Informasi Interaktif : Jurnal Informatika dan Teknologi Informasi

PREDIKSI REKOMENDASI WISATA DI INDONESIA MENGGUNAKAN METODE HYBRID CBF BERBASIS TF-IDF, COSINE SIMILARITY DAN NEURAL NETWORK

2026-01-26T05:16:34+00:00

This research aims to develop a predictive recommendation model for tourist destinations in Indonesia using a hybrid approach that integrates TF-IDF and Cosine Similarity-based content analysis with Neural Network modeling. The main problem addressed is the high complexity in determining relevant tourist destinations due to the numerous choices and diversity of characteristics among destinations. The dataset used consists of 935 tourist destination data points, including text and numeric attributes. The TF-IDF method is used to extract features from destination descriptions, followed by Cosine Similarity to calculate their compatibility with user preferences. Meanwhile, the Neural Network processes numeric features such as category, province, and description length to generate additional relevance prediction scores. These two scores are combined through a hybrid approach to achieve more accurate recommendation results. Evaluation results show that the hybrid model performs very well with Precision@250 of 0.90 and Recall@250 of 0.97, indicating that the model not only selects relevant destinations but also successfully captures nearly all destinations matching user preferences. Overall, this hybrid approach provides more comprehensive recommendations compared to single methods and has the potential to be implemented in a national-scale tourism recommendation system.

ANALISIS SENTIMEN KUALITAS BAHAN BAKAR PERTAMINA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE PADA PLATFORM X

2026-01-14T07:06:18+00:00

Fuel quality is an important factor that influences engine performance and customer satisfaction. As the main fuel provider in Indonesia, Pertamina must ensure that its products meet public expectations. This study aims to analyze public sentiment toward the quality of Pertamina’s fuel products based on data obtained from Platform X (Twitter), using the Support Vector Machine (SVM) algorithm as the primary classification method. Data were collected through a crawling process using the tweet-harvest library version 2.6.1 from April 1, 2025, to September 30, 2025, resulting in 1,596 comments. The data then underwent preprocessing, including cleaning, case folding, normalization, tokenizing, stopword removal, and stemming. Sentiment labeling was performed automatically using a lexicon-based approach with two categories—positive and negative—resulting in 799 positive and 795 negative data points. The classification process was carried out using SVM with an 80% training and 20% testing data split. Based on the evaluation results, the SVM model demonstrated effective and stable performance in classifying Indonesian-language text sentiment in the context of public opinion toward Pertamina’s fuel products.

SISTEM PENDUKUNG KEPUTUSAN UNTUK SELEKSI PENERIMAAN PEGAWAI BARU MENGGUNAKAN METODE KNN DAN WEIGHTED PRODUCT

2026-02-01T07:49:11+00:00

Searching for prospective employees is quite an important thing in the company because every job done by employees will affect the stability of the company. In the recruitment of employees, the quality of prospective applicants is already convincing, but the salary he submits is not in accordance with the ability of the company, or the prospective applicants do not match the criteria that the company is looking for. This mismatch will certainly slow down the company to find the best staff. The results of this study are to provide recommendations for the best employees who understand some of the criteria set by the system using the k-nearest neighbor (KNN) method and weighted product (WP). The parameters used to obtain wisdom are using GPA values, academic values, science and technology values and interview scores. The data that will appear at the conclusion is the ranking of the participants, the type of classification and recommendations chosen by the company. With these data, the company can determine the next policy that can be taken. The results of the accuracy obtained are 87% with a value of k = 3.

SISTEM CERDAS BERBASIS MACHINE LEARNING UNTUK DIAGNOSIS PENYAKIT PADA KUCING

2026-01-14T04:47:57+00:00

The challenge of diagnosing cat diseases quickly and accurately, caused by the tendency of cats to hide pain and often non-specific clinical symptoms, forms the primary background of this research. This study aims to design and build an intelligent system based on machine learning that can provide initial diagnostic recommendations for common cat diseases based on symptom data. The research method used adopts the Agile Scrum framework , with the K-Nearest Neighbor (KNN) algorithm as the classification core. System testing was conducted on 200 test data points covering five main diseases: Cat Flu, Worms, Fungal Infection, Rabies, and Diarrhea. The test results showed excellent performance with an average accuracy rate of 92.50%. Specifically, the system successfully classified 185 data points correctly and 15 incorrectly , with Rabies recording the highest accuracy (96.67%). Although there is still an error rate of 7.5% , this system is proven feasible for use as an initial diagnostic aid; however, its use must still be supported by direct confirmation from a professional veterinarian.

