Sentiment Analysis of the Use of Telecommunication Providers on Twitter Social Media using Convolutional Neural Network

Telecommunication technology continues to develop starting from 1G, 2G, 3G, 4G, and currently entering the 5G era. The Global System for Mobile Communications (GSM) based telecommunication industry in Indonesia consists of three big names: Telkomsel, XL, and Indosat. During the Covid-19 pandemic, activities carried out outside the home should be done online. People hope that the internet network can work properly. However, the reality is not as expected, because many networks are experiencing slow internet problems and many complaints are delivered through social media. Therefore, this research aims to find the insight opinions that have been conveyed to the telecommunications operator in social media. This research used the Convolutional Neural Network (CNN) algorithm to classify text sentiment (negative or positive) about telecommunication providers. The experiment with text data from Twitter is conducted after preprocessing and weighting of the Word2Vec process. The confusion matrix experiment shows that the CNN algorithm's performance reaches an average accuracy value of around 86.22%. The experiment was carried out by dividing the training data and testing the data 5 times in 10 times. The study results indicated that disruption of cellular telecommunications operators provided many sentiments, especially negative sentiment at the beginning of the COVID-19 pandemic. © 2022 IEEE.

Game Popularity Level During Covid-19 Pandemic Using Agglomerative Hierarchical Clustering

During the COVID-19 pandemic, various activities of people outside the home were disrupted and made people move more indoors. For some companies take advantage of this pandemic period as their advantage, especially digital game industry companies. Various games have been released and promoted, these games are published on various game platforms. Currently, Steam is one of the biggest gaming platforms. On this platform, there are a lot of games offered by game developers and provide game pages that are currently popular. However, the website does not provide the popularity level of the currently popular games. This causes ambiguity in determining which games have high, medium, or low popularity. This study tries to create a machine learning model to cluster these games into groups using Agglomerative Hierarchical Clusterin. The distance measure used is euclidean, cosine and manhattan/cityblock and uses single, average, complete and ward linkage. Based on the evaluation results, the best cluster results are the silhouette value of 0.639 and the calinski-harabasz value of 90.192. © 2022 IEEE.

Sentiment Analysis as Assessment of the COVID-19 Social Assistance Pollemic using Random Forest Algorithm

The government's endeavors in organizing the COVID-19 Social Assistance program often encounter problems and lead to the opinion of many parties. One of the opinions expressed on social media is twitter. Sentiments from these opinions were then analyzed to find out the assessment and discussion of each sentiment that can be used as evaluation material for the Social Assistance program. In this study, the sentiment of each preprocessed text was obtained using a labeling process with an assessment of polarity and subjectivity from TextBlob library. The results of neutral, positive, and negative sentiment assessments were weighted using TFIDF. Words that have been formatted into numeric then classified using the Random Forest algorithm. The parameters in this case were in accordance with the documentation on sklearn. An evaluation of the algorithm was also carried out using the 10 kfold cross validation method as a performance validation of the results of testing each piece of data. The performance obtained is quite satisfactory. © 2022 IEEE.

Implementation of K-Nearest Neighbor to Predict the Chances of COVID-19 Patients' Recovery

Coronavirus Disease 2019 (COVID-19) is a new disease discovered in 2019 in Wuhan, China, and then spread worldwide. Many victims have confirmed varying positive levels of infection based on the patient's immunity. This study aimed to predict the chances of COVID-19 patients' recovery based on the patient's symptoms and conditions. The method used is the K-Nearest Neighbor (KNN) algorithm. KNN produces two classes of predictions: the chance of recovering or the possibility of dying. Based on the experimental results on 496 data from patients who were confirmed positive for COVID-19, KNN predicted the chances of recovery for patients with confirmed COVID-19 with an average accuracy of 88.16%. A prediction system for the chance of recovery for COVID-19 patients is constructed by choosing the best model from five test scenarios based on the given k value. The best model is at a value of k equal to 4, with an accuracy value of 88.8%. © 2022 IEEE.