Skip to main content

Nabila Khodeir

Followers

5

Following

4

Co-authors

3

Public Views

Shohei Higashiyama

Ghulam Mubashar Hassan

The University of Western Australia

hadi jahanshahi

Iust

Cairo University

Md. Anwar Hussen Wadud

Bangladesh University of Engineering & Technology

Harnain Kour 18dcs008

Interests

Uploads

Papers by Nabila Khodeir

New weighted BERT features and multi-CNN models to enhance the performance of MOOC posts classification

Neural Computing and Applications

Learning is an essential requirement for humans, and its means have evolved. Ten years ago, Massi... more Learning is an essential requirement for humans, and its means have evolved. Ten years ago, Massive Open Online Courses (MOOCs) were introduced, attracting many interests and learners. MOOCs provide forums for learners to interact with instructors and to express any problems they encounter in the educational process. However, MOOCs have a high dropout rate due to the difficulties of following up on learners' posts and identifying the urgent ones to react quickly. This research aims to assist instructors in automatically identifying urgent posts, making it easier to respond to such posts rapidly, increasing learner engagement, and improving course completion rate. In this paper, we propose a novel classification model for identifying urgent posts. The proposed model consists of four stages. In the first stage, the post-text is code-encoded and vectorized using a pre-trained BERT model. In the second stage, a novel feature aggregation model is proposed to reveal data-based relatio...

Utilizing Diagnosing Problems in a Probabilistic Domain to Build Student Models

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The student answers to questions requiring diagnosing skills are used to estimate the actual student model. Updating and verification of the model are conducted based on the matching between the student's and model answers. Two different approaches to updating are suggested, i) coarse and ii) refined model updating. Moreover, the effect of the order of which questions are presented to the student is investigated. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model. In addition, the accuracy of the algorithm is highly insensitive to the order of which the questions are presented, more so when using the refined model updating approach..

Question Generation for Adaptive Assessment for Student Knowledge Modeling in Probabilistic Domains

Abstract. In this paper a question generation approach for adaptive assessment is purposed to est... more Abstract. In this paper a question generation approach for adaptive assessment is purposed to estimate the student knowledge model in a probabilistic domain within an intelligent tutoring system. Assessing questions are generated adaptively according to the student knowledge based on two factors (i) the student misconceptions that are entailed in the student knowledge model, and (ii) the information gain maximizing. Updating and verification of the student model are conducted based on the matching between the student’s and model answers to assessing questions. Comparison between using the adapted questions and random questions is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40 % in addition to decreasing of the required assessing questions by 50 % compared to using fixed questions.

Addressing student misinterpretations of story problems in MAST

2017 Intl Conf on Advanced Control Circuits Systems (ACCS) Systems & 2017 Intl Conf on New Paradigms in Electronics & Information Technology (PEIT), 2017

Story problems are of ultimate importance of mathematics. This stems from the fact that they help... more Story problems are of ultimate importance of mathematics. This stems from the fact that they help improve various students' skills including reading the story problem, extracting the embedded mathematical information and the unknown quantity to compute, and applying the correct mathematical operators to solve the problem. Unfortunately, this type of problems may suffer from misinterpretation errors and errors due to overlooking some embedded information regardless of the proficiency of the students in mathematics. This paper introduces the Math Story Problem Tutor (MAST), a Web-based intelligent tutoring system of probability story problems. The focus of this paper is to explain how MAST deals with those problems using the Question Generation Module (QGM) and the Cognitive Module (CM). The QGM is able to generate story problems based on Natural Language Generation (NLG) techniques. This results in known semantic descriptions and linguistic structures of each story problem part. ...

Multi-level skills-based student modeling in an Arabic grammar tutor

2017 Intl Conf on Advanced Control Circuits Systems (ACCS) Systems & 2017 Intl Conf on New Paradigms in Electronics & Information Technology (PEIT), 2017

Language Tutoring Systems (LTSs) are computer-based tutoring systems that address linguistic skil... more Language Tutoring Systems (LTSs) are computer-based tutoring systems that address linguistic skills. Most LTSs rely on Natural Language Processing (NLP) tools for analyzing the student's answer to support him/her with appropriate feedback. In such systems, diagnosing the student errors is typically based on a large library of students' expected bugs. In addition, such systems (especially in case of the Arabic language) don't consider modeling of the student knowledge or assigning difficulty levels to the presented questions. Subsequently, such systems do not support individualization of their interactions to each student's needs and preferences. This paper presents the Arabic Grammar Tutor (AGTutor), which utilizes Constraint-Based Modeling (CBM) to model the domain eliminating the need for the bugs' library. Grammar rules are represented as a set of constraints that are categorized in terms of the different linguistic skills. Linguistic skills are classified int...

