Article Per Year (5 Year)
p-Index From 2021 - 2026
0.835
P-Index
This Author published in this journals
All Journal Ambidextrous : Journal of Innovation, Efficiency and Technology in Organization
Yanuarini Nur Sukmaningtyas
Prodi Informatika, Universitas Islam Majapahit
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Comparison of IndoBERT and Naive Bayes Performance on Sentiment Analysis of Indonesian-Language E-Commerce Reviews Tony Kurniawan; Soffa Zahara; Yanuarini Nur Sukmaningtyas
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 5 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v5i02.648

Abstract

The growth of e-commerce platforms in Indonesia has generated a large number of user reviews containing important information about service quality and user satisfaction. Manual analysis of these reviews is inefficient, necessitating a Natural Language Processing (NLP)-based approach. This study aims to compare the performance of Naive Bayes and IndoBERT in sentiment classification of Indonesian-language e-commerce reviews. The dataset consists of 26,103 reviews of Tokopedia, Shopee, and Lazada apps obtained from the Google Play Store. The research stages include sentiment labeling based on ratings, preprocessing, Term Frequency–Inverse Document Frequency (TF-IDF) weighting on Naive Bayes, fine-tuning IndoBERT, and evaluation using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results show that Naive Bayes achieved an accuracy of 80.53%, while IndoBERT achieved 86.48% with a Macro F1-Score of 0.6515 and a Weighted F1-Score of 0.8723. These results show that IndoBERT is more effective in understanding the context of Indonesian text, resulting in better sentiment classification performance.
IoT Based Flood Warning Monitoring System with Using the Telegram Application Muhammad Mirza Safaraz; Soffa Zahara; Yanuarini Nur Sukmaningtyas
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 5 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v5i02.658

Abstract

Floods often occur suddenly and cause losses due to the limited availability of real-time early warning systems that are easily accessible to the public. This study aims to develop an Internet of Things (IoT)-based flood warning monitoring system with notifications using the Telegram application. The system was developed using the Research and Development (R&D) method with a prototyping approach consisting of a sensor module, a data processing module, and a notification module. The implementation was carried out using an ESP32 microcontroller integrated with an ultrasonic sensor to detect water levels and a rain sensor, and utilized the Telegram Bot API for automatic warning delivery. Evaluation of 20 respondents in flood-prone areas was carried out based on notification response speed, reading accuracy, ease of use, and user satisfaction. The results showed that the system was able to send warning notifications with an average time of 1.82 seconds from the detected condition and a sensor reading accuracy level of 98.50%. In addition, the system obtained an ease of use score of 3.42 and a user satisfaction score of 3.35 on a 4-point Likert scale. These results indicate that the IoT-based monitoring approach with Telegram integration is effective in helping the public obtain flood warning information more quickly and easily
Implementation of Internet of Things (IoT) Technology in Monitoring Food Quality and Temperature in Nutrition Fulfillment Service Units (SPPG) Achmad Fadlil Athoriq; Soffa Zahara; Yanuarini Nur Sukmaningtyas
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 5 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v5i02.660

Abstract

Food quality and safety declines often occur undetected and pose a risk to patients due to the limited availability of real-time food temperature and quality monitoring systems that are easily accessible to staff. This study aims to develop an Internet of Things (IoT)-based food quality and temperature monitoring system with notifications using the Telegram application at the Nutrition Fulfillment Service Unit (SPPG). The system was developed using the Research and Development (R&D) method with a prototyping approach consisting of a sensor module, a data processing module, and a notification module. Implementation was carried out using an ESP32 microcontroller integrated with a DS18B20 temperature sensor to detect food temperature and an MQ-135 gas sensor to detect food quality (freshness), and utilizing the Telegram Bot API for automatic alert delivery. Evaluation of 20 nutrition officer respondents at SPPG was carried out based on notification response speed, reading accuracy, ease of use, and user satisfaction. The results showed that the system was able to send warning notifications with an average time of 1.82 seconds from the detected condition and a sensor reading accuracy rate of 98.50%. Additionally, the system received a user-friendliness score of 3.42 and a user satisfaction score of 3.35 on a 4-point Likert scale. These results demonstrate that the IoT-based monitoring approach with Telegram integration effectively helps SPPG officers obtain food quality and temperature monitoring information more quickly and easily.
Smart Drip Irrigation Monitoring and Control System for Melon Cultivation Based on ESP32 and Using Blynk Application Muhammad Dzikri Idham Surya; Soffa Zahara; Yanuarini Nur Sukmaningtyas
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 5 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v5i02.661

