Analysis Sentiment Based on IMDB Aspects from Movie Reviews using SVM

A movie is a spectacle that can be done at a relaxed time. Currently, there are many movies that can be watched via the internet or cinema. Movies that are watched on the internet are sometimes charged to watch so that potential viewers before watching a movie will read comments from users who have watched the movie. The website that is often used to view movie comments today is IMDB. Movie comments are many and varied on the IMDB website, we can see comments based on the star rating aspect. This causes users to have difficulty analyzing other users' comments. So, this study aims to analyze the sentiment of opinions from several comments from IMDB website users using the star rating aspect and will be classified using the support vector machine method (SVM). Sentiment analysis is a classification process to understand the opinions, interactions, and emotions of a document or text. SVM is very efficient for many applications in science and engineering, especially for classification (pattern recognition) problems. In addition to the SVM method, the TF-IDF technique is also used to change the shape of the document into several words. The results obtained by applying the SVM model are 79% accuracy, 75% precision, and 87% recall. The SVM classification is also superior to other methods, namely logistic regression.

Particle Swarm Optimization-based Support Vector Machine Method for Sentiment Analysis in OVO Digital Payment Applications

Sentiment analysis is used to analyze reviews of a place or item from an application or website that then classified the review into positive reviews or negative reviews. reviews from users are considered very important because it contains information that can make it easier for new users who want to choose the right digital payment. Reviews about digital payment ovo are so much that it is difficult for prospective users of ovo digital payment applications to draw conclusions about ovo digital payment information. For this reason, a classification method is needed in this study using support vector machine and PSO methods. In this study, we used 400 data that were reduced to 200 positive reviews and 200 negative reviews. The accuracy obtained by using the support vector machine method of 76.50% is in the fair classification, while the accuracy obtained by using the support vector machine and Particle Swarm Optimization (PSO) method is 82.75% which is in good classification.

WhatsApp Chat Fraud Analysis Using Support Vector Machine Method

Fraud is one of the most cyber crime on social media. One of the popular social media in Indonesia is Whatsapp. Cases of fraud through chat on Whatsapp application often occur in Indonesia, its due to lack of information. The research conducted related to the detection of words containing fraud in WhatsApp chat application. The methods in this research applies the literature study method to find secondary data in the references theories and relevant research. The data collection is carried out by collecting chats that lead to fraud cases and then processing them using RapidMiner application with SVM (Support Vector Mechine) method. The results of this research can be concluded that this research succeeded in implementing SVM algorithm for whatsapp fraud chat analysis with an accuracy rate of 84.21%

Anomaly Detection of Electric Gate Valve Based on Multi-Kernel Support Vector Machine

Valve is an indispensable fluid control component in nuclear power system. Nuclear power station has a large number of gate valve equipment, which works under high temperature, high pressure, high radioactivity and other harsh conditions. In nuclear power plant accidents and economic losses, a considerable part of them are caused by valve failure. Aiming at the fault of electric gate valve, this paper proposes an anomaly detection method based on multi-kernel support vector machine. Firstly, the acoustic emission instrument is used to measure the fault state data and extract the fault features. Secondly, on the basis of classical support vector machine, multiple kernel function combinations are selected to decompose the model into convex optimization problems to realize the abnormal state detection of internal leakage fault of electric gate valve in nuclear power plant. The results show that, compared with the classical support vector machine method, the constructed support vector machine method based on multikernel learning has better effect and higher accuracy in anomaly detection of electric gate valve.

Forecasting the Number of Offset Printing Machine Breakdowns Using the Support Vector Machine (SVM) Metdhod

PT. MJT is a company engaged in manufacturing that produces various types of plastic tubes for cosmetic packaging. Production activities at PT. MJT uses an intermittent process, which in the printing division requires a longer total setup time because this process produces various types of specifications of goods to order. This has an effect on the amount of engine breakdown. The purpose of this research is to try the method of forecasting the number of breakdowns for offset printing machines at PT. MJT. One of the methods used in this research is the Support Vector Machine method. Support Vector Machine is a method that can help predict the number of breakdowns that will be experienced by the offset printing machine at PT. MJT. Support vector machine is a method that can reduce the error value in forecasting compared to other methods. From this research, it is hoped that it can produce a forecast of the number of breakdowns for offset printing machines at PT. MJT for a period of one year or twelve periods.