PREDIKSI TIMBULAN SAMPAH RUMAH TANGGA DI KOTA BEKASI MENGGUNAKAN RANDOM FOREST DALAM PERENCANAAN PRODUKSI KOMPOS

2026-01-15T23:57:40+00:00

The rapid population growth and urban activity have caused a continuous increase in household waste generation. Bekasi City is one of the major contributors, with a significant amount of organic household waste requiring a sustainable management strategy. This research proposes a Machine Learning approach based on the Random Forest algorithm to predict household waste generation for compost production planning. The dataset includes demographic variables and annual waste records from 2022 to 2024. The method consists of preprocessing, data splitting, and model evaluation stages. Results show that the model achieved an MAE of 1111.70, RMSE of 1549.57, and an R² value of 0.95, indicating strong predictive capability. The model was then used to calculate household waste prediction for 2025 to 2030, showing an increasing trend. Additionally, the projection enabled the estimation of compost production potential based on an assumption that 70% of total waste is organic and 50% of it can be processed into compost. This research confirms that Machine Learning and Artificial Intelligence approaches can support local waste management policy and long-term sustainability planning.

PERANCANGAN APLIKASI DAN IMPLEMENTASI SISTEM REPOSITORI DIGITAL UNTUK PENGELOLAAN KOLEKSI DOKUMEN DI SMK YUPPENTEK 1 TANGERANG

2026-01-14T05:43:43+00:00

At SMK YUPPENTEK 1 Tangerang, there are still many issues in managing documents such as student final assignments, scientific papers, and administrative documents. Conventional storage, either physically or scattered across various digital media, increases the risk of losing important data and causes difficulties in searching, monitoring, and sharing information. The SRD was developed using the PHP programming language, built with the Laravel framework and MySQL database, providing a robust and scalable platform. The results of the implementation and functional testing using Black-Box Testing show that the Digital Repository System (SRD) has successfully aided the document digitalization process, storage standardization, and ease of access through access control mechanisms and advanced search features at SMK YUPPENTEG 1 Tangerang, aiming to increase operational productivity and ensure consistent data availability. The main finding of the research is the increased security of digital assets and a reduction in search time of more than 70%. In conclusion, the implementation of the Digital Repository System at SMK YUPPENTEK 1 Tangerang has proven successful as a modern solution that can improve operational efficiency and ensure continuous information availability.

RANCANG BANGUN SISTEM INFORMASI PENDAFTARAN DAN ABSENSI ASLAB BERBASIS CONTAINER-AS-A-SERVICE (CAAS) (STUDI KASUS: FASTAPI DAN GOOGLE CLOUD RUN)

2026-01-14T05:53:24+00:00

Manual management of laboratory assistants (aslab) often leads to problems such as inefficiency in data management, information delays, and a lack of transparency in the selection process. On the other hand, the development of information systems in campus environments is often hampered by traditional server infrastructure (IaaS) which is complicated to maintain and inefficient in terms of operational costs, especially during low traffic. This study aims to design and build an Aslab Registration, Administration, and Attendance Information System by implementing a modern architecture in the form of Container-as-a-Service (CaaS). The system is built using the Python FastAPI framework, packaged with Docker container technology, and deployed on Google Cloud Run services integrated with Google Cloud SQL. The research method uses a Research and Development (R&D) model adapted from the Borg & Gall model. The results of Black-Box testing and User Acceptance Testing (UAT) indicate that the system runs well in a serverless cloud environment and meets user functional needs. The use of a CaaS architecture provides significant advantages in terms of automatic scalability (auto-scaling), cost efficiency through a pay-per-request model, and ease of deployment compared to conventional server infrastructure.

SISTEM REKOMENDASI DESTINASI WISATA BERBASIS CONTENT-BASED FILTERING DAN ANALISIS FITUR GEOSPASIAL

2026-01-15T23:46:50+00:00

This study develops a tourism destination recommendation system based on Content-Based Filtering integrated with geospatial feature analysis to enhance the relevance and contextual accuracy of recommendations for users. The system addresses the limitations of existing tourism recommendation platforms that primarily focus on popularity and ratings without considering users’ location proximity and personal preferences. The dataset used in this research originates from Tourism in Indonesia (Kaggle), focusing on the Jakarta and Bandung regions. Text features are extracted using the Term Frequency–Inverse Document Frequency (TF-IDF) method, while the similarity between destinations is measured using Cosine Similarity. Additionally, geographic distances are analyzed through the Haversine formula to strengthen the spatial context of the recommendations. The system was developed using the Agile (Scrum) methodology to ensure an iterative and adaptive development process aligned with user needs. Evaluation results indicate strong system performance, achieving a Precision of 0.63, Recall of 0.90, and an F1-Score of 0.73. These findings demonstrate that integrating content-based and spatial analysis approaches effectively improves the accuracy and personalization of tourism recommendations based on users’ preferences and location context.

