BSpace Repository :: Browsing by Author "Shaalan, Khaled"

Browsing by Author "Shaalan, Khaled"

Now showing 1 - 20 of 46

A Chatbot Intent Classifier for Supporting High School Students
(2022) K. Assayed, Suha; Shaalan, Khaled; Alkhatib, Manar
INTRODUCTION: An intent classification is a challenged task in Natural Language Processing (NLP) as we are asking the machine to understand our language by categorizing the users’ requests. As a result, the intent classification plays an essential role in having a chatbot conversation that understand students’ requests. OBJECTIVES: In this study, we developed a novel chatbot called “HSchatbot” for predicting the intent classifications from high school students’ enquiries. Evidently, students in high schools are the most concerned among all students about their future; thus, in this stage they need an instant support in order to prepare them to take the right decision for their career choice. METHODS: The authors in this study used the Multinomial Naive-Bayes and Random Forest classifiers for predicting the students’ enquiries, which in turn improved the performance of the classifiers by using the feature’s extractions. RESULTS: The results show that the random forest classifier performed better than Multinomial Naive-Bayes since the performance of this model is checked by using different metrics like accuracy, precision, recall and F1 score. Moreover, all showed high accuracy scores exceeding 90% in all metrics. However, the accuracy of Multinomial Naive-Bayes classifier performed much better when using CountVectorizers compared to using the TF-IDF. CONCLUSION: In the future work, the results will be analysed and investigated in order to figure out the main factors that affect the performance of Multinomial Naive-Bayes classifier, as well as evaluating the model with using a large corpus of students’ questions and enquiries.
A Multimodal Approach to Improve Performance Evaluation of Call Center Agent
(MDPI, 2021) Ahmed , Abdelrahman; Shaalan, Khaled; Toral, Sergio; Hifny, Yasser
The paper proposes three modeling techniques to improve the performance evaluation of the call center agent. The first technique is speech processing supported by an attention layer for the agent’s recorded calls. The speech comprises 65 features for the ultimate determination of the context of the call using the Open-Smile toolkit. The second technique uses the Max Weights Similarity (MWS) approach instead of the Softmax function in the attention layer to improve the classification accuracy. MWS function replaces the Softmax function for fine-tuning the output of the attention layer for processing text. It is formed by determining the similarity in the distance of input weights of the attention layer to the weights of the max vectors. The third technique combines the agent’s recorded call speech with the corresponding transcribed text for binary classification. The speech modeling and text modeling are based on combinations of the Convolutional Neural Networks (CNNs) and Bi-directional Long-Short Term Memory (BiLSTMs). In this paper, the classification results for each model (text versus speech) are proposed and compared with the multimodal approach’s results. The multimodal classification provided an improvement of (0.22%) compared with acoustic model and (1.7%) compared with text model.
A Systematic Review of Conversational AI Chatbots in Academic Advising
(SpringerLink, 2024) Assayed, Suha Khalil; Alkhatib, Manar; Shaalan, Khaled
Purpose – This paper aims to review several studies published between 2018 to 2022 about advising chatbots in schools and universities as well as evaluating the state-of-the-art machine learning models that are deployed into these models. Methodology – This paper follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), it demonstrated the main phases of the systematic review, it starts with screening 128 articles and then including 11 articles for systematic review which focused on the current services of the advising chatbots in schools and universities, as well the artificial models that are embedded into the chatbots. Findings – Two main dimensions with other sub-dimensions are extracted from the 11 included studies as it shows the following: 1- Advising chatbots AI Architecture which includes other sub-dimensions on identifying the deep learning based chatbots, hybrid chatbots and other open-resources for customizing chatbots; 2- The goals of the advising chatbot as it includes both the admission advising and academic advising. Conclusion – Most of studies shows that advising chatbots are developed for admission and academic advising. Few researchers who study the chatbots in high schools, there is a lack of studies in developing chatbots for students advising in high schools. Limitations and future work – This study is constrained to review the studies from 2018–2022, and it is not exposed to the chatbots artifacts, even though, the human-chatbot interaction has an essential impact on students’ experiences. Future research should include the impact of chatbots interactive design and students’ experiences.