Iagnosing Problems in a P Robabilistic D Omain to B Uild S Tudent M Odels

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The student answers to questions requiring diagnosing skills are used to estimate the actual student model. Updating and verification of the model are conducted based on the matching between the student's and model answers. Two different approaches to updating are suggested, i) coarse and ii) refined model updating. Moreover, the effect of the order of which questions are presented to the student is investigated. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model. In addition, the accuracy of the algorithm is highly insensitive to the order of which the questions are presented, more so when using the refined model updating approach..

Question generation for adaptive assessment for student knowledge modeling in probabilistic domains

In this paper a question generation approach for adaptive assessment is purposed to estimate the ... more In this paper a question generation approach for adaptive assessment is purposed to estimate the student knowledge model in a probabilistic domain within an intelligent tutoring system. Assessing questions are generated adaptively according to the student knowledge based on two factors (i) the student misconceptions that are entailed in the student knowledge model, and (ii) the information gain maximizing. Updating and verification of the student model are conducted based on the matching between the student’s and model answers to assessing questions. Comparison between using the adapted questions and random questions is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40% in addition to decreasing of the required assessing questions by 50% compared to using fixed questions.

Inferring the Differential Student Model in a Probabilistic Domain Using Abduction inference in Bayesian networks

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The suggested algorithm aims to estimate the actual student model through the student answers to questions requiring diagnosing skills. Updating and verification of the model are conducted based on the matching between the student and model answers. Two different approaches to updating namely coarse and refined model are suggested. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model.

Student Modeling Using Educational Data Mining Techniques

2019 6th International Conference on Advanced Control Circuits and Systems (ACCS) & 2019 5th International Conference on New Paradigms in Electronics & information Technology (PEIT)

Educational Data Mining (EDM) is a research area which applies machine learning, data mining and ... more Educational Data Mining (EDM) is a research area which applies machine learning, data mining and statistical techniques to different types of data that come from educational settings. Student modeling is one of EDM applications that used to recommend or adapt the educational system resources. This paper explores the different educational systems and their characteristics. In addition, modeling of the student learning style, affective state, and prediction of the student performance are addressed. Profiling, grouping students and collaboration analysis are also explored.

Rule-based Cognitive Modeling and Model Tracing in a Math Story Problem Tutor

International Journal of Emerging Technologies in Learning (iJET)

Intelligent Tutoring Systems (ITSs) are intended to help in tutoring the students in specific dom... more Intelligent Tutoring Systems (ITSs) are intended to help in tutoring the students in specific domains typically by improving their problem solving skills. An important aspect of such ITSs is their ability to solve the generated problems in the same way that the student would in addition to interpreting the student actions to provide relevant feedback and help. Cognitive models that mimic the way knowledge is represented in human minds are excellent means toward achieving this goal. This paper discusses cognitive modelling in the MAth Story problem Tutor (MAST). MAST is a Web-based ITS that can generate probability story problems of different contexts, types and difficulty levels. The paper also discusses the model tracing approach of MAST to interpret the student actions in symbolizing the word problems and estimating the required probabilities to provide relevant feedback and help. A major contribution of the paper is in considering the symbolization of the probability word problem...

