In today’s era, company performance is influenced by quick and easy responses to interacting with users. Twitter is one of the social media which is believed that public opinion on Twitter can influence the government or companies to make policies. Public criticism on Twitter is more quickly responded than people who contacting customer service directly, this is because the companies or government do not want their image to be bad due to delays in responding to public complaints on Twitter. Studies related to opinion writing on social media can use the method of topic modeling and sentiment analysis in order to get what topics are currently being discussed and also the value of their sentiments. Modeling of the topic was carried out using Latent Dirichlet Allocation and sentiment analysis using the Indonesian Sentiment Lexicon. A case study of public opinion on BPJS Kesehatan using Twitter data for 3 months from February to April 2020, obtained 5 main topics with the BPJS Kesehatan’s New Contribution Rate as a trending topic with a sentiment value of 61.7% positive and 38.3% negative.
Every piece of information contained in a story sometimes has a variety of themes and seems not specific so there is difficulty in digesting information simultaneously. This requires grouping based on the topic relevance of the news. This grouping can make it easier for readers to get the information in accordance with the topic you want to read. Each news group must have different information characteristics so that we need a special algorithm that is able to handle topic discovery and classification using training data on many Indonesian news articles. This research will apply an algorithm of Porter Stemmer Enhancement in the stemming process and Likelihood method for news classification based on categories and identification of topics. Based on the test results using 900 training data and 90 test data, obtained a fairly high accuracy, namely 95.56% for category classification and 97.78% for topic identification.
There are many problems in the real world that can be modeled as large scale global optimization problems. Usually, large scale global optimization problems are global optimization problems where the dimensions are greater than or equal to 1000. In this research, we propose a genetic algorithm that can be used to solve large scale optimization problems with dimensions up to 100000. To measure the capabilities of the proposed genetic algorithm, we use five different test functions. Based on the results obtained, it can be inferred that the proposed genetic algorithm can find a good solution in a fairly short time.
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.