Aseel Alhadlaq
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Aseel Alhadlaq has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Abeer Ali Alnuaim
Department of Computer Science and Engineering College of Applied Studies King Saud University 11451 Riyadh Saudi Arabia
3 shared publications Alaa Altheneyan
2 shared publications- Alaa Altheneyan
Department of Computer Science and Engineering, College of Applied Studies and Community Services, King Saud University, Riyadh, Saudi Arabia
2 shared publications - Ahmed Kharrufa
Newcastle University, Newcastle upon Tyne, United Kingdom
1 shared publication - Ajay Agarwal
KIET Group of Institutions
1 shared publication - Akshat Srivastava
School of Computer Science Engineering and Technology, Bennett University, Plot Nos 8-11, TechZone 2, Greater Noida 201310, India
1 shared publication
Latest Publications
- Open Access
- 16 September 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3180
Feature selection for emotion recognition in speech: a comparative study of filter and wrapper methods
Feature selection is essential for enhancing the performance and reducing the complexity of speech emotion recognition models. This article evaluates various feature selection methods, including correlation-based (CB), mutual information (MI), and recursive feature elimination (RFE), against baseline approaches using three different feature sets: (1) all available features (Mel-frequency cepstral coefficients (MFCC), root mean square energy (RMS), zero crossing rate (ZCR), chromagram, spectral centroid frequency (SCF), Tonnetz, Mel spectrogram, and spectral bandwidth), totaling 170 features; (2) a five-feature subset (MFCC, RMS, ZCR, Chromagram, and Mel spectrogram), totaling 163 features; and (3) a six-feature subset (MFCC, RMS, ZCR, SCF, Tonnetz, and Mel spectrogram), totaling 157 features. Methods are compared based on precision, recall, F1-score, accuracy, and the number of features selected. Results show that using all features yields an accuracy of 61.42%, but often includes irrelevant data. MI with 120 features achieves the highest performance, with precision, recall, F1-score, and accuracy at 65%, 65%, 65%, and 64.71%, respectively. CB methods with moderate thresholds also perform well, balancing simplicity and accuracy. RFE methods improve consistently with more features, stabilizing around 120 features.
- 16 September 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3180
Open AccessFeature selection for emotion recognition in speech: a comparative study of filter and wrapper methods
Feature selection is essential for enhancing the performance and reducing the complexity of speech emotion recognition models. This article evaluates various feature selection methods, including correlation-based (CB), mutual information (MI), and recursive feature elimination (RFE), against baseline approaches using three different feature sets: (1) all available features (Mel-frequency cepstral coefficients (MFCC), root mean square energy (RMS), zero crossing rate (ZCR), chromagram, spectral centroid frequency (SCF), Tonnetz, Mel spectrogram, and spectral bandwidth), totaling 170 features; (2) a five-feature subset (MFCC, RMS, ZCR, Chromagram, and Mel spectrogram), totaling 163 features; and (3) a six-feature subset (MFCC, RMS, ZCR, SCF, Tonnetz, and Mel spectrogram), totaling 157 features. Methods are compared based on precision, recall, F1-score, accuracy, and the number of features selected. Results show that using all features yields an accuracy of 61.42%, but often includes irrelevant data. MI with 120 features achieves the highest performance, with precision, recall, F1-score, and accuracy at 65%, 65%, 65%, and 64.71%, respectively. CB methods with moderate thresholds also perform well, balancing simplicity and accuracy. RFE methods improve consistently with more features, stabilizing around 120 features.
- Open Access
- 16 August 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2267
Distilroberta2gnn: a new hybrid deep learning approach for aspect-based sentiment analysis
In the field of natural language processing (NLP), aspect-based sentiment analysis (ABSA) is crucial for extracting insights from complex human sentiments towards specific text aspects. Despite significant progress, the field still faces challenges such as accurately interpreting subtle language nuances and the scarcity of high-quality, domain-specific annotated datasets. This study introduces the Distil- RoBERTa2GNN model, an innovative hybrid approach that combines the DistilRoBERTa pre-trained model’s feature extraction capabilities with the dynamic sentiment classification abilities of graph neural networks (GNN). Our comprehensive, four-phase data preprocessing strategy is designed to enrich model training with domain-specific, high-quality data. In this study, we analyze four publicly available benchmark datasets: Rest14, Rest15, Rest16-EN, and Rest16-ESP, to rigorously evaluate the effectiveness of our novel DistilRoBERTa2GNN model in ABSA. For the Rest14 dataset, our model achieved an F1 score of 77.98%, precision of 78.12%, and recall of 79.41%. The Rest15 dataset shows that our model achieves an F1 score of 76.86%, precision of 80.70%, and recall of 79.37%. For the Rest16-EN dataset, our model reached an F1 score of 84.96%, precision of 82.77%, and recall of 87.28%. For Rest16-ESP (Spanish dataset), our model achieved an F1 score of 74.87%, with a precision of 73.11% and a recall of 76.80%. These metrics highlight our model’s competitive edge over different baseline models used in ABSA studies. This study addresses critical ABSA challenges and sets a new benchmark for sentiment analysis research, guiding future efforts toward enhancing model adaptability and performance across diverse datasets.
