The quality of a movie can be known from the opinions or reviews of previous audiences. This classification of reviews is grouped into positive opinions and negative opinions. One of the data mining algorithms that are most frequently used in research is the Support Vector Machine because it works well as a method of classifying text but has a very sensitive deficiency in the selection of features. The Information Gain method as feature selection can solve problems faster and more stable convergence levels. After testing on two movie review datasets are Cornell and Stanford datasets. The results obtained on the Cornell dataset is the Support Vector Machine algorithm to produce an accuracy of 83.05%, while for the Support Vector Machine based on Information Gain, the accuracy value is 85.65%. Increased accuracy reached 2.6%. Then, the results obtained on the Stanford dataset is the Support Vector Machine algorithm yields a value of 86.46%, while for the Support Vector Machine based on Information Gain, the accuracy value is 86.62%. Increased accuracy reached 0.166%. Support Vector Machine based Information Gain on the problem of movie review sentiment analysis proved to provide more accurate value.

Cancer is something big in the world. Cancer is a malignant disease that is difficult to cure if the spread is too wide. However, detecting cancer cells as early as possible can reduce the risk of death. This study aims to predict the level of early detection of disasters in European countries using 5 classification algorithms, namely: Desecion Tree, Naïve Bayes, k-Nearset Neighbor, Random Forest and Neural Network of which algorithm is the best for this study. Tests carried out with several stages of research include: dataset (data contains), initial data processing, proposed method, credit method using 10 times cross validation, test results and t-test different tests. The alpha value is 0.05. if the probability is> 0.05 then H0 is accepted. If the probability is <0.05 then Ho is rejected. The results of the research that obtained performance with an accuracy value of 98.35% were the Neural Network algorithm. Whereas, the results of the research usi ng the algirtic t-test with the best models are: Random Forest algorithm and Neural Network, the relatively good Naïve Bayes algorithm, the Desecion Tree algorithm is quite good and the poor algorithm is the K- Nearset Neighbor (K-NN) algorithm.

School is a teaching and learning institution. The problem observed in schools, in general, is that there is still no centrally managed web-based system, one of which is the loss of facility and infrastructure inventory data that is still maintained using Microsoft Excel, or the absence of a unique system to summarize it. Inventory data of facilities and infrastructure in the database or online. If information is needed, the school should look up each one in the office files. As a result of these problems, an application is needed in the form of a site information system and web-based infrastructure, every year the amount of data owned by schools increases and it is difficult to manage it. The manual summary is used to assist service schools in processing data such as information on the inventory of facilities and infrastructure. This research aims to develop an information system capable of managing real estate and infrastructure information in a web-based database system so that the system can connect to the Internet quickly and accurately. The author uses XAMPP as a local hosting server, which includes Apache as an HTTP server, MySQL as a database, Sublime Text 3 as a sentence editor for HTML and PHP scripts, and PHP as a programming language, and uses a browser to view output from web pages, and creates a database with SQL Yog.

Each Regional Apparatus Work Unit (SKPD) must report the use of the budget or realization report to BAPPEDA. Each SKPD officer submits a realization report to the Secretariat. If an error occurs in the preparation of the realization report, the wrong SKPD will be informed again and must re-create and repeat the administration process for reporting realization. This is deemed ineffective, because each SKPD must come to the office only to submit a realization report and also charge officers who fill in the realization data for each SKPD. Therefore, this writing contains research to solve the problems faced by BAPPEDA Kubu Raya Regency by building a web-based SKPD realization reporting administration information system that uses the waterfall model as a software development model consisting of analysis, design, coding, testing. and supporters. Data collection techniques used consisted of observation, interviews and literature study. This system provides facilities to two (2) levels of users, namely Secretariat officers and SKPD officers. Secretariat officers can manage SKPD data, users, descriptions, programs, activities, access RKA-SKPD reports and realization reports. SKPD officers can change SKPD data, manage users, manage RKA-SKPD, access RKA-SKPD reports (personal), manage realization transactions and access realization reports (personal). This system is made using hypertext preprocessor (PHP) programming language, hypertext markup language (HTML), cascading style sheet (CSS), jquery, javascript and bootstrap as well as codeigniter as a framework, MySQL as a database application and sublime text as a web editor. This system is expected to help and be used as a tool in the administration of reporting on the realization of SKPD at BAPPEDA Kubu Raya Regency

The intrusion detection system is an important component that performs the analysis for. the problem arising from the IDS is a collection of data sets in a computer network. to increase the high level and low false positive level of approach with the learning machine in applied. The data mining algorithm used is Naïve bayes one of the most widely used algorithms in space due to its simplicity, efficiency and effectiveness. NB has high accuracy and speed when applied into the database with large data. However, the NB algorithm assumes independent attributes (free) and is very sensitive to the selection of many features that interfere with the performance or accuracy of the NB to be low but in practice, the possibilities of the feature are interrelated. The Feature Dependent Naïve Bayes (FDNB) method is an effective method used to solve existing problems in NB by computing features as pairs and creating dependencies between each other as well as by applying learning models implemented to cross-validation, Feature Selection and data steps preprocessing that gives better accuracy results. After testing with two models of Naïve bayes and FDNB, the results obtained from the Naïve Bayes algorithm resulted in an accuracy of 84.42%, while for FDNB and oversampling (CFS + GS) the accuracy was 94.58%, FDNB and oversampling (CFS + BFS) the accuracy value of 94.69%, FDNB and SMOTE (CFS + GS) and FDNB and SMOTE (CFS + BFS) has an accuracy value of 93.27%. For the average per attack type DOS attack shows the highest result for its accuracy value of 97.86% and U2R attack produces the best accuracy when classifying U2R with 93.80% accuracy, U-F size of 96.26% U2R can be considered as a very result nice. Because U2R attack is considered very dangerous.