Journal of Information System Exploration and Research

Analyzing the Impact of Effort Expectancy and Cognitive Attitudes on The Willingness to Accept ChatGPT

Andri Saputra; Oktafiyani Aisah Noraini, Dwika Ananda Agustina Pertiwi — Mon, 11 Aug 2025 00:00:00 +0000

This study aims to analyze the impact of Effort Expectancy (EE) adapted from the Unified Theory of Acceptance and Use of Technology (UTAUT) and Cognitive Attitude (CA) from the Theory of Reasined Action (TRA) model on Willingness to Accept (WA) adapted from TAM on ChatGPT. By understanding the relationship between these factors, we can identify effective strategies to increase user acceptance of ChatGPT technology. The research method used is quantitative with multiple linear regression calculations in SPSS. This study obtained 50 respondents with a total of 10 variables but there were 3 main variables. With the final result, Effort Expectancy has no significant effect on Willingness to Accept while Cognitive Attitude has a significant effect on Willingness to Accept. This suggests that users’ perceptions of how easy or difficult it is to use ChatGPT do not influence their decision to accept and use the technology. In this context, users may feel that ease of use is not a major factor influencing their acceptance of ChatGPT. This means that users’ cognitive attitudes—including their beliefs, perceptions, and understanding of the technology—play an important role in their decision to accept and use ChatGPT.

Enhancing Abusive Language Detection on Twitter Using Stacking Ensemble Learning

Putri Utami, Yulizchia Malica Pinkan Tanga, Jumanto Unjung, Much Aziz Muslim — Tue, 19 Aug 2025 00:00:00 +0000

Detecting abusive language on Twitter is an important step in reducing the prevalence of negative content and harassment. This study aims to improve the accuracy and effectiveness of abusive language detection on Twitter by addressing the limitations of the single model commonly used previously. The stacking method is employed by combining Term Frequency-Inverse Document Frequency (TF-IDF) as the feature extraction method, along with the Naive Bayes and XGBoost algorithms as classification models. Naive Bayes is known for its simplicity in handling text classification, while XGBoost excels in processing complex data and achieving high accuracy. The combination of these two models is expected to improve performance in detecting coarse language. The research results show that the proposed model outperforms the methods in previous studies, with an accuracy of 91.91% and an AUC of 96.76%. These findings demonstrate the effectiveness of the stacking approach in reducing classification errors in coarse language detection. Further research could explore the use of larger datasets or more complex models to improve detection accuracy.

Identifying Coconut Maturity Levels Using CNN and YOLOv8 Deep Learning Algorithms

Alfaiz Alafi Luthfie, Alamsyah Alamsyah — Fri, 22 Aug 2025 00:00:00 +0000

To improve the efficiency and accuracy of determining coconut maturity levels in the processing industry, this study proposes an automated detection system employing Convolutional Neural Networks (CNN) and the You Only Look Once version 8 (YOLOv8) algorithm to classify maturity levels from image data. This study introduces an automated detection system using Convolutional Neural Networks (CNN) and the You Only Look Once version 8 (YOLOv8) algorithm to identify coconut maturity levels from image data. A dataset of 230 coconut images was utilized, classified into two categories: Young Coconut and Mature Coconut. The YOLOv8 model was trained and evaluated using standard object detection metrics, including mean Average Precision (mAP), precision, recall, and F1-score. The proposed model achieved a mAP of 90.5%, precision of 99.3%, recall of 94.2%, and F1-score of 96.6%, demonstrating high accuracy in detecting coconut maturity. This approach offers a practical and efficient alternative to manual assessment, contributing to improved accuracy and operational efficiency in agricultural practices.

Guava Disease Classification Using EfficientNet and Genetic Algorithm-Optimized XGBoost

Aditya Yoga Darmawan, Bagus Al Qohar, Ahmad Ubai Dullah — Fri, 26 Sep 2025 00:00:00 +0000

Guava is an evergreen plant in the Myrtaceae family, is renowned for its adaptability and noteworthy nutritional benefits. However, guava production has experienced a substantial decline in recent years due to various diseases affecting the fruit. Farmers typically employ manual inspection to identify these diseases, a method that is time-consuming, labor-intensive, and susceptible to errors. This underscores the necessity for an automated classification model capable of accurately diagnosing guava fruit diseases. While numerous machine learning and deep learning models have been developed for agricultural disease detection, research on combining deep transfer learning as a feature extractor with machine learning classifiers remains relatively limited. Addressing this research gap, the proposed model integrates the strengths of both approaches, achieving an impressive accuracy of 98.62%, surpassing the performance reported in previous studies. This encouraging outcome underscores the potential of hybrid models in enhancing guava fruit disease classification, paving the way for more efficient and scalable agricultural management solutions.