudah berkembang dalam tahun 1980 sebanyak 4,1% dan tahun 2014 menjadi sebanyak 8,6%. Menurut Riset Kementerian Kesehatan pada tahun 2018, Prevalensi diabetes Indonesia sebanyak 2,0%, sedangkan di Provinsi Jawa Timur sebanyak 2,6% pada penduduk umur diatas 15 tahun (KEMENKES RI, 2019). Penelitian ini dikembangkan melalui pengolahan data sekunder database kesehatan Dataset Diabetes yang diambil dari dataset Kaggle dan dapat diakses melalui https://www.kaggle.com/johndasilva/diabetes. Dimana datanya sendiri terdiri dari 2000 record dengan beberapa variabel prediktor medik (Pregnancies/Kehamilan, Glucose/Glukosa, BloodPressure/Tekanan Darah, SkinThickness/Ketebalan Kulit, Insulin, BMI/Indeks Masa Tubuh, DiabetesPedigreeFunction/Keturunan, Age/Umur and Outcome/Hasil). Kemudian data tersebut akan diolah dengan menggunakan metode Support Vector Machine dan metode Naive Bayes untuk mengetahui akurasi hasil diagnosa diabetes. Berdasarkan hasil dari penelitian yang sudah dilakukan metode Support Vector Machine memiliki nilai akurasi yang jauh lebih tinggi dibandingkan dengan menggunakan metode Naive Bayes. Nilai akurasi untuk model metode Support Vector Machine adalah 78,04% dan nilai akurasi untuk metode Naive Bayes 76,98%. Berdasarkan nilai ini, perbedaan akurasinya adalah 1,06%. Sehingga dapat disimpulkan bahwa penerapan metode Support Vector Machine mampu menghasilkan tingkat akurasi diagnosis diabetes yang lebih baik dibandingkan dengan menggunakan metode Naive Bayes.

Download Full-text

Analisis Sentimen Opini Terhadap Vaksin Covid - 19 pada Media Sosial Twitter Menggunakan Support Vector Machine dan Naive Bayes

Jurnal Komtika ◽

10.31603/komtika.v5i1.5185 ◽

2021 ◽

Vol 5 (1) ◽

pp. 19-25

Author(s):

Frizka Fitriana ◽

Ema Utami ◽

Hanif Al Fatta

Keyword(s):

Support Vector Machine ◽

Naive Bayes ◽

Naïve Bayes ◽

World Health ◽

Support Vector ◽

Support Vector Machine Algorithm ◽

Bayes Algorithm ◽

Health Organization ◽

The Right ◽

The Impact

The corona virus outbreak, commonly referred to as COVID-19, has been officially designated a global pandemic by the World Health Organization (WHO). To minimize the impact caused by the virus, one of the right steps is to develop a vaccine, however, with the vaccination for the Indonesian people, it is controversial so that it invites many people to give an opinion assessment, but the limited space makes it difficult for the public to express their opinion, because Therefore, people choose social media as a place to channel public opinion. Support vector machine algorithm has better performance in terms of accuracy, precision and recall with values of 90.47%, 90.23%, 90.78% with performance values on the Bayes algorithm, namely 88.64%, 87.32%, 88, 13%, with a difference of 1.83% accuracy, 2.91% precision and 2.65% recall, while for time the Naive Bayes algorithm has a better performance level with a value of 8.1 seconds and the Support vector machine algorithm gets a time speed of 11 seconds with a difference of 2, 9 seconds. With the results of sentiment analysis neutral 8.76%, negative 42.92% and positive 48.32% for Bayes and neutral 10.56%, negative 41.28% and positive 48.16% for SVM.

Download Full-text

Analisis Sentimen Twitter Kuliah Online Pasca Covid-19 Menggunakan Algoritma Support Vector Machine dan Naive Bayes

Jurnal Komtika ◽

10.31603/komtika.v5i1.5189 ◽

2021 ◽

Vol 5 (1) ◽

pp. 43-51

Author(s):

Hendrik Setiawan ◽

Ema Utami ◽

Sudarmawan Sudarmawan

Keyword(s):