Abstract

Melon cultivation often faces obstacles in maintaining optimal soil moisture and efficient water use due to conventional irrigation methods which tend to be manual, imprecise, and time-consuming. This research aims to develop an intelligent drip irrigation monitoring and control system to automate watering and optimize soil moisture in melon cultivation. The system was developed using the Research and Development (R&D) method with an Internet of Things (IoT) approach consisting of a soil moisture sensor as input, an ESP32 microcontroller as the control center, and a water pump as an actuator. Implementation was carried out by integrating a capacitive sensor to read soil conditions in real-time, which was then processed by the ESP32 to automatically activate the water pump through a relay module based on a specified threshold, and utilizing the Blynk application as a remote monitoring and control interface. System evaluation was carried out based on sensor reading accuracy, control response speed, and water use efficiency. The results showed that the system was able to maintain soil moisture in the optimal range of 60-80% for melon plants with a sensor reading accuracy reaching 97.5%. Furthermore, the system successfully increased water efficiency by 45% compared to manual watering methods, and achieved an average response time of 2.5 seconds for sending data to the Blynk application. These results demonstrate that the ESP32- and Blynk-based IoT approach effectively helps farmers optimize melon cultivation with greater efficiency, precision, and remote monitoring.
Design and Construction of a Rice Drying System Using Microcontroller-Based Canopy Control Muhammad Dwi Indra Saputra; Soffa Zahara; Yanuarini Nur Sukmaningtyas
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 5 No. 03 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v5i03.673

Abstract

The rice drying process is an important post-harvest stage to produce good quality grain, but conventional methods that rely on sun drying and manual canopy operation are still vulnerable to unpredictable weather changes, so the grain is at risk of being exposed to rain and decreasing its quality. This study aims to design and build a rice drying system with automatic canopy control based on a microcontroller that can work without continuous manual supervision and can be monitored remotely. The method used is Research and Development (R&D) with the stages of needs identification, design, implementation, testing, and evaluation. The system is built using an ESP32 microcontroller as the main control unit integrated with a DHT22 sensor, Light Dependent Resistor (LDR), and an FC-37 rain sensor to detect temperature, air humidity, light intensity, and rain; a servo motor as a canopy driver; a DC blower to help air circulation; an I2C LCD as a local monitoring medium; and a Telegram Bot as a real-time remote monitoring medium. The test results showed that the DHT22 sensor had a temperature reading error of 0.98%–1.38% and humidity of 1.33%–1.54% compared to the benchmark, while the LDR sensor and FC-37 rain sensor were able to control the canopy position and blower status precisely in all test scenarios. The system successfully opened and closed the canopy automatically according to environmental conditions, kept the blower active at night as long as the grain was not dry, stopped its operation when rain was detected or the grain was dry, and sent the system status to Telegram in real-time. These results indicate that the integration of environmental sensors, actuators, and IoT connectivity based on Telegram Bot can be an effective alternative solution to reduce reliance on manual supervision and the risk of grain damage due to unpredictable weather.
Co-Authors Achmad Fadlil Athoriq Muhammad Dwi Indra Saputra Muhammad Dzikri Idham Surya Muhammad Mirza Safaraz Soffa Zahara Tony Kurniawan