Sentiment Analysis about Large-Scale Social Restrictions in Social Media Twitter Using Algoritm K-Nearest Neighbor

Sentiment analysis is a data processing to recognize topics that people talk about and their sentiments toward the topics, one of which in this study is about large-scale social restrictions (PSBB). This study aims to classify negative and positive sentiments by applying the K-Nearest Neighbor algorithm to see the accuracy value of 3 types of distance calculation which are cosine similarity, euclidean, and manhattan distance for Indonesian language tweets about large-scale social restrictions (PSBB) from social media twitter. With the results obtained, the K-Nearest Neighbor accuracy by the Cosine Similarity distance 82% at k = 3, K-Nearest Neighbor by the Euclidean Distance with an accuracy of 81% at k = 11 and K-Nearest Neighbor by Manhattan Distance with an accuracy 80% at k = 5, 7, 9, 11, and 13. So, in this study the K-Nearest Neighbor algorithm with the Cosine Similarity Distance calculation gets the highest point.

The Hybrid of Jaro-Winkler and Rabin-Karp Algorithm in Detecting Indonesian Text Similarity

The String-matching technique is part of the similarity technique. This technique can detect the similarity level of the text. The Rabin-Karp is an algorithm of string-matching type. The Rabin-Karp is capable of multiple patterns searching but does not match a single pattern. The Jaro-Winkler Distance algorithm can find strings within approximate string matching. This algorithm is very suitable and gives the best results on the matching of two short strings. This study aims to overcome the shortcomings of the Rabin-Karp algorithm in the single pattern search process by combining the Jaro-Winkler and Rabin-Karp algorithm methods. The merging process started from pre-processing and forming the K-Gram data. Then, it was followed by the calculation of the hash value for each K-Gram by the Rabin-Karp algorithm. The process of finding the same hash score and calculating the percentage level of data similarity used the Jaro-Winkler algorithm. The test was done by comparing words, sentences, and journal abstracts that have been rearranged. The average percentage of the test results for the similarity level of words in the combination algorithm has increased. In contrast, the results of the percentage test for the level of similarity of sentences and journal abstracts have decreased. The experimental results showed that the combination of the Jaro-Winkler algorithm on the Rabin-Karp algorithm can improve the similarity of text accuracy.

Usability of Jawara Sains Mobile Learning Application Using System Usability Scale (SUS)

The application of interactive learning multimedia is one of the factors that impact the learning process for achieving learning outcomes. In developing a mobile application, the main principle is usability. This research goal is to presents a usability evaluation of the Jawara Sains, which is a mobile application to learn science subjects. This research used a System Usability Scale (SUS) questionnaire to measure the level of users’ perceived usability. This score can indicate the usability performance of effectiveness, efficiency, and ease of use. Jawara Sains's SUS score achieved 75.45, which indicates a B grade, acceptable, and categorized in the good range. This score can also indicate whether a user is a promoter or not. The analysis showed that the Jawara Sains is categorized into the passive Net Promoter Score (NPS), which means users will not influence other people. Therefore, recommendations are needed for its usability improvements.

Comparison of Machine Learning Classification Methods in Hepatitis C Virus

The hepatitis C virus (HCV) is considered a problem to the health of societies are the main. There are around 120-130 million or 3% of the world's total population infected with HCV. Without treatment, most major infectious acute evolve into chronic, followed by diseases liver, such as cirrhosis and cancer liver. The data parameters used in this study included albumin (ALB), bilirubin (BIL), choline esterase (CHE), -glutamyl-transferase (GGT), aspartate amino-transferase (AST), alanine amino-transferase (ALT), cholesterol (CHOL), creatinine (CREA), protein (PROT), and Alkaline phosphatase (ALP). This research proposes a methodology based on machine learning classification methods including k-nearest neighbors, naïve Bayes, neural network, and random forest. The aim of this study is to assess and evaluate the level of accuracy using the algorithm classification machine learning to detect the disease HCV. The result show that the accuracy of the method NN has a value of accuracy are high, namely at 95.12% compared to the method KNN, naïve Bayes and RF in a row amounted to 89.43%, 90.24%, and 94.31%.

Prediction System for Problem Students using k-Nearest Neighbor and Strength and Difficulties Questionnaire

The student counseling process is the spearhead of character development proclaimed by the government through education regulation number 20 of 2018 concerning strengthening character education. Counseling at the secondary school level carries out to attend to these problems that might resolve with a decision support system. So that makes research challenging to measure completion on target because it is not doing based on data. The counseling teacher does not know about student's mental and emotional health conditions, so it is often wrong to handle them. Therefore, we need a system that can recognize conditions and provide recommendations for managing problems and predicting students who have potential issues. The Algorithm used to predict problem students is K-Nearest Neighbor with a dataset of 100 students. The stages of predictive calculation are data collection, data cleaning, simulation, and accuracy evaluation. Meanwhile, building the system is done using the rapid application development methodology where the instrument used to map the student's condition is the Strenght and Difficulties Questionaire instrument. This research is a system to predict problem students with an accuracy rate of 83%. The level of user experience based on the User Experience Questionnaire (UEQ) results in the conclusion that the system reaches "Above Average.". This system is expecting to help counseling teachers implement an early warning system, help students know learning modalities, and help parents recognize the child's personality better.