Bi-GRU Urgent Classification for MOOC Discussion Forums Based on BERT

IEEE Access

MOOC provides a forum for communication between students and teachers and is a platform for stude... more MOOC provides a forum for communication between students and teachers and is a platform for students to articulate their problems in the education process. Because of the large number of students and the small number of teachers, distinguishing posts that require rapid intervention is challenging. Therefore, there is a need to automatically classify the posts in the forum and distinguish urgent posts requiring a quick response. This classification is mainly based on the numerical representation of the text included in the students' posts. BERT is a model for representing words according to the context in which they are used. These context-dependent representations can capture many syntactic and semantic properties of words under diverse linguistic contexts. This paper aims to utilize such representation as a pre-trained embedding layer for a broader task, and then it is fine-tuned to define the urgent post. This embedding layer passes on the classification model consisting of a multi-layer bi-directional Gated Recurrent Unit (GRU). Also, different types of embedding layers have been experimented with other deep neural network structures for comparison. Despite the simplicity of the proposed structure, using BERT as an embedding layer achieves urgent posts classification with a weighted F-score of 91.9%, 91.0%, and 90.0% on the Stanford MOOC Posts dataset. Distinguishing urgent posts with high accuracy helps teachers prioritize their responses and answer learner questions promptly. Also, this helps reducing dropout rates and improving completion rates. INDEX TERMS BERT, embedding layer, gated recurrent unit, MOOC, urgent posts. NABILA A. KHODEIR received the M.A. and Ph.D. degrees from the Electronics and Com

Constraint-based and Fuzzy Logic Student Modeling for Arabic Grammar

International Journal of Computer Science and Information Technology

Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with lin... more Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with linguistic skills. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not consider the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different difficulty levels. Constraint-based student modeling (CBSM) technique is used as a short-term student model. CBSM is used to define in small grain level the different grammar skills through the defined skill structures. The main contribution of this paper is the hierarchal representation of the system&#39;s basic grammar skills as domain knowledge. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. In addition, satisfying constraints and the number of trails the student takes for answering each question and fuzzy logic decision system are used to determine the student learning level for each lesson as a long-term model. The results of the evaluation showed the system&#39;s effectiveness in learning in addition to the satisfaction of students and teachers with its features and abilities.

Constraint-based Student Modelling in Probability Story Problems with Scaffolding Techniques

International Journal of Emerging Technologies in Learning (iJET)

Constraint-based student modelling (CBM) is an important technique employed in intelligent tutori... more Constraint-based student modelling (CBM) is an important technique employed in intelligent tutoring systems to model student knowledge to provide relevant assistance. This paper introduces the Math Story Problem Tutor (MAST), a Web-based intelligent tutoring system for probability story problems, which is able to generate problems of different contexts, types and difficulty levels for self-paced learning. Constraints in MAST are specified at a low-level of granularity to allow fine-grained diagnosis of the student error. Furthermore, MAST extends CBM to address errors due to misunderstanding of the narrative story. It can locate and highlight keywords that may have been overlooked or misunderstood leading to an error. This is achieved by utilizing the role of sentences and keywords that are defined through the Natural Language Generation (NLG) methods deployed in the story problem generation. MAST also integrates CBM with scaffolding questions and feedback to provide various forms o...

Generating story problems via controlled parameters in a web-based intelligent tutoring system

International Journal of Information and Learning Technology

Detection and Handling of Different Types of Concept Drift in News Recommendation Systems

International Journal of Computer Science and Information Technology

To address the increase in volume of data streams online users interact with, there are a growing... more To address the increase in volume of data streams online users interact with, there are a growing number of tools and models to summarize and extract information. These tools use prediction models to personalize and extract useful information. However, data streams are highly prone to the phenomena of concept drift, in which the data distribution changes over time. To maintain the performance level of these models, models should adapt to handle the existence of adrift. In this work, we present the Incremental Knowledge Concept Drift (IKCD) algorithm, an adaptive unsupervised learning algorithm for recommendation systems in news data stream. Data modelling in IKCD uses k-means clustering to determine the occurrence of a drift while avoiding the dependency on the availability of data labels. Once a drift is detected, new retraining data is composed from the old and new concept. IKCD is tested using synthetic and real benchmark datasets from various domains, which demonstrate the different drift types and with different rate of change. Experimental results illustrate an enhanced performance with respect to (a) reducing model sensitivity to noise, (b) reducing model rebuilding frequency up to 50% in case of re-occurring drift and (c) increasing accuracy of the model by about 10% with respect the accuracy of confidence distribution batch detection algorithm.

