Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi

Sentiment Analysis on TikTok Shop Reviews Using Long Short-Term Memory Method to Find Business Opportunity

2023-12-22T17:37:21+07:00

During the world-changing year of covid 19, social media commerce grew fast. The prolonged use of social media encourages users to make online purchases via social media. TikTok, the most downloaded social media app, offers its users a social media commerce experience, TikTok Shop. The TikTok shop provided a new option for business expansion. Business owners may optimize the potential use of TikTok shops by learning more about TikTok Shop. The purpose of this study is to use sentiment analysis to evaluate the business potential of TikTok Shop. The data from Google Play reviews is analysed using the LSTM algorithm. Based on the results of research conducted using a confusion matrix, the LSTM algorithm method using word2vec has an accuracy of 74%. This study found that the business prospects of TikTok shops may be challenging.

ICONIX Process for Analysis and Design of Web-Based Savings and Loan Cooperative Applications

2023-12-22T17:36:10+07:00

The rapid advancement of information technology has led to the computerization of activities in virtually all domains. One notable example is the website, which is widely utilized by the public today to facilitate various business processes. Technology's proliferation has also significantly simplified and enhanced solutions to economic challenges, especially in cooperatives. Cooperatives play an instrumental role in fostering economic growth. While cooperative management utilizes applications, many administrative activities remain manual, lack real-time processing, and are only accessible to the cooperative's administrators. The process is challenging for cooperative members who wish to view transaction reports or conduct activities like installments, deposits, Surplus Dividends (SHU), or loans; they must physically visit the cooperative. This paper will delve into the steps in analyzing and designing a web-based cooperative application utilizing the Iconix process. The system analysis stages encompass data gathering via observation, interviews, and questionnaires. The system design stages cover the design of the user interface (GUI) graphics, use case diagrams, domain model diagrams, robustness diagrams, sequence diagrams, and class diagrams. This study's findings will benefit cooperative stakeholders looking to establish a web-based savings and loan system. This will provide them with a comprehensive overview of business processes through the analysis and design phases, all leveraging the Iconix process.

Sentiment Analysis on the Shopee Application on Playstore Using the Random Forest Classification Method

2023-11-29T09:34:42+07:00

In analyzing customer or consumer satisfaction with company services, it is essential for companies to find service deficiencies and to know user expectations for the company. This study aims to build sentiment analysis on the Shoppe application on the Google Playstore. The method used includes TF-IDF as text vectorization, Random Forest as a classification model, and Evaluation Matrix as an evaluation model, providing accuracy, precision, recall, and F1-Score. Based on the results of this study, the model we used achieved an accuracy rate of 94%, a precision of 91%, a recall of 91%, and an F1-Score of 93%. The limitations of this study are identifying words in English and regional languages because the corpus module we use is literature, a special Indonesian corpus. In future research, we will try to build a new engine/algorithm and try to add datasets in the hope that the level of accuracy will be even better.

Comparison of the Effect of Word Normalization on Naïve Bayes Classifier and K-Nearest Neighbor Methods for Sentiment Analysis

2023-12-03T21:02:17+07:00

In the pre-processing stage of sentiment analysis, there are several essential steps, one of which is word normalization, which is converting non-standard words into standard words. However, some research on sentiment analysis generally does not go through the word normalization stage, which can affect accuracy. This study aims to compare the effect of word normalization on the Naive Bayes Classifier and K-Nearest Neighbor methods for sentiment analysis of public opinion on the Agency Social Security Administrator for Health (BPJS Kesehatan). Gathering the data, labeling it, pre-processing it with two different scenarios, word weighting it with TF-IDF, classifying it using Naive Bayes Classifier and K-Nearest Neighbor, and lastly computing the accuracy of the Confusion Matrix are the steps that are involved. As a result of these discovered fact, the most superior accuracy results are obtained by the Naive Bayes Classifier method 1^st scenario, namely by using word normalization at the pre-processing stage and getting an accuracy of 87.14%. This research shows that the Naive Bayes Classifier method with word normalization produces better accuracy, precision, recall, and F1-score.

Developing a Business Intelligence Dashboard of Liquid Material at a Toy Manufacturing Company using a System Development Life Cycle (SDLC) Model

2023-12-22T17:44:00+07:00

Fashion doll manufacturers place a substantial emphasis on maintaining aesthetic appeal. One of the most important aspects of preserving a fashion doll's attractive appearance is using liquids to keep the hair in place despite countless shocks and bumps during the distribution process. According to a recent observation on liquid material control at one of the largest toy manufacturing companies worldwide, the process and database had shortcomings that might be fixed by developing a business intelligence dashboard using the SDLC methodology. The SDLC approach was adopted as the improvement methodology. According to the initial observation, improvement can be made by designing a system architecture that includes input data until data visualization. The form was created in Microsoft Forms and integrated into Microsoft Excel, Microsoft Power Automate, and Microsoft Power BI. After being implemented, this enhancement successfully reduced deficiencies and waste. According to the testing findings, all the capabilities perform as the users and stakeholders desired, satisfying all user requirements. Consequently, the organization applies business intelligence to the other departmental areas to visualize the data.

