Jurnal Online Informatika
Not a member yet
276 research outputs found
Sort by
Delineation of The Early 2024 Election Map: Sentiment Analysis Approach to Twitter Data
Get PDFAs a democratic country, the people hold an important role in determining power in Indonesia. The closest political agenda in Indonesia is the 2024 Election. A survey has been conducted by several private survey agencies regarding the 2024 political map which has revealed the top five names, namely Prabowo Subianto, Ganjar Pranowo, Anies Baswedan, Sandiaga Uno, and Ridwan Kamil. This study aims to describe the initial map of the 2024 Election through a sentiment analysis approach to Twitter data. This study uses tweet data that mentions five political figures during 2021. In general, the demographic condition of Twitter users that pros or cons to five political figures, among them: located on the Java, in the age group 19–29 years old, and male. The sentiment analysis method used is supervised learning with different methods for each figure. The difference in methods adjusts the best evaluation value given in each figure. The results showed that the highest positive sentimental tweets and the highest number of pro accounts was about Ganjar Pranowo. On the other hand, the highest negative sentiment and the highest number of contra accounts was about Prabowo Subianto. Many words that often appear on a figure\u27s positive sentiment are expressions of hope, prayer, and support. On negative tweets, the word that comes up a lot relating to the work field or work region of the figures.Â
The Measurement and Evaluation of Information System Success Based on Organizational Hierarchical Culture
Get PDFIn this study, the adoption of the Delone & McLean information system success model and its adaptation using the organizational hierarchy culture theory is used to explore the state of information system success and examine the factors that suggest success. This research was conducted at universities in Banten Province, which currently rely on information systems in many ways, especially those related to university management. By measuring the evaluation of the success of information systems and the hierarchical culture in organizations using a model that the researcher built according to the integration of 2 models. The results the measurement of the success of information systems were obtained from distributing questionnaires, there were still 85 (63%) respondents, and 84 (61.3%) were satisfied with the performance of the information system success model. The least squares structural equation modeling analysis (PLS-SEM) was then applied due to the sample size. The previous stage consisted of evaluating the reflective measurement model in evaluating the reliability of internal consistency using Composite Reliability, Reliability indicators, Convergent Validity and Discriminant Validity, finally it was concluded that the success of information system by hierarchical culture integration model in the organization on could be passed on the more complex research terms, especially using samples, and different questionnaires
Sentiment Analysis from Indonesian Twitter Data Using Support Vector Machine And Query Expansion Ranking
Get PDFSentiment analysis is a computational study of a sentiment opinion and an overflow of feelings expressed in textual form. Twitter has become a popular social network among Indonesians. As a public figure running for president of Indonesia, public opinion is very important to see and consider the popularity of a presidential candidate. Media has become one of the important tools used to increase electability. However, it is not easy to analyze sentiments from tweets on Twitter apps, because it contains unstructured text, especially Indonesian text. The purpose of this research is to classify Indonesian twitter data into positive and negative sentiments polarity using Support Vector Machine and Query Expansion Ranking so that the information contained therein can be extracted and from the observed data can provide useful information for those in need. Several stages in the research include Crawling Data, Data Preprocessing, Term Frequency – Inverse Document Frequency (TF-IDF), Feature Selection Query Expansion Ranking, and data classification using the Support Vector Machine (SVM) method. To find out the performance of this classification process, it will be entered into a configuration matrix. By using a discussion matrix, the results show that calcification using the proposed reached accuracy and F-measure score in 77% and 68% respectively
AR Make-up Filter for Social Media using the HSV Color Extraction
Get PDFChoosing the appropriate cosmetics is an arduous task. Because cosmetics are tested directly on the skin to ensure each person’s preferences are met. The consumer repeatedly tries a sample and then discards it until he discovers one that meets his tastes. The cosmetics business and consumers are affected by this move. Companies can utilize Augmented Reality (AR) technology as an alternative to mass-producing cosmetic samples. The difficulty of deploying augmented reality is the difficulty of putting cosmetics into camera video streams. Each individual bears the burden of skin color and its effect on light. HSV Color Extraction was the method employed for this study. The application of augmented reality intends to enable consumers to test cosmetics with their chosen color and assist businesses in competing in the industry by promoting items and engaging customers. This work makes it easier to choose cosmetics using augmented reality and social media. AR simulates the usage of the desired color cosmetics, whereas social media allows users to obtain feedback on their color preferences. The outcomes of this study indicate that augmented reality (AR) apps can display filters in bright, dim, and even wholly dark lighting conditions. This research contributes originality that cosmetic firms can utilize to market their products on social media
Classification of the Fluency Multipurpose of Bank Mandiri Credit Payments Based on Debtor Preferences Using Naive Bayes and Neural Network Method
Get PDFOne that has an important role in generating bank profits is providing credit to customers, but credit also carries a very high risk. For this reason, in providing credit to debtors, of course the bank will utilize the personal data of prospective debtors in detail to avoid the risk of problems that will arise in the future. One of the appropriate risks for banks in providing credit is the behavior of customers who do not pay installments at the time which causes bad loans. To overcome and overcome the many bad events, there is an algorithmic calculation method with an intelligent computing system that helps banks in selecting prospective debtors who will be given credit. There are many algorithmic methods that can be used in this kind of research. This study analyzes the classification of staffing credit based on the criteria that become the Bank\u27s standard.The data used by the author in this study uses existing debtor credit data from 2017 to 2020, the modeling process is carried out using split validation with the Naive Bayes algorithm and Neural Network, with this algorithm the 1,314 datasets is divided into 2 parts, namely 80% used as training data and 20% used as testing data. The results showed that the Neural Network algorithm has better results with a correct value of 84.13%, while the Naive Bayes algorithm only produces a value of 72.62
