Indonesian General Analysis Dataset is a dataset sourced from social media twitter by using keywords in the form of conjunctions to get a dataset that does not only focus on a particular topic. The use of Indonesian language datasets with general topics can be used to test the accuracy of the classification model so as to provide additional reference in choosing the right methods and parameters for sentiment analysis. One of the algorithms which in several studies produces the highest level of accuracy is naive Bayes which has several variations. This study aims to obtain the method with the best accuracy from the naive Bayes variation by setting the minimum and maximum document frequency parameters on the Indonesian General Analysis Dataset for sentiment analysis. The naive Bayes classifier variations used include Bernoulli naive Bayes, gaussian naive Bayes, complement naive Bayes and multinomial naive Bayes. The research stage begins with downloading the dataset. Preprocessing becomes the next stage which consists of tokenizing, stemming, converting abbreviations and eliminating conjunctions. In the preprocessed data, feature extraction is carried out by converting the dataset into vectors and applying the TF-IDF method before entering the sentiment analysis classification stage. Tests in this study were carried out by applying the minimum document frequency (min-df) and maximum document frequency (max-df) for each variation of naive Bayes to obtain the appropriate parameters. The test uses k-fold cross validation of the dataset to divide the training data and sentiment analysis test data. The next confusion matrix is made to evaluate the level of accuracy.
Reporting the existence of waste is an essential thing in big cities because if the waste is not disposed of quickly it will cause new problem such as disease. One of the things to be done is by increasing community participation by utilizing technologies such as smartphones to report the existence of waste. Location-Based Service (LBS) uses GPS technology in its application. Besides being able to find out the user's position, the LBS application can also determine the position of the reported waste. If a user can maximize this technology, then he or she can help out waste workers to retrieve waste by solely reporting the waste location. This research produces a mobile application that can locate and display the user's and waste position. This application is the integration of google map services in determining the path between users and a place.
An emerging outbreak of Covid-19 has now been detected across the globe. Given this pandemic condition, the robust estimation reports are urgently needed. Therefore, this study aims to analyze the impacts of community mobility (before, during, and after the lockdown period) on the spread of the Covid-19 in Jakarta, Indonesia. The secondary data was derived from surveillance data for Covid-19 daily cases from the Health Office of DKI Jakarta Province and the Ministry of Health. The community mobility indicators were retrieved from the Google website. Our results showed that in the pre-lockdown period, the Covid-19 daily cases rapidly increased, while community mobility significantly dropped. The increasing number of Covid-19 daily cases was significantly affected by the number of Covid-19 tests per day rather than community mobility. During the restriction period, the number of Covid-19 tests per day, and community mobility statistically affected the decreasing number of Covid-19 daily cases. Meanwhile, after the lockdown period, the number of Covid-19 daily cases rapidly increased, which significantly has a direct relationship with the increasing level of community mobility. Overall, community mobility and the number of tests per day are the essential variables that explain the number of Covid-19 daily cases in Jakarta, Indonesia. Additionally, this study did not observe any impact of average air temperature and air pollution on the spread of Covid-19. This study figures out that community mobility could potentially explain the progression of Covid-19.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.