Graphical Representation in Tutoring Systems

International Journal of Computer Science and Information Technology

Visual representation and organization of the knowledge have been utilized in different ways in t... more Visual representation and organization of the knowledge have been utilized in different ways in tutoring systems to upgrade their usefulness. This paper concentrates on the usage of various graphical formalisms, for example, the conceptual graph, ontology, and concept map in tutoring systems. The paper addresses what is way of the utilization of every formalism and the offering of the potential outcomes to assist the student in education systems.

Inferring the Differential Student Model in a Probabilistic Domain Using Abduction inference in Bayesian networks

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The suggested algorithm aims to estimate the actual student model through the student answers to questions requiring diagnosing skills. Updating and verification of the model are conducted based on the matching between the student and model answers. Two different approaches to updating namely coarse and refined model are suggested. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model.

Question generation for adaptive assessment for student knowledge modeling in probabilistic domains

In this paper a question generation approach for adaptive assessment is purposed to estimate the ... more In this paper a question generation approach for adaptive assessment is purposed to estimate the student knowledge model in a probabilistic domain within an intelligent tutoring system. Assessing questions are generated adaptively according to the student knowledge based on two factors (i) the student misconceptions that are entailed in the student knowledge model, and (ii) the information gain maximizing. Updating and verification of the student model are conducted based on the matching between the student's and model answers to assessing questions. Comparison between using the adapted questions and random questions is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40% in addition to decreasing of the required assessing questions by 50% compared to using fixed questions.

Bayesian based adaptive question generation technique

Journal of Electrical Systems and Information Technology, 2014

In this paper we aim to estimate the student knowledge model in a probabilistic domain using auto... more In this paper we aim to estimate the student knowledge model in a probabilistic domain using automatic adaptively generated assessment questions. The student answers are used to estimate the actual student model. Updating and verification of the model are conducted based on the matching between the student's and model answers. Moreover, a comparative study between using the adaptive and random generated questions for updating the student model is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40% in addition to decreasing of the required assessing questions by 35%.

Bayesian based student knowledge modeling in intelligent tutoring systems

2012 6th IEEE International Conference on E-Learning in Industrial Electronics (ICELIE), 2012

ABSTRACT

New weighted BERT features and multi-CNN models to enhance the performance of MOOC posts classification

Neural Computing and Applications

Learning is an essential requirement for humans, and its means have evolved. Ten years ago, Massi... more Learning is an essential requirement for humans, and its means have evolved. Ten years ago, Massive Open Online Courses (MOOCs) were introduced, attracting many interests and learners. MOOCs provide forums for learners to interact with instructors and to express any problems they encounter in the educational process. However, MOOCs have a high dropout rate due to the difficulties of following up on learners' posts and identifying the urgent ones to react quickly. This research aims to assist instructors in automatically identifying urgent posts, making it easier to respond to such posts rapidly, increasing learner engagement, and improving course completion rate. In this paper, we propose a novel classification model for identifying urgent posts. The proposed model consists of four stages. In the first stage, the post-text is code-encoded and vectorized using a pre-trained BERT model. In the second stage, a novel feature aggregation model is proposed to reveal data-based relatio...

Utilizing Diagnosing Problems in a Probabilistic Domain to Build Student Models

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The student answers to questions requiring diagnosing skills are used to estimate the actual student model. Updating and verification of the model are conducted based on the matching between the student's and model answers. Two different approaches to updating are suggested, i) coarse and ii) refined model updating. Moreover, the effect of the order of which questions are presented to the student is investigated. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model. In addition, the accuracy of the algorithm is highly insensitive to the order of which the questions are presented, more so when using the refined model updating approach..

Question Generation for Adaptive Assessment for Student Knowledge Modeling in Probabilistic Domains

Abstract. In this paper a question generation approach for adaptive assessment is purposed to est... more Abstract. In this paper a question generation approach for adaptive assessment is purposed to estimate the student knowledge model in a probabilistic domain within an intelligent tutoring system. Assessing questions are generated adaptively according to the student knowledge based on two factors (i) the student misconceptions that are entailed in the student knowledge model, and (ii) the information gain maximizing. Updating and verification of the student model are conducted based on the matching between the student’s and model answers to assessing questions. Comparison between using the adapted questions and random questions is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40 % in addition to decreasing of the required assessing questions by 50 % compared to using fixed questions.

