Maedeh Mosharraf | University of Tehran (original) (raw)

Papers by Maedeh Mosharraf

ABSTRACT Providing adaptivity for eLearning systems may be accomplished through incorporating lea... more ABSTRACT Providing adaptivity for eLearning systems may be accomplished through incorporating learning style, which may be supposed non-stable characteristic in case of children. This paper presents a hybrid model for initiating and updating personality type of children in eLearning systems. A modified MMTIC (Murphy-Meisgeier Type Indicator for Children) questionnaire has been applied in start–up phase of system to recognize children personality type. This questionnaire is made based on MBTI (Myers-Briggs Type Indicator). Patterns of children behaviors are extracted by monitoring the details of their interaction with system. Using clustering algorithms and sequential pattern mining, system updates the personality type of children. The proposed approach is used in 81 fourth-grade children in elementary school. Delivery results suggest that this method provides good precision in diagnosing children personality type and can be an appropriate solution for non-stability in children learning style.

ABSTRACT Web rapid development has provided new learning environments, bringing online education ... more ABSTRACT Web rapid development has provided new learning environments, bringing online education as a necessity in many sectors of the society. In such an environment, selecting supervisor is a critical decision that graduate students as well as professors are involved with, which could benefit from e-learning tools. In this paper we have proposed a solution for student-supervisor assignment based on Genetic Algorithm (GA), so that the task of student-supervisor assignment is mapped to an optimization problem that could be solved with GA approaches. In our GA approach, search space is the set of all bipartite graphs that are transformed to arrays of integer numbers as chromosomes representations. Assigning supervisors to students requires some information about professors and students. For this purpose, we have profiled students and professors through deriving their decision parameters and other required information, using data obtained from various sources including Learning Management System (LMS), Community of Practice (CoP), as well as our question-answering user interface. This system is implemented at the University of Tehran, using different profiles of students and professors. Delivery results suggest that our new method provides good precision in student-supervisor compatibility.

IEEE Transactions on Learning Technologies, Apr 1, 2020

Rapid development of Open Educational Resources (OER) is often motivated by a new educational par... more Rapid development of Open Educational Resources (OER) is often motivated by a new educational paradigm. This paradigm tends to cover current challenges such as reusing, goaloriented remixing, revising, and redistributing OER. This paper proposes a system to automatically remix, which is a step towards automatic course generation. This system uses an Agent-Based Modeling (ABM) approach to profile OER and simulate the process of selecting and linking the appropriate ones. Each resource profile provides us with metadata that shows its domain and is completed using an appropriate ontology before agents' interactions. ABM enables cooperation between OER to satisfy requirements of the input syllabus. Using the interaction ability, the most compatible agents, which cover the concepts of the input syllabus, can be linked. The efficiency of the proposed method is evaluated through applying the implemented system on two datasets: ARIADNE and SlideShare. In our experimental results on OER related to the domain of eLearning we report on the system precision and user satisfaction. Our approach is generic; it can be used with any OER repository and any content management system with free reuse and remix licenses.

Gamified systems benefit from various gamification-elements to motivate users and encourage them ... more Gamified systems benefit from various gamification-elements to motivate users and encourage them to persist in their quests towards a goal. This paper proposes a categorization of gamification-elements and learners' motivation type to enrich a learning management system with the advantages of personalization and gamification. This categorization uses the learners' motivation type to assign gamification-elements in learning environments. To find out the probable relations between gamification-elements and learners' motivation type, a field-research is done to measure learners' motivation along with their interests in gamification-elements. Based on the results of this survey, all the gamification-elements are categorized according to related motivation types, which form our proposed categorization. To investigate the effects of this personalization approach, a gamified learning management system is prepared. Our implemented system is evaluated in Technical English course at University of Tehran. Our experimental results on the average participation rate show the effectiveness of the personalization approach on the learners' motivation. Based on the paper findings, we suggest an integrated categorization of gamification-elements and learners' motivation type, which can further enhance the learners' motivation through personalization.

Knowledge Management & E-Learning: An International Journal, Mar 15, 2013

Due to paramount importance of knowledge, lifelong learning, globalization, and mobility; eLearni... more Due to paramount importance of knowledge, lifelong learning, globalization, and mobility; eLearning as an information technology application has faced rapid growth in recent years. Disseminated war for talent enforces providers of eLearning products to identify technological gaps of learning and provide personalized services for customers of this industry. As we may know, designing customer-centered environments and managing enduser relations are the most effective elements in the market gain, due to the importance of customer satisfaction. The special features of eLearning systems with respect to their centers and users make them appropriate realms for applying a Customer Relationship Management (CRM) methodology. Learner Relationship Management (LRM), which is more specialized than CRM in eLearning context, plays a significant role in improving quality of services, enhancing learners' satisfaction and retention, keeping them, and recruitment new users. LRM provides an integrated infrastructure for eLearning systems and helps them to analyse learners' capabilities and find the best match to overcome the turbulent environment and tight competition. Also, by improving the service quality and enhancing teaching and learning flows, LRM offers personalized instructions to learners.