A SYSTEMATIC REVIEW OF CRYPTDB: IMPLEMENTATION, CHALLENGES, AND FUTURE OPPORTUNITIES
(Journal of Management Information and Decision Sciences, 2021) Yousuf, Hana; A. Salloum, Said; Aburayya, Ahmad; Al-Emran, Mostafa; Shaalan, Khaled
In the case of compromised databases or interested database managers, CryptDB has been built for validated and realistic protection. CryptDB operates through encrypted data while executing SQL queries. The key concept of the SQL-aware encryption technique is to map SQL operations to encryption methods, adjustable query-driven encryption which facilitates CryptDB to modify the encryption level of data depending on user queries and to alter the data through layered encryption levels in an efficient manner. The systematic literature review in this paper shows that there is ongoing research regarding the implementation of CryptDB in new applications such as cloud computing and management information systems. Experiments are being conducted to improve the encryption schemes and layers to avoid data leakage when CryptDB is applied in dynamic applications. Further, there are studies on alternative query-processing systems to improve the performance and throughput. However, CryptDB is found to be the only practical approach to process the queries for encrypted data.
Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks
(MDPI, 2020) Ahmed , Abdelrahman; Toral, Sergio; Shaalan, Khaled; Hifny, Yaser
Measuring the productivity of an agent in a call center domain is a challenging task. Subjective measures are commonly used for evaluation in the current systems. In this paper, we propose an objective framework for modeling agent productivity for real estate call centers based on speech signal processing. The problem is formulated as a binary classification task using deep learning methods. We explore several designs for the classifier based on convolutional neural networks (CNNs), long-short-term memory networks (LSTMs), and an attention layer. The corpus consists of seven hours collected and annotated from three different call centers. The result shows that the speech-based approach can lead to significant improvements (1.57% absolute improvements) over a robust text baseline system.
AI-based Academic Advising Framework: A Knowledge Management Perspective
((IJACSA) International Journal of Advanced Computer Science and Applications,, 2022) Bilquise, Ghazala; Shaalan, Khaled
Academic advising has become a critical factor of students’ success as universities offer a variety of programs and courses in their curriculum. It is a student-centered initiative that fosters a student’s involvement with the institution by supporting students in their academic progression and career goals. Managing the knowledge involved in the advising process is crucial to ensure that the knowledge is available to those who need it and that it is used effectively to make good advising decisions that impact student persistence and success. The use of AI-based tools strengthens the advising process by reducing the workload of advisors and providing better decision support tools to improve the advising practice. This study explores the challenges associated with the current advising system from a knowledge management perspective and proposes an integrated AI-based framework to tackle the main advising tasks.
An Arabic social media based framework for incidents and events monitoring in smart cities
(2019) Alkhatib Manar; El Barachi, May; Shaalan, Khaled
Smart city initiatives aim at leveraging human, collective, and technological capital to ensure sustainable development and quality of life for their citizens. Offering efficient and sustainable emergency rescue services in smart cities requires coordinated efforts and shared information between the public, the decision makers, and rescue teams. With the rapid growth and proliferation of social media platforms, there is a vast amount of user-generated content that can be used as source of information about cities. In this work, we propose a novel framework for events and incidents’ management in smart cities. Our framework uses text mining, text classification, named entity recognition, and stemming techniques to extract the intelligence needed from Arabic social media feeds, for effective incident and emergency management in smart cities. In our system, the data is automatically collected from social media feeds then processed to generate incident intelligence reports that can provide emergency situational awareness and early warning signs to rescue teams. The proposed framework was implemented and tested using datasets collected from Arabic Twitter feeds over a two-years span, and the obtained results show that Polynomial Networks and Support Vector Machines are the top performers in terms of Arabic text classification, achieving classification accuracy of 96.49% and 94.58% respectively, when used with stemming. The results also showed that the use of stemming led to a penalty in terms of response time, and that the richer the dataset/corpus used in terms of size and composition, the higher the classification accuracy will be.