Addressing student misinterpretations of story problems in MAST

2017 Intl Conf on Advanced Control Circuits Systems (ACCS) Systems & 2017 Intl Conf on New Paradigms in Electronics & Information Technology (PEIT), 2017

Story problems are of ultimate importance of mathematics. This stems from the fact that they help... more Story problems are of ultimate importance of mathematics. This stems from the fact that they help improve various students' skills including reading the story problem, extracting the embedded mathematical information and the unknown quantity to compute, and applying the correct mathematical operators to solve the problem. Unfortunately, this type of problems may suffer from misinterpretation errors and errors due to overlooking some embedded information regardless of the proficiency of the students in mathematics. This paper introduces the Math Story Problem Tutor (MAST), a Web-based intelligent tutoring system of probability story problems. The focus of this paper is to explain how MAST deals with those problems using the Question Generation Module (QGM) and the Cognitive Module (CM). The QGM is able to generate story problems based on Natural Language Generation (NLG) techniques. This results in known semantic descriptions and linguistic structures of each story problem part. ...

Multi-level skills-based student modeling in an Arabic grammar tutor

2017 Intl Conf on Advanced Control Circuits Systems (ACCS) Systems & 2017 Intl Conf on New Paradigms in Electronics & Information Technology (PEIT), 2017

Language Tutoring Systems (LTSs) are computer-based tutoring systems that address linguistic skil... more Language Tutoring Systems (LTSs) are computer-based tutoring systems that address linguistic skills. Most LTSs rely on Natural Language Processing (NLP) tools for analyzing the student's answer to support him/her with appropriate feedback. In such systems, diagnosing the student errors is typically based on a large library of students' expected bugs. In addition, such systems (especially in case of the Arabic language) don't consider modeling of the student knowledge or assigning difficulty levels to the presented questions. Subsequently, such systems do not support individualization of their interactions to each student's needs and preferences. This paper presents the Arabic Grammar Tutor (AGTutor), which utilizes Constraint-Based Modeling (CBM) to model the domain eliminating the need for the bugs' library. Grammar rules are represented as a set of constraints that are categorized in terms of the different linguistic skills. Linguistic skills are classified int...

Iagnosing Problems in a P Robabilistic D Omain to B Uild S Tudent M Odels

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The student answers to questions requiring diagnosing skills are used to estimate the actual student model. Updating and verification of the model are conducted based on the matching between the student's and model answers. Two different approaches to updating are suggested, i) coarse and ii) refined model updating. Moreover, the effect of the order of which questions are presented to the student is investigated. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model. In addition, the accuracy of the algorithm is highly insensitive to the order of which the questions are presented, more so when using the refined model updating approach..

Question generation for adaptive assessment for student knowledge modeling in probabilistic domains

In this paper a question generation approach for adaptive assessment is purposed to estimate the ... more In this paper a question generation approach for adaptive assessment is purposed to estimate the student knowledge model in a probabilistic domain within an intelligent tutoring system. Assessing questions are generated adaptively according to the student knowledge based on two factors (i) the student misconceptions that are entailed in the student knowledge model, and (ii) the information gain maximizing. Updating and verification of the student model are conducted based on the matching between the student’s and model answers to assessing questions. Comparison between using the adapted questions and random questions is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40% in addition to decreasing of the required assessing questions by 50% compared to using fixed questions.

Inferring the Differential Student Model in a Probabilistic Domain Using Abduction inference in Bayesian networks

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The suggested algorithm aims to estimate the actual student model through the student answers to questions requiring diagnosing skills. Updating and verification of the model are conducted based on the matching between the student and model answers. Two different approaches to updating namely coarse and refined model are suggested. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model.

Student Modeling Using Educational Data Mining Techniques

2019 6th International Conference on Advanced Control Circuits and Systems (ACCS) & 2019 5th International Conference on New Paradigms in Electronics & information Technology (PEIT)

Educational Data Mining (EDM) is a research area which applies machine learning, data mining and ... more Educational Data Mining (EDM) is a research area which applies machine learning, data mining and statistical techniques to different types of data that come from educational settings. Student modeling is one of EDM applications that used to recommend or adapt the educational system resources. This paper explores the different educational systems and their characteristics. In addition, modeling of the student learning style, affective state, and prediction of the student performance are addressed. Profiling, grouping students and collaboration analysis are also explored.