- 16 August 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2267
Open AccessDistilroberta2gnn: a new hybrid deep learning approach for aspect-based sentiment analysis
In the field of natural language processing (NLP), aspect-based sentiment analysis (ABSA) is crucial for extracting insights from complex human sentiments towards specific text aspects. Despite significant progress, the field still faces challenges such as accurately interpreting subtle language nuances and the scarcity of high-quality, domain-specific annotated datasets. This study introduces the Distil- RoBERTa2GNN model, an innovative hybrid approach that combines the DistilRoBERTa pre-trained model’s feature extraction capabilities with the dynamic sentiment classification abilities of graph neural networks (GNN). Our comprehensive, four-phase data preprocessing strategy is designed to enrich model training with domain-specific, high-quality data. In this study, we analyze four publicly available benchmark datasets: Rest14, Rest15, Rest16-EN, and Rest16-ESP, to rigorously evaluate the effectiveness of our novel DistilRoBERTa2GNN model in ABSA. For the Rest14 dataset, our model achieved an F1 score of 77.98%, precision of 78.12%, and recall of 79.41%. The Rest15 dataset shows that our model achieves an F1 score of 76.86%, precision of 80.70%, and recall of 79.37%. For the Rest16-EN dataset, our model reached an F1 score of 84.96%, precision of 82.77%, and recall of 87.28%. For Rest16-ESP (Spanish dataset), our model achieved an F1 score of 74.87%, with a precision of 73.11% and a recall of 76.80%. These metrics highlight our model’s competitive edge over different baseline models used in ABSA studies. This study addresses critical ABSA challenges and sets a new benchmark for sentiment analysis research, guiding future efforts toward enhancing model adaptability and performance across diverse datasets.
- 23 November 2023
- Published by Taylor & Francis in Behaviour & Information Technology
- Vol. 43 (11) , 2639-2666
Qudwa: STEM e-mentoring for young women in Saudi Arabia
- 23 November 2023
- Published by Taylor & Francis in Behaviour & Information Technology
- Vol. 43 (11) , 2639-2666
Qudwa: STEM e-mentoring for young women in Saudi Arabia
- Top Cited PapersOpen Access
- 31 May 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (11) , 6729
A Twitter-Based Comparative Analysis of Emotions and Sentiments of Arab and Hispanic Football Fans
Twitter is one of the best online platforms for social interaction, introducing unique means of story-telling through tweets and enabling multiple approaches to the analysis of their content. This study was motivated by the increasing practice of incorporating Twitter into cultural studies and the research gap in Twitter-based cultural studies between emerging nations. This research aims to examine the emotional and sentimental cultural traits of Arabic and Hispanic viewers of a specific football match, as shown through their tweets, regardless of their distinct languages, to determine whether cultural diversity can be noticed in online interaction. Hundreds of tweets from both communities were translated into English as an intermediate language and then evaluated and contrasted using machine learning (ML) models. According to the research, Arabs are more collectivistic (as opposed to individualistic) and, as a result, exhibit less emotional arousal than Hispanics, which was partially supported by the collected Twitter data. This demonstrates how Twitter could play a key part in cultural research, and, therefore, this study contributes to cross-national comparative cultural research. We demonstrate that our method can also be used to evaluate the quality of machine translation based on how effectively it captures the emotions and sentiments of original languages.
- 31 May 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (11) , 6729
Top Cited PapersOpen AccessA Twitter-Based Comparative Analysis of Emotions and Sentiments of Arab and Hispanic Football Fans
Twitter is one of the best online platforms for social interaction, introducing unique means of story-telling through tweets and enabling multiple approaches to the analysis of their content. This study was motivated by the increasing practice of incorporating Twitter into cultural studies and the research gap in Twitter-based cultural studies between emerging nations. This research aims to examine the emotional and sentimental cultural traits of Arabic and Hispanic viewers of a specific football match, as shown through their tweets, regardless of their distinct languages, to determine whether cultural diversity can be noticed in online interaction. Hundreds of tweets from both communities were translated into English as an intermediate language and then evaluated and contrasted using machine learning (ML) models. According to the research, Arabs are more collectivistic (as opposed to individualistic) and, as a result, exhibit less emotional arousal than Hispanics, which was partially supported by the collected Twitter data. This demonstrates how Twitter could play a key part in cultural research, and, therefore, this study contributes to cross-national comparative cultural research. We demonstrate that our method can also be used to evaluate the quality of machine translation based on how effectively it captures the emotions and sentiments of original languages.