An Innovative Study of E-Payment Systems Adoption in Higher Education: Theoretical Constructs and Empirical Analysis
(International Journal of Interactive Mobile Technologies, 2019) A. Salloum, Said; Al-Emran, Mostafa; Khalaf, Rifat; Habes, Mohammed; Shaalan, Khaled
Examining the adoption of e-payment systems is not a new research topic. Nevertheless, studying the factors affecting the adoption of epayment systems in higher educational institutions is a new research trend. Thus, this study is considered one of the few that attempts to investigate the fac tors affecting the e-payment systems adoption in six different universities in the United Arab of Emirates (UAE). A total number of 289 students took part in the study. This study proposed a new research model in which the students’ intention to use the e-payment systems are affected by five different factors including perceived benefit, performance expectancy, perceived risk, perceived security/privacy, and trust. The partial least squares-structural equation modeling (PLS-SEM) approach was used to validate the research model. The empirical results suggested that perceived benefit and performance expectancy have a significant positive relationship with the students’ intention to use e-payment systems, whereas perceived security/privacy and perceived risk exhibited a significant negative relationship. However, the results triggered out that trust has an insignificant relationship with the students’ intention to use e-payment systems. The results acquired from this research provide a fresh and an up-to-date information on the e-payment systems adoption in the higher educational institutions.
Arabic Educational Neural Network Chatbot
(Information Sciences Letters An International Journal, 2023) A. Alazzam, Bayan; Alkhatib, Manar; Shaalan, Khaled
Chatbots (machine-based conversational systems) have grown in popularity in recent years. Chatbots powered by artificial intelligence (AI) are sophisticated technologies that replicate human communication in a range of natural languages. A chatbot’s primary purpose is to interpret user inquiries and give relevant, contextual responses. Chatbot success has been extensively reported in a number of widely spoken languages; nonetheless, chatbots have not yet reached the predicted degree of success in Arabic. In recent years, several academics have worked to solve the challenges of creating Arabic chatbots. Furthermore, the development of Arabic chatbots is critical to our attempts to increase the use of the language in academic contexts. Our objective is to install and create an Arabic chatbot that will help the Arabic language in the area of education. To begin implementing the chabot, we collected datasets from Arabic educational websites and had to prepare these data using the NLP methods. We then used this data to train the system using a neural network model to create an Arabic neural network chabot. Furthermore, we found relevant research, conducted earlier investigations, and compared their findings by searching Google scholar and looking through the linked references. Data was gathered and saved in a json file. Finally, we programmed the chabot and the models in Python. As a consequence, an Arabic chatbot answers all questions about educational regulations in the United Arab Emirates.
Arabic Question Answering: A Study on Challenges, Systems, and Techniques
(International Journal of Computer Applications, 2019) Samy, Heba; E. Hassanein, Ehab; Shaalan, Khaled
The enormous increase of the amount of information available on the web creates the need for systems like Question Answering to bridge the gap between general end users and the web with its different data representations. A considerable portion of the available data on the web is written in Arabic for and by Arabic users. This paper provides a review of the Arabic Question Answering Systems building processes and the challenges met by the researchers in this topic due to the Arabic language special characteristics. A general architecture is represented for the Question Answering task on both structured and unstructured data. Then, an overview of the work done in Arabic Question Answering Systems is presented. Finally, a number of tools and linguistic resources are recommended for researchers to develop Arabic question answering systems.
Artificial Intelligence Chatbots: A Survey of Classical versus Deep Machine Learning Techniques
(2023) A. Alazzam, Bayan; Alkhatib, Manar; Shaalan, Khaled
: Artificial Intelligence (AI) enables machines to be intelligent, most importantly using Machine Learning (ML) in which machines are trained to be able to make better decisions and predictions. In particular, ML-based chatbot systems have been developed to simulate chats with people using Natural Language Processing (NLP) techniques. The adoption of chatbots has increased rapidly in many sectors, including, Education, Health Care, Cultural Heritage, Supporting Systems and Marketing, and Entertainment. Chatbots have the potential to improve human interaction with machines, and NLP helps them understand human language more clearly and thus create proper and intelligent responses. In addition to classical ML techniques, Deep Learning (DL) has attracted many researchers to develop chatbots using more sophisticated and accurate techniques. However, research has paid chatbots have widely been developed for English, there is relatively less research on Arabic, which is mainly due to its complexity and lack of proper corpora compared to English. Though there have been several survey studies that reviewed the state-of-the-art of chatbot systems, these studies (a) did not give a comprehensive overview of how different the techniques used for Arabic chatbots in comparison with English chatbots; and (b) paid little attention to the application of ANN for developing chatbots. Therefore, in this paper, we conduct a literature survey of chatbot studies to highlight differences between (1) classical and deep ML techniques for chatbots; and (2) techniques employed for Arabic chatbots versus those for other languages. To this end, we propose various comparison criteria of the techniques, extract data from collected studies accordingly, and provide insights on the progress of chatbot development for Arabic and what still needs to be done in the future.