Knowledge Management & E-Learning: An International Journal, Mar 15, 2016

Open Educational Resources (OERs) have gained increased attention for their potential to provide ... more Open Educational Resources (OERs) have gained increased attention for their potential to provide equitable and accessible educational facilities for people worldwide. Obviating demographic, economic, and geographic educational boundaries can be the OERs slogan. Realization of this promise is an inevitable target of eLearning, thus offering education new challenges. In this observation paper, we express OERs altruistic and idealistic reasons as well as their opportunities and advantages for three groups of eLearning stakeholders, namely learners, teachers, and educational institutions. Also, this paper addresses open questions such as what are the current limitations and challenges of developing and distributing OERs in the fast changing global educational environment.

Semantic web technology can influence the next generation of eLearning systems and applications. ... more Semantic web technology can influence the next generation of eLearning systems and applications. Ontology as a major component of semantic web can be used in creating metadata for eLearning resources to improve adaptive eLearning systems. This paper presents an approach to automatically enrich eLearning domain ontology based on the integration of graph clustering techniques and external knowledge resources. The semantic similarity of concepts which is measured using the words hierarchy of WordNet combined with relations of concepts extracted from the Wikipedia graph is applied to link the new eLearning concepts to the domain ontology. The generated ontology as an integrated knowledge of eLearning domain can be used to model educational activities and to build, organize, and update specific learning resources. Explicit representation of eLearning concepts leads to uniform tagging of these resources and improves the results of web services in this domain.

What is preferred by adults and what works for them will not necessarily be appropriate for child... more What is preferred by adults and what works for them will not necessarily be appropriate for children. Nowadays, most things designed and created in the world still have not been designed for children as a user group. eLearning systems, as an important human achievement in the age of technology, exhibit a similar situation to other experiences. Much research and many innovations in these systems are accomplished for young people in higher educational environments. In this paper, we design and implement a learning management system (LMS) for students in elementary school, which leads to their meaningful learning enhancement. Decreasing competitive pressures and fear of failure through changing assessment process and improving motivation of learning through sending some informative and positive feedback are the other features of our LMS. Pedagogical constraints and children's preferences are the foundations of our system that is implemented based on MVC pattern. This LMS has successfully passed primary tests and started to be used in a real elementary school; however, its development is still ongoing .

Aslib proceedings, Feb 16, 2022

PurposeThe purpose of the paper is to propose a semantic model for describing open source softwar... more PurposeThe purpose of the paper is to propose a semantic model for describing open source software (OSS) in a machine–human understandable format. The model is extracted to support source code reusing and revising as the two primary targets of OSS through a systematic review of related documents.Design/methodology/approachConducting a systematic review, all the software reusing criteria are identified and introduced to the web of data by an ontology for OSS (O4OSS). The software semantic model introduced in this paper explores OSS through triple expressions in which the O4OSS properties are predicates.FindingsThis model improves the quality of web data by describing software in a structured machine–human readable profile, which is linked to the related data that was previously published on the web. Evaluating the OSS semantic model is accomplished through comparing it with previous approaches, comparing the software structured metadata with profile index of software in some well-known repositories, calculating the software retrieval rank and surveying domain experts.Originality/valueConsidering context-specific information and authority levels, the proposed software model would be applicable to any open and close software. Using this model to publish software provides an infrastructure of connected meaningful data and helps developers overcome some specific challenges. By navigating software data, many questions which can be answered only through reading multiple documents can be automatically responded on the web of data.

2022 27th International Computer Conference, Computer Society of Iran (CSICC)

Aslib Journal of Information Management, 2022

Purpose The purpose of the paper is to propose a semantic model for describing open source softwa... more Purpose The purpose of the paper is to propose a semantic model for describing open source software (OSS) in a machine–human understandable format. The model is extracted to support source code reusing and revising as the two primary targets of OSS through a systematic review of related documents. Design/methodology/approach Conducting a systematic review, all the software reusing criteria are identified and introduced to the web of data by an ontology for OSS (O4OSS). The software semantic model introduced in this paper explores OSS through triple expressions in which the O4OSS properties are predicates. Findings This model improves the quality of web data by describing software in a structured machine–human readable profile, which is linked to the related data that was previously published on the web. Evaluating the OSS semantic model is accomplished through comparing it with previous approaches, comparing the software structured metadata with profile index of software in some wel...