- Open Access
- 4 April 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (7) , 4583
Computer-Based Simulated Learning Activities: Exploring Saudi Students’ Attitude and Experience of Using Simulations to Facilitate Unsupervised Learning of Science Concepts
Today, computer-based simulations are widely used in a range of industries and fields for various purposes. They are helpful in testing different scenarios and hypotheses, allowing users to explore the consequences of different decisions and actions. This study aimed to explore the university students’ attitudes and experiences of using simulations to facilitate their unsupervised (without teachers’ support) learning of science concepts. This study involved 566 university students who used online simulations so support their unsupervised learning of science content in physics, chemistry, math, earth science, and biology. The data collected via a cross-sectional survey were analyzed using parametric statistics. The participants of the study showed a high -level of engagement and satisfaction with the use of simulations for unsupervised science learning, suggesting that computer-based simulations have the potential to serve as a user-centered learning interface capable of engaging university students without the teachers’ support. This study did not find a gender-based divide in the students’ experiences. Participants’ independent learning abilities were found to have a significant positive influence on their satisfaction and engagement. The results of this study have theoretical and practical implications for science learning beyond classroom walls.
- 4 April 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (7) , 4583
Open AccessComputer-Based Simulated Learning Activities: Exploring Saudi Students’ Attitude and Experience of Using Simulations to Facilitate Unsupervised Learning of Science Concepts
Today, computer-based simulations are widely used in a range of industries and fields for various purposes. They are helpful in testing different scenarios and hypotheses, allowing users to explore the consequences of different decisions and actions. This study aimed to explore the university students’ attitudes and experiences of using simulations to facilitate their unsupervised (without teachers’ support) learning of science concepts. This study involved 566 university students who used online simulations so support their unsupervised learning of science content in physics, chemistry, math, earth science, and biology. The data collected via a cross-sectional survey were analyzed using parametric statistics. The participants of the study showed a high -level of engagement and satisfaction with the use of simulations for unsupervised science learning, suggesting that computer-based simulations have the potential to serve as a user-centered learning interface capable of engaging university students without the teachers’ support. This study did not find a gender-based divide in the students’ experiences. Participants’ independent learning abilities were found to have a significant positive influence on their satisfaction and engagement. The results of this study have theoretical and practical implications for science learning beyond classroom walls.
- Open Access
- 22 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 29447-29463
Big Data ML-Based Fake News Detection Using Distributed Learning
Users rely heavily on social media to consume and share news, facilitating the mass dis-semination of genuine and fake stories. The proliferation of misinformation on various social media platforms has serious consequences for society. The inability to differentiate between the sev-eral forms of false news on Twitter is a major obstacle to effective detection of fake news. Researchers have made progress toward a solution by placing a greater emphasis on methods for identifying bogus news. The dataset FNC-1, which includes four categories for identifying false news, will be used in this study. The state-of-the-art methods for spotting fake news are evaluated and compared using big data technology (Spark) and machine learning. The methodology of this study employed a decentralized Spark cluster to create a stacked ensemble model. Following feature extraction using N-grams, Hashing TF-IDF, and count vectorizer, we used the proposed stacked ensemble classification model. The results show that the suggested model has a superior classification performance of 92.45% in the F1 score compared to the 83.10 % F1 score of the baseline approach. The proposed model achieved an additional 9.35% F1 score compared to the state-of-the-art techniques.
- 22 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 29447-29463
Open AccessBig Data ML-Based Fake News Detection Using Distributed Learning
Users rely heavily on social media to consume and share news, facilitating the mass dis-semination of genuine and fake stories. The proliferation of misinformation on various social media platforms has serious consequences for society. The inability to differentiate between the sev-eral forms of false news on Twitter is a major obstacle to effective detection of fake news. Researchers have made progress toward a solution by placing a greater emphasis on methods for identifying bogus news. The dataset FNC-1, which includes four categories for identifying false news, will be used in this study. The state-of-the-art methods for spotting fake news are evaluated and compared using big data technology (Spark) and machine learning. The methodology of this study employed a decentralized Spark cluster to create a stacked ensemble model. Following feature extraction using N-grams, Hashing TF-IDF, and count vectorizer, we used the proposed stacked ensemble classification model. The results show that the suggested model has a superior classification performance of 92.45% in the F1 score compared to the 83.10 % F1 score of the baseline approach. The proposed model achieved an additional 9.35% F1 score compared to the state-of-the-art techniques.