Natural Disaster Logistic Assistance Using A Star Method

2023-12-29T01:51:52+07:00

Natural disasters in Indonesia have tremendously impacted the victims. This is because there has not been a solution/method that can be used immediately when a natural disaster occurs, so losses caused by natural disasters continue to increase and are difficult to recover. The research used a case study of the Cianjur area. The research provides immediate assistance when natural disasters occur, as a liaison between donors and disaster victims, and is easy to use anytime and anywhere—assisting using the A Star method, which is used in navigation systems to obtain the fastest and closest distance by calculating two points using Longitude and Latitude. The result is an app for mobile devices used by donors, couriers, and victims of natural disasters, where donors can give their donated items faster. Apps can help the community at large. Many people can use the application to share information at the disaster site. The application is also easy to use anytime and anywhere, obtained from a weight of 4.00 by the users

Information Security System Design Using XDR And EDR

2024-01-15T21:03:33+07:00

The development of technology has provided many benefits in providing services to the community and helping to manage government efficiently. However, increasing reliance on technology also indirectly increases the risk of cyberattacks. Every company has the threat of cyber attacks from hackers who try to access and possess important and confidential assets both from inside and outside the company. To protect these assets, a cybersecurity system is needed that is able to protect against various threats of attack from irresponsible parties. A layered cybersecurity system is needed to be able to detect and respond to cyber attacks that occur automatically. XDR is a tool to detect and respond to cyber attacks based on the results of data analysis throughout the infrastructure with the aim of improving the efficiency of security operations. In addition, a system is also needed that is able to detect, alert, investigate, isolate and remove malicious software at endpoints in real-time, this system is called EDR. The test results after the implementation of the security system are systems that can monitor cyber attacks that appear in real-time, provide an automatic response so that information security on servers and endpoint devices can be protected.

Sentiment Analysis on the Impact of MBKM on Student Organizations Using Supervised Learning with Smote to Handle Data Imbalance

2024-01-15T12:58:55+07:00

Recently, there has been a decline in student interest in joining organizations. One of the causes is the MBKM program "Merdeka Belajar Kampus Merdeka". With this program from the government, more and more students are interested in entering because it is considered more profitable. Responses regarding this were conveyed by students through questionnaires, Twitter crawling, and YouTube comments. The data obtained was 1,770 (negative, positive, and neutral labeling) using Sastrawi, Nazief & Adriani, and Arifin Setiono stemming. There is an imbalance of data in labeling, so it is necessary to do SMOTE to balance the data. The algorithms used in the research focus on modeling the Naïve Bayes Classifier, Support Vector Machine, and Decision Tree with the split random method, with the best results using Support Vector Machine. Of the three algorithms, the highest results were obtained from the results of Arifin Setiono's data setmming, using a Support Vector Machine with 91% accuracy, obtained from 90% training data and 10% testing.

Classification of Depression Expressions on Twitter Using Ensemble Learning with Word2Vec

2024-01-28T20:30:36+07:00

One of the mental health disorders experienced by people is depression. Depression is a mental disorder characterized by feelings of sadness, loss of interest or pleasure in daily activities, and decreased cognitive function that can affect social life, work, and general physical health. Early detection is needed to prevent the occurrence of bad risks. One of the early detections can be done through social media. This is because social media is one of the tools used to channel expression. This research uses data taken from Twitter social media to create a machine learning model. Before model building, data pre-processing will be carried out using Word2Vec to convert text into a continuous vector representation. The algorithm used is ensemble learning by combining five algorithms: Logistic Regression, Decision Tree, K-Nearest Neighbor, Artificial Neural Network, and Support Vector Machine. The results show that different Word2Vec architectures can give the model another performance. Ensemble Learning can improve the performance of using a single model. The best results were obtained by using a data ratio of 90:10 using the Skip-gram architecture to get an accuracy value and f1-score of 94%.