ASystematic Review on Blockchain Adoption
(MDPI, 2022) AlShamsi, Mohammed; Al-Emran, Mostafa; Shaalan, Khaled
: Blockchain technologies have received considerable attention from academia and industry due to their distinctive characteristics, such as data integrity, security, decentralization, and reli ability. However, their adoption rate is still scarce, which is one of the primary reasons behind conducting studies related to users’ satisfaction and adoption. Determining what impacts the use and adoption of Blockchain technologies can efficiently address their adoption challenges. Hence, this systematic review aimed to review studies published on Blockchain technologies to offer a thorough understanding of what impacts their adoption and discuss the main challenges and opportunities across various sectors. From 902 studies collected, 30 empirical studies met the eligibility criteria and were thoroughly analyzed. The results confirmed that the technology acceptance model (TAM) and technology–organization–environment (TOE) were the most common modelsforstudying Blockchain adoption. Apart from the core variables of these two models, the results indicated that trust, perceived cost, social influence, and facilitating conditions were the significant determinants influencing several Blockchain applications. The results also revealed that supply chain management is the main domain in which Blockchain applications were adopted. Further, the results indicated inadequate exposure to studying the actual use of Blockchain technologies and their continued use. It is also essential to report that existing studies have examined the adoption of Blockchain technologies from the lens of the organizational level, with little attention paid to the individual level. This review is believed to improve our understanding by revealing the full potential of Blockchain adoption and opening the door for further research opportunities.
Bilingual AI-Driven Chatbot for Academic Advising
((IJACSA) International Journal of Advanced Computer Science and Applications,, 2022) Bilquise, Ghazala; Ibrahim, Samar; Shaalan, Khaled
Conversational technologies are revolutionizing how organizations communicate with people, thereby raising quick responses and constant availability expectations. Students often have queries about the institutional and academic policies and procedures, academic progression, activities, and more in an academic environment. In reality, the student services team and the academic advisors are overwhelmed with several queries that they cannot provide instant responses to, resulting in dissatisfaction with services. Our study leverages Artificial Intelligence and Natural Language processing technologies to build a bilingual chatbot that interacts with students in the English and Arabic languages. The conversational agent is built in Python and designed for students to support advising-related queries. We use a purpose-built domain-specific corpus consisting of the common questions advisors receive from students and their responses as the chatbots knowledge base. The chatbot engine determines the user intent by processing the input and retrieves the most appropriate response that matches the intent with an accuracy of 80% in English and 75% in Arabic. We also evaluated the chatbot interface by conducting field experiments with students to test the accuracy of the chatbot with real-time input and test the application interface.
Chatbot Adoption: A Multiperspective Systematic Review and Future Research Agenda
(IEEE, 2023) Alsharhan , Abdulla; Al-Emran, Mostafa; Shaalan, Khaled
—Studies on Chatbot adoption are gaining traction across different fields. Previous studies have outlined several drivers of Chatbot adoption through the lenses of various tech nology adoption theories. However, these studies have not been thoroughlyreviewedandsynthesized.Therefore,thisarticleaimsto analyzethetechnologyadoptiontheories,antecedents,moderators, domains, methodologies, and participants through a multiperspec tive viewpoint. Out of 3942 studies collected, 219 studies were ana lyzed. The main findings indicated that the technology acceptance model, social presence theory, and computers are social actors are the main dominant theories in explaining Chatbot adoption. MoststudiesfocusedonexaminingtheusageintentionofChatbots, with limited investigations on actual use and continuous intention. Nearly 63% of the analyzed studies did not employ moderators, andthose that did tend to do so mostfrequently focused on gender, Chatbot/technical experience, andage.Thisarticle presents afresh viewpoint that deepens our understanding of Chatbot adoption and proposes several agendas for future research. The agenda incorporates research directions for Chatbots adoption in general and generative artificial intelligence in specific. It also offers sev eral theoretical contributions and provides relevant information to Chatbot developers, decision-makers, practitioners, IT vendors, and policymakers.
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.
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.