Rule-based Cognitive Modeling and Model Tracing in a Math Story Problem Tutor

International Journal of Emerging Technologies in Learning (iJET)

Intelligent Tutoring Systems (ITSs) are intended to help in tutoring the students in specific dom... more Intelligent Tutoring Systems (ITSs) are intended to help in tutoring the students in specific domains typically by improving their problem solving skills. An important aspect of such ITSs is their ability to solve the generated problems in the same way that the student would in addition to interpreting the student actions to provide relevant feedback and help. Cognitive models that mimic the way knowledge is represented in human minds are excellent means toward achieving this goal. This paper discusses cognitive modelling in the MAth Story problem Tutor (MAST). MAST is a Web-based ITS that can generate probability story problems of different contexts, types and difficulty levels. The paper also discusses the model tracing approach of MAST to interpret the student actions in symbolizing the word problems and estimating the required probabilities to provide relevant feedback and help. A major contribution of the paper is in considering the symbolization of the probability word problem...

Bi-GRU Urgent Classification for MOOC Discussion Forums Based on BERT

IEEE Access

MOOC provides a forum for communication between students and teachers and is a platform for stude... more MOOC provides a forum for communication between students and teachers and is a platform for students to articulate their problems in the education process. Because of the large number of students and the small number of teachers, distinguishing posts that require rapid intervention is challenging. Therefore, there is a need to automatically classify the posts in the forum and distinguish urgent posts requiring a quick response. This classification is mainly based on the numerical representation of the text included in the students' posts. BERT is a model for representing words according to the context in which they are used. These context-dependent representations can capture many syntactic and semantic properties of words under diverse linguistic contexts. This paper aims to utilize such representation as a pre-trained embedding layer for a broader task, and then it is fine-tuned to define the urgent post. This embedding layer passes on the classification model consisting of a multi-layer bi-directional Gated Recurrent Unit (GRU). Also, different types of embedding layers have been experimented with other deep neural network structures for comparison. Despite the simplicity of the proposed structure, using BERT as an embedding layer achieves urgent posts classification with a weighted F-score of 91.9%, 91.0%, and 90.0% on the Stanford MOOC Posts dataset. Distinguishing urgent posts with high accuracy helps teachers prioritize their responses and answer learner questions promptly. Also, this helps reducing dropout rates and improving completion rates. INDEX TERMS BERT, embedding layer, gated recurrent unit, MOOC, urgent posts. NABILA A. KHODEIR received the M.A. and Ph.D. degrees from the Electronics and Com

Constraint-based and Fuzzy Logic Student Modeling for Arabic Grammar

International Journal of Computer Science and Information Technology

Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with lin... more Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with linguistic skills. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not consider the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different difficulty levels. Constraint-based student modeling (CBSM) technique is used as a short-term student model. CBSM is used to define in small grain level the different grammar skills through the defined skill structures. The main contribution of this paper is the hierarchal representation of the system&#39;s basic grammar skills as domain knowledge. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. In addition, satisfying constraints and the number of trails the student takes for answering each question and fuzzy logic decision system are used to determine the student learning level for each lesson as a long-term model. The results of the evaluation showed the system&#39;s effectiveness in learning in addition to the satisfaction of students and teachers with its features and abilities.

Constraint-based Student Modelling in Probability Story Problems with Scaffolding Techniques

International Journal of Emerging Technologies in Learning (iJET)

Constraint-based student modelling (CBM) is an important technique employed in intelligent tutori... more Constraint-based student modelling (CBM) is an important technique employed in intelligent tutoring systems to model student knowledge to provide relevant assistance. This paper introduces the Math Story Problem Tutor (MAST), a Web-based intelligent tutoring system for probability story problems, which is able to generate problems of different contexts, types and difficulty levels for self-paced learning. Constraints in MAST are specified at a low-level of granularity to allow fine-grained diagnosis of the student error. Furthermore, MAST extends CBM to address errors due to misunderstanding of the narrative story. It can locate and highlight keywords that may have been overlooked or misunderstood leading to an error. This is achieved by utilizing the role of sentences and keywords that are defined through the Natural Language Generation (NLG) methods deployed in the story problem generation. MAST also integrates CBM with scaffolding questions and feedback to provide various forms o...

