1 March 2019 in Journal of Physics: Conference Series
DPDavid Frietz Pangaribuan
Developments in information technology are increasing impact on communication and information exchange. One of its development is Twitter. The widespread use of social media has resulted in the availability of a large textual information so that it appears the need of presenting data that will allow users to get accurate information. This research will be conducted sentiment analysis on Twitter against election debates governor Jakarta to know the public response to some public figures. Ahead of the elections, many of the people who responded to a public figure in the social media Twitter. Public figures referred to in the study was the candidate of the Jakarta governor which are Basuki Tjahaja Purnama, Anies Rasyid Baswedan, and Harimurti Agus Yudhoyono. Based on this research, it will use the keyword 'Basuki' or 'Ahok' 'Agus' 'Badwater' 'pilgub' 'election' and 'debat' on Twitter sentiment in Indonesian language. Tweet contains a sentiment that has been collected, will be seen its profile location so it can be considered whether the user was included in the province of Jakarta or outside of Jakarta. Each tweet sentiments of these two categories will then be preprocessing to make it easy to be processed and analyzed. After passing through the phase, it will be calculated for each category with Naive Bayes algorithm in order to get the value of the sentiment of the people residing in the provinces of Jakarta and outside Jakarta to the three candidates for the Jakarta governor.
1 March 2019 in Journal of Physics: Conference Series
Artificial Neural Network (ANN) is a learning method that can be used for prediction and classification. In this study, ANN back-propagation is implemented to predict the closing price of the S&P 500 stock exchange using historical data. Historical data consisting of five variables, namely open, high, low, close, and volume. The historical data are taken from finance.yahoo.com which stores historical data of daily stock prices up to 65 years earlier. The data is designed based on daily prediction scenarios of the closing stock price of the S&P 500 stock exchange. Using the scenario an application prototype using R and Java software has been successfully built. The prototype is dynamic during select the data set (10, 50, 100, 500 past data) to get the best stock closing prediction for the next day. The selection of the best stock closing prediction uses the MAPE (Mean Average Percentage Error) criterion which is in contrast to the prediction accuracy level. The smaller the MAPE value the better the predicted result. Based on the implementation results, the average MAPE for daily forecast for 1 month in April 2017 was 0.2307 indicating that the average daily prediction accuracy rate for 1 month was 99.77%. Our prototype application can make prediction automatically every day, every time when connected to the internet.