Analytical Comparison of Lung Cancer Classification Using K-Nearest Neighbor and Naïve Bayes Algorithms

2024-02-08T11:34:18+07:00

Lung cancer stands as a significant global contributor to human mortality, constituting 25% of all cancer-related deaths in 2021. Its elusive nature, often devoid of early symptoms in a quarter of diagnosed cases, poses a challenge for timely detection. Unlike some other cancers, lung cancer remains hidden from the naked eye, with its symptoms often masquerading as those of other ailments like bronchitis, asthma, or persistent coughs. Early diagnosis is pivotal for effective treatment and increased survival rates. In light of the pressing nature of the situation, this study investigates the prediction of lung cancer by using data mining tools. It is essential to conduct data mining, which is a process that involves searching for patterns and trends inside vast data repositories to discover valuable insights. Within this context, classification emerges as a fundamental aspect that discerns objects based on their distinctive characteristics. A comparative study is undertaken to address the complexities associated with lung cancer classification, focusing on the K-Nearest Neighbor (KNN) and Naïve Bayes Classifier (NBC) algorithms. Through the utilization of a dataset that contains one thousand instances and twenty-four criteria, the purpose of this study is to determine which algorithm is preferable in the categorization of lung cancer. Upon analysis, the study yields noteworthy results. The KNN algorithm exhibits an accuracy rate of 98.34%, surpassing the NBC algorithm's accuracy of 89.37%. Consequently, this research concludes that, in lung cancer classification, the KNN algorithm outperforms the Naïve Bayes algorithm. These findings promise to enhance the efficacy of early lung cancer detection, potentially saving numerous lives through improved classification methods.

Forensic Analysis of Podman Container Towards Metasploit Backdoor Using Checkpointctl

2024-02-09T11:07:26+07:00

Container systems are a virtualization technology with an isolated environment. The isolated environment in a container system does not make cyber attacks impossible. In this research, containers where a cyber incident occurred, were forensically tested on the container's memory to obtain digital evidence. The forensic process uses standards from the NIST framework with collection, examination, analysis, and reporting stages. The forensic process begins by checking the container to obtain information from the container's memory. When the checkpoint procedure is executed in Podman, it is performed on one of the containers. This process produces a file in the.tar.gz format containing the container's information. After completing the checkpoint process, forensics is done by reading the checkpoint file using a checkpointctl tool. Forensic results showed that the container ran a malicious program as a backdoor with a PHP extension.

Implementation Of Fuzzy Logic to Identify Accident Categories In SMS-Based Two-Wheeled Vehicles

2024-02-09T11:20:40+07:00

Two-wheeled vehicle is the most popular means of transportation in Indonesia. As a result, it would cause several issues. One of them is an increased possibility of an accident to happen. In the event of an accident, quick aid from the public to the victim can reduce the risk of severe injury suffered by him. The person who provides aid to the injured victim may ask for money from the victim's family whose amount is not proportionate with the severity of the accident. In light of this, a system has been devised to identify and categorize the different types of accidents and send the formation to a family phone number registered electronically. The accident level is categorized using the Sugeno-type fuzzy logic method. The parameters used to differentiate the accident categories are speed, slope, and duration of vehicle braking time. The information is then sent to the registered phone via SMS that contains the accident category and the coordinates of the accident location provided by the GPS Neo 6 module. The algorithm is based on the vehicle's tilt angles, which range from 45(to the right) and -45(to the left). The fuzzy logic then determines the category, which processes and produces the accident category based on the speed and vehicle braking duration parameters. The proposed algorithm in this research will be experimented with using a real motorbike. Based on the experimental results, it has been found that the performance of the fuzzy logic method has an accuracy of 88.89% when determining the category of accident (light or heavy) and the time taken to send the information to the family member via SMS is quite fast.

Depression Detection of Users in Social-Media Twitter Using Decision Tree with Word2Vec

2024-02-14T21:29:54+07:00

Social media is a medium or place on the Internet that allows users to be themselves. Interact, cooperate, share, and communicate with other users virtually. Not only do users share happy feelings, but they also share their emotions and sentiments towards a particular issue. Which sometimes makes users look depressed when they deliver it. Depression itself is the most commonly encountered mental illness, which makes the sufferer feel sad, lonely, inferior, and disconnected from the people around them. And even worse, depression can make the sufferer have suicidal thoughts. Therefore, we need to know whether the user indicated being depressed or not to prevent unwanted things by using a depression measurement tool scale called DASS 42 for data labeling. To detect depression, we can use the sufferer's Twitter account to take data based on tweets from the user and change the entire dataset to a vector using both the architectures of Word 2, Vec Skip-Gram, and CBOW. In this research, we utilize a decision tree to detect depression. The best results were obtained from the Word2Vec Skip-Gram model with a data ratio of 90:10 using the Gini criterion parameter and a maximum depth value of 20, resulting in an accuracy of 93% and a f1-score of 94%.