Faculty and staff publications

Permanent URI for this community

https://bspace.buid.ac.ae/handle/1234/2225

Browse

Browsing Faculty and staff publications by Author "Abdallah, Sherief"

Now showing 1 - 10 of 10
  • No Thumbnail Available
    Item
    A Pilot Study Investigating the Use of Mobile Technology for Coordinating Educational Plans in Inclusive Settings
    (SAGE journals, 2021) Siyam, Nur; Abdallah, Sherief
    Good coordination among school staff and families leads to increased learning quality and academic success for students with special education needs and disabilities (SEND). This pilot study aims to investigate the use of mobile technology for the coordination of therapy and learning for students with SEND. This study first follows a participatory design methodology to identify the key design principles required to inform the design of a coordination mobile app for special education. Then, a mobile app (IEP-Connect) is designed and implemented with the aim of facilitating information sharing between different parties involved in the intervention of students with SEND. The proposed app uses the Individualized Educational Plan (IEP) as the focal point of coordination. The evaluation of the app focused on students with autism spectrum disorder (ASD) as their learning requires sharing information from different distributed sources. Results from the usability study revealed that the app has “good” usability and that participants were satisfied with the use of the app for recording and sharing IEP information. The results of this study provide an understanding of the ways in which a coordination app for special education could be made easy and rewarding to use.
  • No Thumbnail Available
    Item
    Cyberbullying Detection Model for Arabic Text Using Deep Learning
    (World scientific connect, 2023) Albayari, Reem; Abdallah, Sherief; Shaalan, Khaled
    . In the new era of digital communications, cyberbullying is a significant concern for society. Cyberbullying can negatively impact stakeholders and can vary from psychological to pathological, such as self-isolation, depression and anxiety potentially leading to suicide. Hence, detecting any act of cyberbullying in an automated manner will be helpful for stakeholders to prevent any unfortunate results from the victim’s perspective. Data-driven approaches, such as machine learning (ML), par ticularly deep learning (DL), have shown promising results. However, the meta-analysis shows that ML approaches, particularly DL, have not been extensively studied for the Arabic text classification of cyberbullying. Therefore, in this study, we conduct a performance evaluation and comparison for various DL algorithms (LSTM, GRU, LSTM-ATT, CNN-BLSTM, CNN-LSTM and LSTM-TCN) on different datasets of Arabic cyberbullying to obtain more precise and dependable findings. As a result of the models’ evaluation, a hybrid DL model is proposed that combines the best characteristics of the baseline models CNN, BLSTM and GRU for identifying cyberbullying. The proposed hybrid model improves the accuracy of all the studied datasets and can be integrated into different social media sites to automatically detect cyberbullying from Arabic social datasets. It has the potential to significantly reduce cyberbullying. The application of DL to cyberbullying detection problems within Arabic text classification can be considered a novel approach due to the complexity of the problem and the tedious process involved, besides the scarcity of relevant research studies.
  • No Thumbnail Available
    Item
    Cyberbullying Detection Model for Arabic Text Using Deep Learning
    (2023) Albayari, Reem; Abdallah, Sherief; Shaalan, Khaled
    In the new era of digital communications, cyberbullying is a significant concern for society. Cyberbullying can negatively impact stakeholders and can vary from psychological to pathological, such as self-isolation, depression and anxiety potentially leading to suicide. Hence, detecting any act of cyberbullying in an automated manner will be helpful for stakeholders to prevent any unfortunate results from the victim’s perspective. Data-driven approaches, such as machine learning (ML), par ticularly deep learning (DL), have shown promising results. However, the meta-analysis shows that ML approaches, particularly DL, have not been extensively studied for the Arabic text classification of cyberbullying. Therefore, in this study, we conduct a performance evaluation and comparison for various DL algorithms (LSTM, GRU, LSTM-ATT, CNN-BLSTM, CNN-LSTM and LSTM-TCN) on different datasets of Arabic cyberbullying to obtain more precise and dependable findings. As a result of the models’ evaluation, a hybrid DL model is proposed that combines the best characteristics of the baseline models CNN, BLSTM and GRU for identifying cyberbullying. The proposed hybrid model improves the accuracy of all the studied datasets and can be integrated into different social media sites to automatically detect cyberbullying from Arabic social datasets. It has the potential to significantly reduce cyberbullying. The application of DL to cyberbullying detection problems within Arabic text classification can be considered a novel approach due to the complexity of the problem and the tedious process involved, besides the scarcity of relevant research studies.
  • No Thumbnail Available
    Item
    Ensemble Stacking Model for Sentiment Analysis of Emirati and Arabic Dialects
    (ScienceDirect, 2023) A. Al Shamsi, Arwa; Abdallah, Sherief