Performance Analysis of ACO and FA Algorithms on Parameter Variation Scenarios in Determining Alternative Routes for Cars as a Solution to Traffic Jams
Get PDFThis study proposes several alternative optimal routes on traffic-prone routes using Ant Colony Optimization (ACO) and Firefly Algorithm (FA). Two methods are classified as the metaheuristic method, which means that they can solve problems with complex optimization and will get the solution with the best results. Comparison of alternative routes generated by the two algorithms is measured based on several parameters, namely alpha and beta in determination of the best alternative route. The results obtained are that the alternative route produced by FA is superior to ACO, with an accuracy of 88%. This is also supported by the performance of the FA algorithm which is generally superior, where the resulting alternative route is shorter in distance, time, running time and there is no influence on the alpha parameter value. But in each iteration, the number of alternative routes generated is less. The contribution of this research is to provide information about the best algorithm between ACO and FA in providing the most optimal alternative route based on the fastest travel time. The recommended alternative path is a path that is sufficient for cars to pass, because the selection takes into account the size of the road capacity
YouTube X-Rating Detection with Bahasa-Slang Title Using Query Expansion and Rule Based Approaches
Get PDFThe detection of X-rating content on the Internet is still rarely done in Indonesia and the performance of the existing work to detect X-rating content, especially in video is still low. The largest video portal, YouTube, does not yet have automatic X-rating content detection through its content either. Some X-rating content prevention service providers in Indonesia, such as the Internet Positive and Nawala Project, detect X-rating content using the keyword detection method of a web page and then block the web page with DNS filtering. However, that method does not pay attention to using Bahasa-Slang. This work developed Metasearch named Safedio. Safedio aims to detect X-rating content on YouTube content through video titles that contain Bahasa-Slang. Safedio utilizes Query Expansion and Rule-Based approaches. The Query Expansion is a technique to get additional rules in search. In the end, Safedio can detect X-rating content through video titles in both Bahasa and Bahasa-Slang. The average results return with precision 71%, recall 46% and accuracy 72%
Systematic Literature Review Of Particle Swarm Optimization Implementation For Time-Dependent Vehicle Routing Problem
Get PDFTime-dependent VRP (TDVRP) is one of the three VRP variants that have not been widely explored in research in the field of operational research, while Particle Swarm Optimization (PSO) is an optimization algorithm in the field of operational research that uses many variables in its application. There is much research conducted about TDVRP, but few of them discuss PSO\u27s implementation. This article presented as a literature review which aimed to find a research gap about implementation of PSO to resolve TDVRP cases. The research was conducted in five stages. The first stage, a review protocol defined in the form of research questions and methods to perform the review. The second stage is references searching. The third stage is screening the search result. The fourth stage is extracting data from references based on research questions. The fifth stage is reporting the study literature results. The results obtained from the screening process were 37 eligible reference articles, from 172 search results articles. The results of extraction and analysis of 37 reference articles show that research on TDVRP discusses the duration of travel time between 2 locations. The route optimization parameter is determined from the cost of the trip, including the total distance traveled, the total travel time, the number of routes, and the number used vehicles. The datasets that are used in research consist of 2 types, real-world datasets and simulation datasets. Solomon Benchmark is a simulation dataset that is widely used in the case of TDVRP. Research on PSO in the TDVRP case is dominated by the discussion of modifications to determine random values of PSO variables
Poincaré Plot Method for Physiological Analysis of the Gadget Use Effect on Children Stress Level
Get PDFStress in children can affect the way they think, act, and feel. The habit of using gadgets has several advantages and disadvantages, but there has been no in-depth study of the effect of using gadgets on stress levels in children. This study aims to determine the representation of the physiological condition of using gadgets on stress levels in children. A total of 18 electrocardiogram data were extracted with poincaré plot features. This research has found that there is no difference in the level of stress in children between before and after using gadgets in terms of autonomic nervous activity (Sig. > 0.05). However, there is an increase in sympathetic activity that occurs in children even though they have finished using gadgets. Such conditions certainly need to get more attention, especially related to the duration of gadget use and accessible content
Implementation of Apriori Algorithm for Music Genre Recommendation
Get PDFMusic interest is diverse yet enticing to be a part of knowledge discovery. It influences how people feel, study, work, etc. A lot of things are to be considered in producing brand new music with its correlation to its genre. We have already collected the dataset that we can utilize in this research, which is the history of every song listened to by several users in a total of 20.000 records from a million song dataset. This study implements the Apriori algorithm which can handle a large amount of data while simplifying the data to create a recommendation system where the result is a pattern from the music genre according to the interests of each user with the help of the RapidMiner tool. The purpose of this research is that the pattern which has been found can become a reference for music producers in terms of making or distributing their brand-new music. The result of the best combination of genres states that listeners of the rock genre will also hear the pop genre with a combination frequency of 50, support value of 21.2%, and confidence value of 51%