Deep Learning for Arabic Image Captioning: A Comparative Study of Main Factors and Preprocessing Recommendations
(Deep learning; NLP; Arabic image captioning; Arabic text preprocessing; LSTM; VGG16; INCEPTION V3, 2021) Hejazi, Hani; Shaalan, Khaled
Emerging Research Topic Detection Using Filtered-LDA
(MDPI, 2021) Alattar, Fuad; Shaalan, Khaled
Comparing two sets of documents to identify new topics is useful in many applications, like discovering trending topics from sets of scientific papers, emerging topic detection in microblogs, and interpreting sentiment variations in Twitter. In this paper, the main topic-modeling-based approaches to address this task are examined to identify limitations and necessary enhancements. To overcome these limitations, we introduce two separate frameworks to discover emerging topics through a filtered latent Dirichlet allocation (filtered-LDA) model. The model acts as a filter that identifies old topics from a timestamped set of documents, removes all documents that focus on old topics, and keeps documents that discuss new topics. Filtered-LDA also genuinely reduces the chance of using keywords from old topics to represent emerging topics. The final stage of the filter uses multiple topic visualization formats to improve human interpretability of the filtered topics, and it presents the most-representative document for each topic.
Enhancing Student Services: Machine Learning Chatbot Intent Recognition for High School Inquiries
(SpringerLink, 2024) Assayed, Suha Khalil; Alkhatib, Manar; Shaalan, Khaled
Purpose - This paper aims to develop a novel chatbot to improve student services in high school by transferring students’ enquiries to a particular agent, based on the enquiry type. In accordance to that, comparison between machine learning and neural network is conducted in order to identify the most accurate model to classify students’ requests. Methodology - In this study we selected the data from high school students, since high school is one of the most essential stages in students’ lives, as in this stage, students have the option to select their academic streams and advanced courses that can shape their careers according to their passions and interests. A new corpus is created with (1004) enquiries. The data is annotated manually based on the type of request. The label high-school-courses is assigned to the requests that are related to elective courses and standardized tests during high school. On the other hand, the label majors & universities is assigned to the questions that are related to applying to universities along with selecting the majors. Two novel classifier chatbots are developed and evaluated, where the first chatbot is developed by using a Naive Bayes Machine Learning Algorithm, while the other is developed by using Recurrent Neural Networks (RNN)-LSTM. Findings - Some features and techniques are used in both models in order to improve the performance. However, both models have conveyed a high accuracy score which exceeds (91%). The models have been validated as a pilot testing by using high school students as well as experts in education and six questions and enquiries are presented to the chatbots for the evaluation. Implications and future work - This study can add value to the team of researchers and developers to integrate such classifiers into different applications. As a result, this improves the users’ services, in particular, those implemented in educational institutions. In the future, it is certain that intent recognition will be developed with the addition of a voice recognition feature which can successfully integrated into smartphones.
Factors Affecting Autonomous Vehicles Adoption: A Systematic Review, Proposed Framework, and Future Roadmap
(Taylor & Francis online, 2023) Al Mansoori, Saeed; Al-Emran, Mostafa; Shaalan, Khaled
Autonomous vehicles (AVs) offer several benefits, such as improving road safety, mitigating traffic congestion, and reducing fuel consumption and gas emissions. Despite these benefits, their adop tion rate remains limited due to various factors influencing users’ decisions. While previous studies have identified numerous factors influencing AV adoption using various adoption frameworks, the factors have not been comprehensively analyzed and synthesized. Thus, this systematic review aims to bridge this gap by identifying and classifying the factors influencing the adoption of AVs. Out of 3,532 collected research papers, 71 empirical studies were analyzed thoroughly. The find ings demonstrated that the technology acceptance model (TAM) was the most widely used model for investigating AV adoption. The identified factors in the analyzed studies were classified into distinct categories: psychological and behavioral factors, technological factors, social factors, envir onmental factors, security and privacy factors, AV-related factors, risky and negative factors, condi tional factors, and monetary factors. We have proposed an AV adoption framework grounded in this taxonomy to direct subsequent empirical research. We have also highlighted numerous agen das to serve as a blueprint for future AV adoption studies. This review offers various theoretical insights and actionable recommendations for multiple AV research, development, and implemen tation stakeholders.

Browsing by Author "Shaalan, Khaled"

Results Per Page

Sort Options