    Sentiment analysis is the process of examining people’s opinions and emotions towards goods, services, organizations, individuals, and other things, through the use of textual data. It involves categorizing text as positive, negative, or neutral to quantify people’s beliefs. Social media platforms have become an important source of sentiment analysis data due to their widespread use for sharing opinions and infor mation. As the number of social media users continues to grow, the amount of data generated for senti ment analysis also increases. Previous research on sentiment analysis for the Arabic language has mostly focused on Modern Standard Arabic and various dialects such as Egyptian, Saudi, Algerian, Jordanian, Tunisian, and Levantine. However, there has been no research on the utilization of deep-learning approaches for sentiment analysis of the Emirati dialect, which is an informal form of the Arabic language spoken in the United Arab Emirates. It’s important to note that each country in the Arab world has its dialect, and some dialects may even have several sub-dialects. The primary aim of this research is to create a highly advanced deep-learning model that can effectively perform sentiment analysis on the Emirati dialect. To achieve this objective, the authors have proposed and utilized seven different deep-learning models for sentiment analysis of the Emirati dialect. Then, an ensemble stacking model was introduced to combine the best-performing deep learning models used in this study. The ensemble stacking deep learning model consisted of deep learning models with a meta learner layer of classifiers. The first model combined the two best-performing deep learning models, the second combined the four best-performing models, and the final model combined all seven trained deep learning models in this research. The proposed ensemble stacking deep learning model was assessed on four datasets, three versions of the ESAAD Emirati Sentiment Analysis Annotated Dataset, two versions of Twitter-based Benchmark Arabic Sentiment Analysis Dataset (ASAD), an Arabic Company Reviews dataset, and an English dataset known as a Preprocessed Sentiment Analysis Dataset PSAD. The results of the experiments demonstrated that the proposed ensemble stacking model presented an outstanding performance in terms of accuracy and achieved an accuracy of 95.54% for the ESAAD dataset, 96.71% for the ASAD benchmark dataset, 96.65% for the Arabic Company Reviews Dataset, and 98.53% for the Preprocessed Sentiment Analysis Dataset PSAD.
  • No Thumbnail Available
    Item
    Governmental data analytics: an agile framework development and a real world data analytics case study
    (Inderscience Enterprises Ltd., 2021) Qadadeh, Wafa; Abdallah, Sherief
    Data is a key asset for organisations. Investment in data analytics has increased significantly over recent years to facilitate data-driven decisions. However, organisations face many challenges during the adoption of data analytics projects. According to Gartner, only 15–20% of data science projects get completed. One challenge is the lack of business understanding; even more so in government organisations where profit is not the main target. We propose a framework to help organisations (and in particular, government organisations) define the objectives of their data analytics projects. While many published frameworks have been used by organisations to implement data analytics efficiently, the literature has shown a gap between the objectives defined in research and those in real projects. This gap contributes to a lack of business understanding and is the main focus of this paper. The proposed framework introduces a systematic technique for business problem identification. To validate our framework, we used our proposed framework to help a governmental organisation in implementing their first data analytics initiative
  • No Thumbnail Available
    Item
    Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
    (MDPI, 2022) ALBayari, Reem; Abdallah, Sherief
    Background: the ability to use social media to communicate without revealing one’s real identity has created an attractive setting for cyberbullying. Several studies targeted social media to collect their datasets with the aim of automatically detecting offensive language. However, the majority of the datasets were in English, not in Arabic. Even the few Arabic datasets that were collected, none focused on Instagram despite being a major social media platform in the Arab world. (2) Methods: we use the official Instagram APIs to collect our dataset. To consider the dataset as a benchmark, we use SPSS (Kappa statistic) to evaluate the inter-annotator agreement (IAA), as well as examine and evaluate the performance of various learning models (LR, SVM, RFC, and MNB). (3) Results: in this research, we present the first Instagram Arabic corpus (sub-class categorization (multi-class)) focusing on cyberbullying. The dataset is primarily designed for the purpose of detecting offensive language in texts. We end up with 200,000 comments, of which 46,898 comments were annotated by three human annotators. The results show that the SVM classifier outperforms the other classifiers, with an F1 score of 69% for bullying comments and 85 percent for positive comments.
  • No Thumbnail Available
    Item
    Mining government tweets to identify and predict citizens engagement
    (ScienceDirect, 2019) Siyam, Nur; Alqaryouti, Omar; Abdallah, Sherief