Knowledge Management & E-Learning: An International Journal, 2013

Due to paramount importance of knowledge, life-long learning, globalization, and mobility; eLearn... more Due to paramount importance of knowledge, life-long learning, globalization, and mobility; eLearning as an information technology application has faced rapid growth in recent years. Disseminated war for talent enforces providers of eLearning products to identify technological gaps of learning and provide personalized services for customers of this industry. As we may know, designing customer-centered environments and managing end-user relations are the most effective elements in the market gain, due to the importance of customer satisfaction. The special features of eLearning systems with respect to their centers and users make them appropriate realms for applying a Customer Relationship Management (CRM) methodology. Learner Relationship Management (LRM), which is more specialized than CRM in eLearning context, plays a significant role in improving quality of services, enhancing learners' satisfaction and retention, keeping them, and recruitment new users. LRM provides an integr...

Qualitative development of eLearning environments through a learner relationship management metho... more Qualitative development of eLearning environments through a learner relationship management methodology

Knowledge representation in the form of a concept map can be a good idea to categorize domain ter... more Knowledge representation in the form of a concept map can be a good idea to categorize domain terms and their relations and help to generate ontology. Supplementing detail information to and pruning useless data from the concept map, which likes a skeleton in evolving ontology, can be semantically accomplished using the domain knowledge. In this paper, we propose a method using structural knowledge resources as well as tacit knowledge of experts to generate the ontology of eLearning domain. The concept map of eLearning is manually improved and finally verified using the group of eLearning experts. In order to enrich the ontology with merging into upcoming terms, the paper proposed an automatic method based on two external knowledge sources, Wikipedia and WordNet. The semantic similarity of concepts which is measured using the words hierarchy of WordNet combined with relations of concepts extracted from the Wikipedia graph is applied to link the new eLearning concepts to the domain o...

Driven by the success of linked data, interlinked web of data is a best infrastructure for distri... more Driven by the success of linked data, interlinked web of data is a best infrastructure for distributing open educational resources (OERs). Hand in hand with this structure, immense technological challenges are arising in every phase of their publishing, maintaining, discovering, and accessing. Utilizing OERs licenses and principals of linked data, this paper proposes a federated search engine to retrieve OERs published on web of data. Transforming natural language queries to the SPARQL form using a desirable interface and several preprepared queries, parsing each query and broadcasting the subqueries to several appropriate open repositories, merging retrieved results, and presenting to users in an appropriate user friendly interface are processes of this system. It has successfully passed primary tests and started to be used in a technology enhanced learning laboratory; however, its development is still on-going.

Interdisciplinary Journal of e-Skills and Lifelong Learning

Personalization is one of the most expected features in the current educational systems. User mod... more Personalization is one of the most expected features in the current educational systems. User modeling is supposed to be the first stage of this process, which may incorporate learning style as an important part of the model. Learning style, which is a non-stable characteristic in the case of children, differentiates students in learning preferences. This paper identifies a new hybrid method to initiate and update the information of children’s learning style in an educational system. At the start-up phase, children’s learning style information is gathered through the modified Murphy-Meisgeier Type Indicator for Children (MMTIC) questionnaire, which is based on the well-known Myers-Briggs Type Indicator (MBTI). This primary information will be tuned by tracking children’s behaviors during the learning process. Analytical data mining helped us to cluster these behaviors and find their patterns. The proposed method was applied on 81 fourth grade children in elementary school. Deliverin...

IEEE Transactions on Learning Technologies

Rapid development of open educational resources (OER) is often motivated by a new educational par... more Rapid development of open educational resources (OER) is often motivated by a new educational paradigm. This paradigm tends to address current challenges such as reusing, goal-oriented remixing, revising, and redistributing OER. This paper proposes a system to automatically remix, which is a step towards automatic course generation. This system uses an agent-based modeling (ABM) approach to profile OER and simulate the process of selecting and linking the appropriate ones. Each resource profile provides us with metadata that shows its domain and is completed using an appropriate ontology before agents’ interactions. ABM enables cooperation between OER to satisfy requirements of the input syllabus. Using the interaction ability, the most compatible agents, which cover the concepts of the input syllabus, can be linked. The efficiency of the proposed method is evaluated through applying the implemented system on two datasets: ARIADNE and SlideShare. In our experimental results on OER related to the domain of e-learning, we report on the system precision and user satisfaction. Our approach is generic; it can be used with any OER repository and any content management system with a free reuse and remix license.

Knowledge Management & E-Learning: An International Journal