- Open Access
- 20 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2707
Hybrid ML-Based Technique to Classify Malicious Activity Using Log Data of Systems
A computer system generates logs to record all relevant operational data about the system and all operations performed in such systems. System log examination is crucial in the identification of network- and system-level assaults. In comparison to established hazards, new technological advancements and better connections pose a greater degree of risk. Several machine learning algorithms that continually monitor logs of data have been created in the past to defend the system against many threats. The majority of earlier anomaly detection methods need a priori knowledge and are not intended for spotting recent or impending threats. Additionally, the growing volume of logs creates fresh difficulties for anomaly identification. In this study, we developed a machine learning technique that identifies abnormalities in the system log with higher accuracy and efficiency. In our suggested strategy, we started with three log features, preprocessed them, and then got more than 10 features for the model. We performed studies to test the effectiveness of our suggested approach, and the criteria for that included F1 scores, ROCs, accuracy, sensitivity, and specificity. We also evaluated how well our suggested technique performs in comparison to other methods. Our suggested solution has a greater rate of anomaly identification than any previously published algorithms as per the experimental findings based on the dataset obtained from the Blue Green/l supercomputer system.
- 20 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2707
Open AccessHybrid ML-Based Technique to Classify Malicious Activity Using Log Data of Systems
A computer system generates logs to record all relevant operational data about the system and all operations performed in such systems. System log examination is crucial in the identification of network- and system-level assaults. In comparison to established hazards, new technological advancements and better connections pose a greater degree of risk. Several machine learning algorithms that continually monitor logs of data have been created in the past to defend the system against many threats. The majority of earlier anomaly detection methods need a priori knowledge and are not intended for spotting recent or impending threats. Additionally, the growing volume of logs creates fresh difficulties for anomaly identification. In this study, we developed a machine learning technique that identifies abnormalities in the system log with higher accuracy and efficiency. In our suggested strategy, we started with three log features, preprocessed them, and then got more than 10 features for the model. We performed studies to test the effectiveness of our suggested approach, and the criteria for that included F1 scores, ROCs, accuracy, sensitivity, and specificity. We also evaluated how well our suggested technique performs in comparison to other methods. Our suggested solution has a greater rate of anomaly identification than any previously published algorithms as per the experimental findings based on the dataset obtained from the Blue Green/l supercomputer system.
- Top Cited PapersOpen Access
Two-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning
Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.
Top Cited PapersOpen AccessTwo-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning
Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.
- 21 January 2019
- Published by Taylor & Francis in Behaviour & Information Technology
- Vol. 38 (11) , 1122-1142
Exploring e-mentoring: co-designing & un-platforming
The underrepresentation of women in the STEM workforce is a global issue. In Saudi Arabia, women constitute 48% of undergraduates in STEM, but their participation in STEM careers remains particularly low. We explored the current state of e-mentoring, and the potential for co-designing to enhance e-mentoring experiences for youth in the Saudi context. We report on how we sought to understand the opportunities, barriers and requirements of e-mentoring for young women in Saudi Arabia through (1) the application of a traditional programme of STEM e-mentoring, (2) workshops on the redesign of e-mentoring, and (3) a co-design activity as the first phase of an alternative e-mentoring process. The study demonstrated that the traits of the participants’ generation had a major effect on the findings; more so than cultural norms. This means that the findings have wider implications than just within the Saudi context. We identify a number of recommendations for designing e-mentoring programmes for young women and teenagers, including un-platforming traditional approaches to e-mentoring and the inclusion of co-design activities as a first step in the e-mentoring process.
- 21 January 2019
- Published by Taylor & Francis in Behaviour & Information Technology
- Vol. 38 (11) , 1122-1142
Exploring e-mentoring: co-designing & un-platforming
The underrepresentation of women in the STEM workforce is a global issue. In Saudi Arabia, women constitute 48% of undergraduates in STEM, but their participation in STEM careers remains particularly low. We explored the current state of e-mentoring, and the potential for co-designing to enhance e-mentoring experiences for youth in the Saudi context. We report on how we sought to understand the opportunities, barriers and requirements of e-mentoring for young women in Saudi Arabia through (1) the application of a traditional programme of STEM e-mentoring, (2) workshops on the redesign of e-mentoring, and (3) a co-design activity as the first phase of an alternative e-mentoring process. The study demonstrated that the traits of the participants’ generation had a major effect on the findings; more so than cultural norms. This means that the findings have wider implications than just within the Saudi context. We identify a number of recommendations for designing e-mentoring programmes for young women and teenagers, including un-platforming traditional approaches to e-mentoring and the inclusion of co-design activities as a first step in the e-mentoring process.