Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Journal of Computing Innovations and Emerging Technologies
Friden Elefri Neno
University of Stella Maris Sumba
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Web-Based Decision Support System for Major Selection Using the SAW Method at Efata Ombarade Vocational School Ina Tena Bolo; Friden Elefri Neno; Emerensiana Dappa Ege
Journal of Computing Innovations and Emerging Technologies Vol. 1 No. 2 (2025): Volume 1 No 2
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v1i2.12

Abstract

Efata Ombarade Vocational High School is located in West Sumba Regency, East Wewewa District, East Nusa Tenggara Province. It is a vocational high school offering two majors: tourism and hospitality services business. Every new school year, this school routinely accepts new students, where each applicant chooses a major according to their preferences, which may not be in line with their abilities. To improve the quality of the school and its students, each new student admission involves a selection process based on criteria set by the school, such as National Examination Scores, Report Card Scores, written tests, interviews, and health checks. The current student registration and selection process has several weaknesses, including the time-consuming process of entering data into Microsoft Excel and the delay in obtaining results due to the lack of a specific application to support the calculations. In view of these issues, a system is needed to assist in the process of making faster, more accurate, and more objective decisions regarding student majors. One solution offered is the implementation of a Decision Support System (DSS) using the Simple Additive Weighting (SAW) method. This method works by assigning weights to each criterion used in the assessment, then calculating preference scores to determine the best alternative. The data used includes students' academic scores, particularly their National Examination results, as well as data on their interests. The use of the SAW method in the major selection decision support system is expected to reduce unfairness in assessment, as small differences in scores can be processed proportionally. With this system in place, schools can more easily determine the majors that suit students' abilities and interests. Additionally, this system can also speed up the major selection process, reduce the potential for manual errors, and provide more accurate and fair recommendations for each student.
Geographic Information System for Mapping Solar Power Plants in Lolo Wano Village Haryance Umbu Dasa; Friden Elefri Neno; Alexander Adis
Journal of Computing Innovations and Emerging Technologies Vol. 1 No. 2 (2025): Volume 1 No 2
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v1i2.13

Abstract

The use of renewable energy, particularly solar power plants (SPPs), is one of the strategic solutions to overcome limited access to electricity in rural areas. Lolo Wano Village, as one of the villages with high solar radiation intensity, has great potential for SPP development. However, the planning of SPP construction is often hampered by a lack of integrated spatial data related to residential locations, public facilities, and land availability. This study aims to design a Geographic Information System (GIS) capable of mapping the potential and determining strategic coordinates for SPP construction in Lolo Wano Village. The research method was conducted by collecting primary data in the form of GPS coordinates of residents' houses, schools, village offices, and vacant land with potential for use. Secondary data included administrative maps, topographic maps, and solar radiation data from BMKG and global sources. The data was processed using QGIS/ArcGIS software through the stages of map digitization, spatial overlay, and land suitability analysis based on criteria of solar radiation, accessibility, land area, and proximity to residential areas. The results of the study show that the use of GIS can produce digital maps of the distribution of existing solar power plant locations as well as recommendations for new locations suitable for development. This system not only assists village governments in making decisions on renewable energy development, but also supports equitable access to electricity for the community. Thus, the application of GIS in mapping solar power plants in Lolo Wano Village plays an important role in supporting sustainable development and improving the quality of life of the local community.
Sentiment Analysis of Customer Satisfaction with the Services of the Waikelo Port Class III Administrative Office Using the CAN Order Method Kamalia Ahmad; Friden Elefri Neno; Alexander Adis
Journal of Computing Innovations and Emerging Technologies Vol. 2 No. 1 (2026): Volume 2 No 1
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v2i1.14

Abstract

This study aims to analyze customer satisfaction levels with the services provided by the Waikelo Port Class III Administrative Office using the CAN (Cumulative Agreement Normalized) Order method and sentiment analysis. Data was collected from customer comments on service aspects such as speed of service, staff friendliness, facilities, and registration procedures. The comments were processed through text pre-processing, including case folding, tokenization, stopword removal, and stemming, then analyzed using the VADER Sentiment Analyzer to obtain positive, neutral, and negative scores. These sentiment values were used as input to calculate the CAN value, which determines the satisfaction ranking of each alternative objectively. The results show that service alternatives focusing on speed and staff friendliness have the highest CAN value of 0.83, while alternatives related to facilities and queues have the lowest CAN value of 0.33, indicating aspects that need improvement. Evaluation of the consistency of the CAN ranking with the respondent ranking using Spearman Rank Correlation yields a value of 0.92, indicating a high degree of conformity between the CAN method and customer preferences. This analysis proves that the integration of sentiment analysis and the CAN Order method can provide a quantitative picture of customer satisfaction levels and serve as a basis for practical recommendations to improve service quality.
Application of Convolutional Neural Network Student Reviews for Lecture Facilities at Stella Maris University Sumba Emilia Kuba; Friden Elefri Neno; Karolus Wulla Rato
Journal of Computing Innovations and Emerging Technologies Vol. 2 No. 1 (2026): Volume 2 No 1
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v2i1.21

Abstract

The development of artificial intelligence technology, particularly in the field of deep learning, has opened up new opportunities in text-based data analysis, including student reviews of lecture facilities. This study aims to apply the Convolutional Neural Network (CNN) method in conducting sentiment analysis of student reviews of lecture facilities at Stella Maris University Sumba. Through this approach, it is hoped that the system can automatically and accurately classify student opinions into positive, negative, or neutral categories. The research data was obtained from surveys and student comments on various internal campus platforms. The data processing involved data preprocessing stages such as text cleaning, tokenization, stopword removal, and word embedding using the Word2Vec method. The CNN model was then built with an architecture involving an embedding layer, convolutional layer, max pooling, and fully connected layer to produce the final prediction. The test results show that the CNN model is capable of achieving a high level of accuracy in identifying sentiment polarity, with an average accuracy value of 90.2%. This performance proves that CNN is effective in extracting semantic features from unstructured student review texts. Analysis of the classification results also provides important insights into aspects of campus facilities that received positive and negative responses, such as classroom quality, internet network, and learning environment comfort. These findings can be used as a basis for universities in making strategic policies for the continuous improvement of lecture facilities. Thus, the application of CNN in student review analysis has been proven to support the evaluation and decision-making processes in data-driven academic environments.
Co-Authors Alexander Adis Emerensiana Dappa Ege Emilia Kuba Haryance Umbu Dasa Ina Tena Bolo Kamalia Ahmad Karolus Wulla Rato