Sentiment analysis can detect hate speech using the Natural Language Processing (NLP) concept. This process requires annotation of the text in the labeling. However, when carried out by people, this process must use experts in the field of hate speech, so there is no subjectivity. In addition, if processed by humans, it will take a long time and allow errors in the annotation process for extensive data. To solve this problem, we propose an automatic annotation process with the concept of semi-supervised learning using the K-Nearest Neighbor algorithm. This process requires feature extraction of term frequency-inverse document frequency (TF-IDF) to obtain optimal results. KNN and TF-IDF were able to annotate and increase the accuracy of < 2% from the initial iteration of 57.25% to 59.68% in detecting hate speech. This process can annotate the initial dataset of 13169 with the distribution of 80:20 of training and testing data. There are 2370 labeled datasets; for testing, there are 1317 unannotated data; after preprocessing, there are 9482. The final results of the KNN and TF-IDF annotation processes have a length of 11235 for annotated data.

Communication is the key to conquering this globalization era. And there is no doubt that the language is the most important part of communication. One can communicate well when using the same language or understanding the language used to each other.Sign language is the language of communication priority manually, body language and lip motion in communicating. Sign language has been standardized by the name Sibi (Cue System Indonesian). Sibi is one of the media in the form of books, can help communication among the deaf in the community. His form is setting a systematic set of fingers, hands, and other movements that symbolize Indonesian vocabulary. Media book seems less easily understood by the user, so the need for an application that is able to provide an image that is moving, making it easier to learn the sign language.

Preparation of oil palm cultivation land is the initial physical activity of the planting area. Prior to oil palm cultivation it is advisable to study potential land suitability, to assess the land as appropriate or not to oil palm growth and support crop productivity. Potential land evaluation includes an example of a consideration where it requires the right decision to make a potential land-cultivation way to support crop productivity more effectively. Therefore, system with the PROMETHEE (Preference Ranking Organization for Enrichment Evaluation) method is built because of the ability to handle multiple comparisons, indicating priorities and preferences for each criterion by focusing on values. The criteria needed are: Rainfall, Dry Moon, Topography, Above Sea Level, Soil Acidity, Slope Tilt and Peat Density. The results achieved in this research is decision support system that yields recommendation of potential land of oil palm cultivation, which can be considered by decision maker in determination of potential land of oil palm cultivation.

An organization requires an integration if composed of members who live in different places. Organization requires the automation of business processes by exchanging business documents from applications and system platforms are different, both inside or outside the area of the organization. In this study, an application will be prepared by applying web service technology utilizing REST Web Service Arsitecture, where the server and client can interact with a unified interface, server and client will menghost resource to consume resources provided by the server. Research is organized so that the business processes that occur when a consumer (client) do a query or search items, integrated with web applications. Server provides a client API which is then utilized. Client in this application is a web application. After receiving data from the client, the server and then disseminate the information needs of the goods in question to all members.

Javanese script is one of the languages which are a typical Javanese culture. Javanese script is seen in its use in writing the name of a particular agency or location that has historical and tourism value. The use of Javanese script in public places makes the existence of this script seen by many people, not only by the Javanese people. Some of them have difficulty recognizing the Javanese characters they encounter. One method of pattern recognition and image processing is Convolutional Neural Network (CNN). CNN is a method that uses convolution operations in performing feature extraction on images as a basis for classification. The process consists of initial data processing, classification, and syllable formation. The classification consists of 48 classes covering Javanese script types, namely basic letters (Carakan) and voice-modifying scripts (Sandhangan). It is tested with multi-class confusion matrix scenarios to determine the accuracy, precision, and recall of the built CNN model. The CNN architecture consists of three convolution layers with max-pooling operations. The training configuration includes a learning rate of 0.0001, and the number of filters for each convolution layer is 32, 64, and 128 filters. The dropout value used is 0.5, and the number of neurons in the fully-connected layer is 1,024 neurons. The average performance value of accuracy reached 87.65%, the average precision value was 88.01%, and the average recall value was 87.70%.