Article Per Year (5 Year)
p-Index From 2021 - 2026
0.888
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization International Journal of Advances in Artificial Intelligence and Machine Learning
Jaber, Mustafa Musa
Unknown Affiliation
Computer Science & IT

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

Found 4 Documents
Search

 1 
A Deep Learning Approach to Sentiment Analysis of Hotel Reviews: Comparing BERT and LSTM Models Wang, Gunawan; Jaber, Mustafa Musa
International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 2 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/ijaaiml.v2i2.403

Abstract

Background of study: Background of study: The impact of online reviews on consumer behavior is especially relevant in the hospitality industry, and the sentiment corresponding to these reviews is difficult to determine due to the subjectivity involved in the reviews, disparate writing styles, and the noticeable class imbalance resulting from the positive reviews outnumbering the negative and neutral ones. Standard machine learning approaches are biased toward the majority class and do not address these problems well.Aims and scope of paper: The present research uses BERT and LSTM deep learning models to perform classification of customer reviews for hotels into three categories: positive, neutral, and negative. The main focus of the research is to analyze the performance of the models concerning sentiment prediction and the handling of the data imbalance problem and to benchmark the models with and without the use of under-sampling.Methods: The dataset comprising of 20,000 reviews from the TripAdvisor platform was pre processed in various ways including the removal of stop words/special characters, tokenization, stemming, and lemmatization. The customer reviews were assigned star ratings, which were aggregated into categories of 4-5 stars as positive, 3 stars as neutral, and 1-2 stars as negative. Random under-sampling was used to the positive class to achieve balance in the dataset. The BERT (bert-base-uncased) and LSTM models were prepared with what was assumed to be a final train-validation split of 80:20, and were evaluated based on standard metrics of accuracy, precision, recall, and rel F1 score, and with a cross-validation of 5 folds.Result: Without the use of under-sampling, BERT achieved the best overall performance with an accuracy of 0.86 and an F1 score of 0.93 for the positive sentiment class and an F1 score of 0.79 in the negative sentiment class. However, all models struggled with neutral sentiments (BERT F1-score: 0.43, LSTM: 0.25). Under-sampling improved neutral class recall (BERT: 0.79) but decreased overall accuracy (BERT: 0.73; LSTM: 0.67) and positive class precision.Conclusion: BERT generally outperforms LSTM for hotel review sentiment analysis, particularly with imbalanced data. While under-sampling helps address class imbalance by improving neutral recall, it incurs significant performance trade-offs, reducing overall accuracy and precision in majority classes due to information loss. Future work should explore advanced resampling (SMOTE, ADASYN) or transfer learning (RoBERTa, XLNet) for better balance and neutral sentiment classification.
Software Agent Simulation Design on the Efficiency of Food Delivery Ismail, Shahrinaz; Mostafa, Salama A; Baharum, Zirawani; Erianda, Aldo; Jaber, Mustafa Musa; Jubair, Mohammed Ahmed; Adiya, M. Hasmil
JOIV : International Journal on Informatics Visualization Vol 8, No 1 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.1.2648

Abstract

Food delivery services have gained popularity since the emergence of online food delivery. Since the recent pandemic, the demand for service has increased tremendously. Due to several factors that affect how much time additional riders spend on the road; food delivery companies have no control over the location or timing of the delivery riders. There is a need to study and understand the food delivery riders' efficiency to estimate the service system's capacity. The study can ensure that the capacity is sufficient based on the number of orders, which usually depends on the number of potential customers within a territory and the time each rider takes to deliver the orders successfully. This study is an opportunity to focus on the efficiency of the riders since there is not much work at the operational level of the food delivery structure. This study takes up the opportunity to design a software agent simulation on the efficiency of riders' operations in food service due to the lack of simulation to predict this perspective, which could be extended to efficiency prediction. The results presented in this paper are based on the system design phase using the Tropos methodology. At movement in the simulation, the graph of the efficiency is calculated. Upon crossing the threshold, it is considered that the rider agents have achieved the efficiency rate required for decision-making. The simulation's primary operations depend on frontline remotely mobile workers like food delivery riders. It can benefit relevant organizations in decision-making during strategic capacity planning.
Deep Learning Approach for Prediction of Brain Tumor from Small Number of MRI Images Zailan, Zulaikha N.I.; Mostafa, Salama A.; Abdulmaged, Alyaa Idrees; Baharum, Zirawani; Jaber, Mustafa Musa; Hidayat, Rahmat
JOIV : International Journal on Informatics Visualization Vol 6, No 2-2 (2022): A New Frontier in Informatics
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.6.2-2.987

Abstract

Daily, the computer industry has been moving towards machine intelligence. Deep learning is a subfield of artificial intelligence (AI)'s machine learning (ML). It has AI features that mimic the functioning of the human brain in analyzing data and generating patterns for making decisions. Deep learning is gaining much attention nowadays because of its superior precision when trained with large data. This study uses the deep learning approach to predict brain tumors from medical images of magnetic resonance imaging (MRI). This study is conducted based on CRISP-DM methodology using three deep learning algorithms: VGG-16, Inception V3, MobileNet V2, and implemented by the Python platform. The algorithms predict a small number of MRI medical images since the dataset has only 98 image samples of benign and 155 image samples of malignant brain tumors. Subsequently, the main objective of this work is to identify the best deep learning algorithm that performs on small-sized datasets. The performance evaluation results are based on the confusion matrix criteria, accuracy, precision, and recall, among others. Generally, the classification results of the MobileNet-V2 tend to be higher than the other models since its recall value is 86.00%. For Inception-V3, it got the second highest accuracy, 84.00%, and the lowest accuracy is VGG-16 since it got 79.00%. Thus, in this work, we show that DL technology in the medical field can be more advanced and easier to predict brain tumors, even with a small dataset.
Vehicles Speed Estimation Model from Video Streams for Automatic Traffic Flow Analysis Systems Arriffin, Maizatul Najihah; Mostafa, Salama A.; Khattak, Umar Farooq; Jaber, Mustafa Musa; Baharum, Zirawani; Defni, -; Gusman, Taufik
JOIV : International Journal on Informatics Visualization Vol 7, No 2 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.2.1820

Abstract

Image and video processing have been widely used to provide traffic parameters, which will be used to improve certain areas of traffic operations. This research aims to develop a model for estimating vehicle speed from video streams to support traffic flow analysis (TFA) systems. Subsequently, this paper proposes a vehicle speed estimation model with three main stages of achieving speed estimation: (1) pre-processing, (2) segmentation, and (3) speed detection. The model uses a bilateral filter in the pre-processing strategy to provide free-shadow image quality and sharpen the image. Gaussian filter and active contour are used to detect and track objects of interest in the image. The Pinhole model is used to assess the real distance of the item within the image sequence for speed estimation. Kalman filter and optical flow are used to flatten vehicle speed and acceleration uncertainties. This model is evaluated with a dataset that consists of video recordings of moving vehicles at traffic light junctions on the urban roadway. The average percentage for speed estimation error is 20.86%. The average percentage for accuracy obtained is 79.14%, and the overall average precision of 0.08.
Co-Authors Abdulmaged, Alyaa Idrees Adiya, M. Hasmil Aldo Erianda, Aldo Arriffin, Maizatul Najihah Baharum, Zirawani Defni, - Gunawan Wang, Gunawan Gusman, Taufik Ismail, Shahrinaz Jubair, Mohammed Ahmed Khattak, Umar Farooq Mostafa, Salama A Mostafa, Salama A. Rahmat Hidayat Zailan, Zulaikha N.I.