ANALISIS PENGGUNAAN APLIKASI LINKEDIN DALAM MEMBANGUN PERSONAL BRANDING PADA MAHASISWA UNIVERSITAS NEGERI GORONTALO MENGGUNAKAN MODEL UTAUT

2026-01-15T23:53:13+00:00

Personal branding is an important element for students in shaping their professional image and preparing themselves for the world of work. As a professional social networking platform, LinkedIn offers various features that can support the formation of a professional identity, but its utilization by students is still not optimal. This study aims to examine the strength of the relationship between variables in the UTAUT model and the behavior of using LinkedIn as a means of personal branding among students at Gorontalo State University. Using a quantitative descriptive approach, data was collected through a questionnaire (gfrom) distributed to 80 students who actively use LinkedIn. The analysis was conducted using the PLS-SEM tool with the SmartPLS version 4 application. The results show that Social Influence and Performance Expectancy have an influence on Behavioral Intention with a t-statistic > 1.990 and a p-value < 0.05, while Effort Expectancy does not show a significant influence because the results do not meet the criteria. In addition, Facilitating Condition and Behavioral Intention also had an effect on Use Behavior. UTAUT in this study was able to explain 59.3% of the variance in Behavioral Intention and 58.4% of the variance in Use Behavior. These findings indicate that perceived benefits and environmental support have a stronger influence than ease of use in encouraging students to use LinkedIn.

SISTEM INFORMASI BERBASIS WEB UNTUK PEMBUATAN DAN PENGELOLAAN PORTOFOLIO PRIBADI

2026-02-01T07:16:47+00:00

The swift of information technology has motivated numerous people—especially professionals, students, and scholars—to build their digital self-image. A personal portfolio is an effective way to showcase their identity, skills, and work. However, physical portfolios have several limitations, such as being difficult to access, difficult to distribute, difficult to update, less visually appealing, and requiring dedicated storage space. As a solution, a web-based personal portfolio is here to display professional data and individual work in a more structured, interactive, and easily accessible way via the internet. The purpose of this research is to develop and create a personal portfolio website that is responsive, interactive, and easy to use. The development approach used in this study follows the waterfall model, encomassing the phases of requirements analysis, system design, implementation, and testing. The system was built utilizing PHP, HTML, CSS, and JavaScript programming languages, with a MySQL database as a storage medium. The findings of this research are a web-based personal portfolio creation information system that makes it easy for users to display personal data, educational history, work experience, projects, and skills in a professional and attractive manner. Furthermore, this system can reduce reliance on physical portfolios, which tend to be expensive and time-consuming to create. Data updates are also faster and more efficient. With this website, users are expected to build a professional image in the digital world and make it easier for others to recognize and assess their competencies more effectively.

ANALISIS RISIKO SISTEM MANAJEMEN RANTAI PASOK MAMMA ROTI BERDASARKAN ISO 31000

2026-01-15T23:55:46+00:00

The Food & Beverages (F&B) industry in Indonesia faces complex challenges in managing supply chain operational risks, particularly for rapidly growing franchise companies like Mamma Roti established since 2021. This research aims to identify and analyze operational risks using the ISO 31000:2018 framework as a structured risk management standard. Descriptive qualitative method was applied through direct observation and semi-structured interviews, with analysis following stages of context establishment, identification, likelihood-impact matrix analysis, acceptance criteria evaluation, and risk treatment procedures. Research results identified twelve operational risks (R1-R12) with most at moderate levels, while two risks (R5 and R11) obtained critical scores of 9 related to continuous improvement mechanisms. Recommendations include implementing measurable action trackers, Service Level Agreements (SLA), concise Standard Operating Procedures (SOP), and Business Continuity Plan (BCP) and Disaster Recovery Plan (DRP) with Recovery Time Objective (RTO) of 2-24 hours. Mitigation strategies are expected to reduce risks within 1-3 months and enhance Mamma Roti's operational resilience.