Support Vector Machine ◽

World Health ◽

Support Vector ◽

Online Lectures ◽

Svm Algorithm ◽

The World ◽

The Government ◽

Bayes Algorithm ◽

Health Organization ◽

Performance Results

The World Health Organization (WHO) COVID-19 is an infectious disease caused by the Coronavirus which originally came from an outbreak in the city of Wuhan, China in December 2019 which later became a pandemic that occurred in many countries around the world. This disease has caused the government to give a regional lockdown status to give students the status of "at home" for students to enforce online or online lectures, this has caused various sentiments given by students in responding to online lectures via social media twitter. For sentiment analysis, the researcher applies the nave Bayes algorithm and support vector machine (SVM) with the performance results obtained on the Bayes algorithm with an accuracy of 81.20%, time 9.00 seconds, recall 79.60% and precision 79.40% while for the SVM algorithm get an accuracy value of 85%, time 31.60 seconds, recall 84% and precision 83.60%, the performance results are obtained in the 1st iteration for nave Bayes and the 423th iteration for the SVM algorithm

Download Full-text

KLASIFIKASI TUMOR JINAK DAN TUMOR GANAS PADA CITRA MAMMOGRAM MENGGUNAKAN GRAY LEVEL CO-OCCURRENCE MATRIX (GLCM) DAN SUPPORT VECTOR MACHINE (SVM)

Jurnal Ilmiah Informatika Komputer ◽

10.35760/ik.2021.v26i2.4897 ◽

2021 ◽

Vol 26 (2) ◽

pp. 176-186

Author(s):

Lulu Mawaddah Wisudawati

Keyword(s):

Support Vector Machine ◽

World Health Organization ◽

Computer Aided Diagnosis ◽

World Health ◽

Support Vector ◽

Gray Level ◽

Computer Aided ◽

Health Organization ◽

Occurrence Matrix ◽

Aided Diagnosis

Kanker payudara merupakan penyebab utama kematian pada wanita. Data Global Cancer Observatory 2018 dari World Health Organization (WHO, 2020) menunjukkan kasus kanker yang paling banyak terjadi di Indonesia adalah kanker payudara, yakni 58.256 kasus atau 16.7% dari total 348.809 kasus kanker. Mamografi merupakan teknik yang paling umum digunakan dalam mendeteksi tumor payudara menggunakan sistem sinar-X dosis rendah. Ada beberapa tipe abnormalitas dalam citra mammogram, yaitu mikrokalsifikasi dan massa. Penelitian ini bertujuan untuk meningkatkan performa sistem Computer-Aided Diagnosis (CAD) dalam mengklasifikasi tumor jinak dan tumor ganas dengan mengembangkan metode ekstraksi fitur menggunakan Gray Level Co-Occurrence Matrix (GLCM) dan metode klasifikasi menggunakan Support Vector Machine (SVM). Uji coba dilakukan dengan menggunakan database DDSM dengan 256 citra abnormal (95 tumor jinak dan 161 tumor ganas) menghasilkan nilai akurasi sebesar 83.59% dengan nilai sensitivitas dan spesifisitas 87.58% dan 76.84%. Selain itu, didapatkan nilai AUC sebesar 0.98%. Metode tersebut menunjukkan bahwa sistem memberikan hasil performa yang baik dalam mengklasifikasi tumor jinak dan tumor ganas.

Download Full-text

Machine Learning Based Coronary Artery Disease Prediction

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9007 ◽

2020 ◽

Vol 17 (9) ◽

pp. 3999-4002

Author(s):

A. C. Bhavani ◽

K. Aditya Shastry ◽

K. Deepika ◽

Nithya N. Shanbag ◽

G. C. Akshatha

Keyword(s):

Machine Learning ◽

Coronary Artery ◽

Medical Diagnosis ◽

Performance Metrics ◽

Naive Bayes ◽

Naïve Bayes ◽

Machine Learning Techniques ◽

World Health ◽

Support Vector ◽

Health Organization

The world health organization (WHO) has assessed that the death of around 12 million people across the globe is observed each year because of diseases related to cardiovascular. The dangers associated with the cardiovascular disease can be identified effectively using machine learning techniques. As per survey, around 30% of the patient suffers no symptoms during heart attacks. But the bloodstream contains unique indications of the attack for days. The medical diagnosis of a patient remains a complex task due to several factors. The accurate medical diagnosis of a patient’s heart disease is critical as it significantly leads to the saving of millions of human lives. In this regard, the automation of the medical diagnosis is significant. The goal of this work is the development of a system for predicting the disease related to coronary artery in a patient with high accuracy utilizing machine learning (ML) techniques. Several algorithms like Naïve Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT) classifiers were implemented for predicting the disease. Extensive experiments demonstrated that the naïve Bayes achieved higher accuracy than the DT and SVM with regards to accuracy, precision, F-Measure, Recall, and receiver operating characteristic (ROC) performance metrics.