Generating story problems via controlled parameters in a web-based intelligent tutoring system

International Journal of Information and Learning Technology

Detection and Handling of Different Types of Concept Drift in News Recommendation Systems

International Journal of Computer Science and Information Technology

To address the increase in volume of data streams online users interact with, there are a growing... more To address the increase in volume of data streams online users interact with, there are a growing number of tools and models to summarize and extract information. These tools use prediction models to personalize and extract useful information. However, data streams are highly prone to the phenomena of concept drift, in which the data distribution changes over time. To maintain the performance level of these models, models should adapt to handle the existence of adrift. In this work, we present the Incremental Knowledge Concept Drift (IKCD) algorithm, an adaptive unsupervised learning algorithm for recommendation systems in news data stream. Data modelling in IKCD uses k-means clustering to determine the occurrence of a drift while avoiding the dependency on the availability of data labels. Once a drift is detected, new retraining data is composed from the old and new concept. IKCD is tested using synthetic and real benchmark datasets from various domains, which demonstrate the different drift types and with different rate of change. Experimental results illustrate an enhanced performance with respect to (a) reducing model sensitivity to noise, (b) reducing model rebuilding frequency up to 50% in case of re-occurring drift and (c) increasing accuracy of the model by about 10% with respect the accuracy of confidence distribution batch detection algorithm.

Graphical Representation in Tutoring Systems

International Journal of Computer Science and Information Technology

Visual representation and organization of the knowledge have been utilized in different ways in t... more Visual representation and organization of the knowledge have been utilized in different ways in tutoring systems to upgrade their usefulness. This paper concentrates on the usage of various graphical formalisms, for example, the conceptual graph, ontology, and concept map in tutoring systems. The paper addresses what is way of the utilization of every formalism and the offering of the potential outcomes to assist the student in education systems.

Inferring the Differential Student Model in a Probabilistic Domain Using Abduction inference in Bayesian networks

In this paper we aim to estimate the differential student knowledge model in a probabilistic doma... more In this paper we aim to estimate the differential student knowledge model in a probabilistic domain within an intelligent tutoring system. The suggested algorithm aims to estimate the actual student model through the student answers to questions requiring diagnosing skills. Updating and verification of the model are conducted based on the matching between the student and model answers. Two different approaches to updating namely coarse and refined model are suggested. Results suggest that the refined model, although takes more computational resources, provides a slightly better approximation of the student model.

Question generation for adaptive assessment for student knowledge modeling in probabilistic domains

In this paper a question generation approach for adaptive assessment is purposed to estimate the ... more In this paper a question generation approach for adaptive assessment is purposed to estimate the student knowledge model in a probabilistic domain within an intelligent tutoring system. Assessing questions are generated adaptively according to the student knowledge based on two factors (i) the student misconceptions that are entailed in the student knowledge model, and (ii) the information gain maximizing. Updating and verification of the student model are conducted based on the matching between the student's and model answers to assessing questions. Comparison between using the adapted questions and random questions is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40% in addition to decreasing of the required assessing questions by 50% compared to using fixed questions.

Bayesian based adaptive question generation technique

Journal of Electrical Systems and Information Technology, 2014

In this paper we aim to estimate the student knowledge model in a probabilistic domain using auto... more In this paper we aim to estimate the student knowledge model in a probabilistic domain using automatic adaptively generated assessment questions. The student answers are used to estimate the actual student model. Updating and verification of the model are conducted based on the matching between the student's and model answers. Moreover, a comparative study between using the adaptive and random generated questions for updating the student model is investigated. Results suggest that utilizing adapted generated questions increases the approximation accuracy of the student model by 40% in addition to decreasing of the required assessing questions by 35%.

Bayesian based student knowledge modeling in intelligent tutoring systems

2012 6th IEEE International Conference on E-Learning in Industrial Electronics (ICELIE), 2012

ABSTRACT