    The rise of social media offered new channels of communication between a government and its citizens. The social media channels are interactive, inclusive, low-cost, and unconstrained by time or place. This two-way communication between governments and citizens is referred to as electronic citizen participation, or e-participation. E-participation in the age of technology is considered as a mean for citizens to express their opinions and as a new input to be integrated by policy makers to take decisions. Governments and policy makers always aim to increase such participation not only to utilize public expertise and experience, but also to increase the transparency, trust, and acceptability of government decisions. In this research we investigate how governments can increase citizens e-participation on social media. We collected 55,809 tweets over a period of one year from Twitter accounts of a progressive government in the Arab world. This was followed by statistical analysis of posts characteristics (Type, Day, Time) and their impact on citizens’ engagement. Then, we evaluated how well can different machine learning techniques predict user engagement. Results of the statistical analysis confirmed that post type (video, image, link, and status) impacted citizens’ engagement, with videos and images having the highest positive impact on engagement. Furthermore, posting government tweets on weekdays obtained higher citizens’ engagement than weekends. Conversely, time of post had a weak effect on engagement. The results from the machine learning experiments show that two techniques (Random Forest and Adaboost) produced more accurate predictions, particularly when tweet textual contents were also used in the prediction. These results can help governments increase the engagement of their citizens.
  • No Thumbnail Available
    Item
    Sentiment Analysis of Emirati Dialect
    (MDPI, 2022) A. Al Shamsi, Arwa; Abdallah, Sherief
    : Recently, extensive studies and research in the Arabic Natural Language Processing (ANLP) field have been conducted for text classification and sentiment analysis. Moreover, the number of studies that target Arabic dialects has also increased. In this research paper, we constructed the first manually annotated dataset of the Emirati dialect for the Instagram platform. The constructed dataset consisted of more than 70,000 comments, mostly written in the Emirati dialect. We annotated the comments in the dataset based on text polarity, dividing them into positive, negative, and neutral categories, and the number of annotated comments was 70,000. Moreover, the dataset was also annotated for the dialect type, categorized into the Emirati dialect, Arabic dialects, and MSA. Preprocessing and TF-IDF features extraction approaches were applied to the constructed Emirati dataset to prepare the dataset for the sentiment analysis experiment and improve its classification performance. The sentiment analysis experiment was carried out on both balanced and unbalanced datasets using several machine learning classifiers. The evaluation metrics of the sentiment analysis experiments were accuracy, recall, precision, and f-measure. The results reported that the best accuracy result was 80.80%, and it was achieved when the ensemble model was applied for the sentiment classification of the unbalanced dataset.
  • No Thumbnail Available
    Item
    Text Mining Techniques for Sentiment Analysis of Arabic Dialects: Literature Review
    (ASTESJ, 2021) A. Al Shamsi, Arwa; Abdallah, Sherief
    Social media attracts a lot of users around the world. Many reasons drive people to use social media sites such as expressing opinions and ideas, displaying their diaries and sharing them with others, social communication with family and friends and building new social relationships, learning and sharing knowledge. Written text is one of the most common forms used for communication while using social media sites. People use written texts in different languages, and due to the increased usage of social networking sites around the world, the amount of texts and data resulting from this use is large. These generated data considered as a valuable source of information that attracted business owners, companies, government institutions, and of course, it attracts researchers and data scientists as well. Researchers and data scientists increasingly presented great efforts in investigating and analyzing Arabic Language texts. Most of these efforts targeted the Modern Standard form of Arabic Language. While exploring the social media sites, most of the Arab users tend to use their dialects while utilizing Social Media sites, which results in generating a massive amount of Arabic Dialects texts. The number of researches and analysis of Dialects' form of the Arabic language are limited, however, it is increasing recently. This literature review aims to explore approaches and methods used for Sentiment Analysis of Arabic Dialects text.
  • No Thumbnail Available
    Item
    Toward automatic motivator selection for autism behavior intervention therapy
    (ProQuest Central, 2022) Siyam, Nur; Abdallah, Sherief
    Children with autism spectrum disorder (ASD) usually show little interest in academic activities and may display disruptive behavior when presented with assignments. Research indicates that incorporating motivational variables during interven tions results in improvements in behavior and academic performance. However, the impact of such motivational variables varies between children. In this paper, we aim to address the problem of selecting the right motivator for children with ASD using reinforcement learning by adapting to the most infuential factors impacting the efectiveness of the contingent motivator used. We model the task of selecting a motivator as a Markov decision process problem. The states, actions and rewards design consider the factors that impact the efectiveness of a motivator based on applied behavior analysis as well as learners’ individual preferences. We use a Q-learning algorithm to solve the modeled problem. Our proposed solution is then implemented as a mobile application developed for special education plans coordination. To evaluate the motivator selection feature, we conduct a study involving a group of teachers and therapists and assess how the added feature aids the participants in their decision-making process of selecting a motivator. Preliminary results indicated that the motivator selection feature improved the usability of the mobile app. Analysis of the algorithm performance showed promising results and indicated improvement of the recommendations over time.