Download Full-text

Implementasi Metode Naive Bayes Untuk Memprediksi Resiko Penyakit Jantung

Patria Artha Technological Journal ◽

10.33857/patj.v4i2.351 ◽

2020 ◽

Vol 4 (2) ◽

pp. 66-70

Author(s):

firman Tempola

Keyword(s):

Machine Learning ◽

World Health Organization ◽

Naive Bayes ◽

Naïve Bayes ◽

World Health ◽

Health Organization

Kematian akibat penyakit jantung terus meningkat dan tak mengenal usia muda dan tua. World Health Organization menyebutkan 7,3 juta penduduk dunia meninggal akibat dari penyakit jantung. Bahkan disebutkan penyakit jantung adalah salah penyakit nomor satu paling mematikan. Untuk itu penting diketahui resiko dari pentakit jantung dengan menerapkan model-model yang ada pada machine learning. Tujuan dari penelitian ini yaitu untuk mengimplementasikan metode Naive Bayes untuk memprediksi penyakit jantung, serta dilakukan ujii kinerja algoritma dengan menghitung presisi, recall dan akurasi. Adapun Kriteria-kriteria yang digunakan pada penelitian ini yaitu umur, jenis kelamin, jenis sakit dada, tekanan darah, kolestrol, kadar gula, elektrokardiografi, tekanan jantung, angina induksi, old-peak, segmen_st, Fluoroskopi, denyut jantung. Sedangkan class yang diprediksi ada 2 beresiko dan tidak beresiko. Hasil dalam penelitian ini menunjukan bahwa metode berhasil memprediksi atau mengklasifikasi pasien beresiko penyakit jantung dan tidak beresiko penyakit jantung dengan persentase precision 90%, recall 100% serta mendapatkan akurasi 92.85% dan termaksuk exellent classification.

Download Full-text

A Dataset Centric Feature Selection and Stacked Model to Detect Breast Cancer

International Journal of Intelligent Systems and Applications ◽

10.5815/ijisa.2021.04.03 ◽

2021 ◽

Vol 13 (4) ◽

pp. 24-37

Author(s):

Avijit Kumar Chaudhuri ◽

◽

Dilip K. Banerjee ◽

Anirban Das

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Support Vector Machine ◽

Random Forest ◽

Decision Tree ◽

Naive Bayes ◽

Naïve Bayes ◽

World Health ◽

Support Vector ◽

Kappa Statistics

World Health Organisation declared breast cancer (BC) as the most frequent suffering among women and accounted for 15 percent of all cancer deaths. Its accurate prediction is of utmost significance as it not only prevents deaths but also stops mistreatments. The conventional way of diagnosis includes the estimation of the tumor size as a sign of plausible cancer. Machine learning (ML) techniques have shown the effectiveness of predicting disease. However, the ML methods have been method centric rather than being dataset centric. In this paper, the authors introduce a dataset centric approach(DCA) deploying a genetic algorithm (GA) method to identify the features and a learning ensemble classifier algorithm to predict using the right features. Adaboost is such an approach that trains the model assigning weights to individual records rather than experimenting on the splitting of datasets alone and perform hyper-parameter optimization. The authors simulate the results by varying base classifiers i.e, using logistic regression (LR), decision tree (DT), support vector machine (SVM), naive bayes (NB), random forest (RF), and 10-fold crossvalidations with a different split of the dataset as training and testing. The proposed DCA model with RF and 10-fold cross-validations demonstrated its potential with almost 100% performance in the classification results that no research could suggest so far. The DCA satisfies the underlying principles of data mining: the principle of parsimony, the principle of inclusion, the principle of discrimination, and the principle of optimality. This DCA is a democratic and unbiased ensemble approach as it allows all features and methods in the start to compete, but filters out the most reliable chain (of steps and combinations) that give the highest accuracy. With fewer characteristics and splits of 50-50, 66-34, and 10 fold cross-validations, the Stacked model achieves 97 % accuracy. These values and the reduction of features improve upon prior research works. Further, the proposed classifier is compared with some state-of-the-art machine-learning classifiers, namely random forest, naive Bayes, support-vector machine with radial basis function kernel, and decision tree. For testing the classifiers, different performance metrics have been employed – accuracy, detection rate, sensitivity, specificity, receiver operating characteristic, area under the curve, and some statistical tests such as the Wilcoxon signed-rank test and kappa statistics – to check the strength of the proposed DCA classifier. Various splits of training and testing data –namely, 50–50%, 66–34%, 80–20% and 10-fold cross-validation – have been incorporated in this research to test the credibility of the classification models in handling the unbalanced data. Finally, the proposed DCA model demonstrated its potential with almost 100% performance in the classification results. The output results have also been compared with other research on the same dataset where the proposed classifiers were found to be best across all the performance dimensions.

Download Full-text