Implementation of Fuzzy C-Means for Clustering the Majelis Ulama Indonesia (MUI) Fatwa Documents

Since the Indonesian Ulema Council (MUI) was established in 1975 until now, this institution has produced 201 edicts covering various fields. Text mining is one of the techniques used to collect data hidden from data that form text. One method of extracting text is Clustering. The present study implements the Fuzzy C-Means Clustering method in MUI fatwa documents to classify existing fatwas based on the similarity of the issues discussed. Silhouette Coefficient is used to analyze the resulting clusters, with the best value of 0.0982 with 10 clusters grouping. Classify fatwas based on the similarity of the issues discussed can make it easier and faster in the search for an Islamic law in Indonesia.

Interactive Learning Media for Cellular Communication Systems using the Multimedia Development Life Cycle Model

Based on the observations conducted to the students of Diploma of Telecommunications Engineering Telkom University. It revealed that the students have difficulty learning and understanding the chapters of call processing and network optimization in the course of cellular communication systems. It has resulted from the current learning media, which are only in the form of textbooks and Powerpoint slides considered less attractive. Hence, the learning process becomes ineffective and has an impact on low learning outcomes. In this study, an interactive learning media was designed with the Multimedia Development Life Cycle (MDLC) method, Adobe Flash professional CS6 software, using the action script 2.0 programming language. Learning media were designed according to users’ needs and learning outcomes of cellular communication system courses. Based on the testing results, the functionality showed 100% of features function as design specifications. Meanwhile, the user satisfaction testing results obtained an average MOS of 4.73, which means that the learning media is classified great. Furthermore, based on the quantitative testing, the average value of Quiz after using this interactive learning media was 81, which means that the learning media can increase students’ interest so that it affects the increase in learning outcomes by 66% from previous years.

A Fast Dynamic Assignment Algorithm for Solving Resource Allocation Problems

The assignment problem is one of the fundamental problems in the field of combinatorial optimization. The Hungarian algorithm can be developed to solve various assignment problems according to each criterion. The assignment problem that is solved in this paper is a dynamic assignment to find the maximum weight on the resource allocation problems. The dynamic characteristic lies in the weight change that can occur after the optimal solution is obtained. The Hungarian algorithm can be used directly, but the initialization process must be done from the beginning every time a change occurs. The solution becomes ineffective because it takes up a lot of time and memory. This paper proposed a fast dynamic assignment algorithm based on the Hungarian algorithm. The proposed algorithm is able to obtain an optimal solution without performing the initialization process from the beginning. Based on the test results, the proposed algorithm has an average time of 0.146 s and an average memory of 4.62 M. While the Hungarian algorithm has an average time of 2.806 s and an average memory of 4.65 M. The fast dynamic assignment algorithm is influenced linearly by the number of change operations and quadratically by the number of vertices.

Discovering Computer Science Research Topic Trends using Latent Dirichlet Allocation

Before conducting a research project, researchers must find the trends and state of the art in their research field. However, that is not necessarily an easy job for researchers, partly due to the lack of specific tools to filter the required information by time range. This study aims to provide a solution to that problem by performing a topic modeling approach to the scraped data from Google Scholar between 2010 and 2019. We utilized Latent Dirichlet Allocation (LDA) combined with Term Frequency-Indexed Document Frequency (TF-IDF) to build topic models and employed the coherence score method to determine how many different topics there are for each year’s data. We also provided a visualization of the topic interpretation and word distribution for each topic as well as its relevance using word cloud and PyLDAvis. In the future, we expect to add more features to show the relevance and interconnections between each topic to make it even easier for researchers to use this tool in their research projects.

Comparison of C4.5 Algorithm and Support Vector Machine in Predicting the Student Graduation Timeliness

In higher educational institutions, graduation rates are one of the many aspects to assess the quality of the learning process. Al-Hidayah Islamic University in Bogor is one of the established private Islamic universities to create skilled human resources with moral values required by many companies nowadays. Having another institution in Bogor as a competitor with the same direction and objective is a challenge for Al-Hidayah Islamic University. Thus a solution is required to face the competition. One solution is to predict the student graduation timeliness of the students using data mining method with classification function. The implemented methodology in the data mining is Discovery Knowledge of Database (KDD), starting from selecting, preprocessing, transformation, data mining, and evaluation/ interpretation. There were two Algorithm models used in this paper, namely C4.5 and Support Vector Machine (SVM). The classification procedure consists of predictor variables and one of the target variables. Predictor variables are gender, Grade Point Average, marital status, and job status. Rapid Miner software was used to process the data. The final results of both Algorithms show an 81% precision rate and 80% accuracy level for the C4.5 Algorithm, while SVM has an 88% precision rate and 85% accuracy level.