Fig 1 - uploaded by Lilia Cheniti-Belcadhi
Content may be subject to copyright.
![Architecture of assessment framework To enable personalized assessment support as described in the scenario above, meta-information about the course, the learning and assessment resources and about the learners themselves is required. The Assessment framework makes use of learning standards LOM [9] and Dublin Core [4] to support interoperability. It is also designed to be](profile/Lilia-Cheniti-Belcadhi/publication/221424023/figure/fig1/AS:393980085850114@1470943580347/Architecture-of-assessment-framework-To-enable-personalized-assessment-support-as.png)
Architecture of assessment framework To enable personalized assessment support as described in the scenario above, meta-information about the course, the learning and assessment resources and about the learners themselves is required. The Assessment framework makes use of learning standards LOM [9] and Dublin Core [4] to support interoperability. It is also designed to be
Source publication
This paper describes the design, development and qualitative evaluation of a Web-based personalized assessment service of an object-oriented programming course at the University of Sousse. The assessment service was integrated in the personal reader software, of the University of Hannover and was designed to select specific questions based on the p...
Similar publications
Managing computer programming assignments and evaluating submitted programs is an important role for educators in computer science. This paper introduces neoESPA, an automatic source code evaluation system for programming assignments. The neoESPA supports the overall procedure for evaluating source codes submitted by students. It also provides the...
Citations
... However, it would not take into account multi-peer piloting for learning in a collaborative situation, and the question of the learning process is lightly addressed and even less that of prerequisites. A personalized assessment system using Web services and allowing the selection and presentation of learning and assessment resources adapted to the learner's level of knowledge was designed by Lilia ChenitiBelcadhi et al [7]. This work aimed to personalize assessments through web and mobile platforms with a view to more adapted learning. ...
The supply and demand for training, having undergone a revolution, involves information and communication technologies including artificial intelligence. However, following training adapted to the evolution of the learners skills remains a challenge. Our study aims to provide a solution aimed at promoting a personalized online learning process. Our approach consisted of choosing a decision tree algorithm following a comparative study and developing an architecture based upstream on the evaluation of the learners knowledge. This architecture directs the learner, according to their performance, towards educational resources (documents, courses, sections, videos, etc.) or learning devices, in an iterative and incremental manner until the end of the learning process. The results obtained reside in the proposed model based on the gradient boosting algorithm adapted to the personalization of human learning. This model takes into account three essential components driven by artificial intelligence and covers an entire personalized learning process from checking prerequisites to the end of successful learning.
... The impact of choice of the evaluation type is very important and can have direct consequences on how to structure the course content and individual learning. In literature, there are several articles about this topic, but often there is a tendency to translate classical educational materials into distant learning without any transformation [2][3][4][5]. As a result, evaluation is not considered as an integral part of the learning activity and one of its important components, but it is often isolated from it. ...
It is no coincidence, that the distance learning platforms are increasingly used in universities, colleges and companies offering effective and continuous training of their employees without constraint of time and space. The effectiveness of such a learning system depends mainly on the degree of information assimilated by the learner at the end of training. In this article, we focus on the conception and implementation of a system for measuring competence for the computer sciences. This system uses the model of the item response theory. The results provided by this system are presented to the student, as a dashboard. They will allow the teacher or tutor to have the necessary elements to monitor their learning by identifying the causes blocking and checking its achievements. This system can also help to improve the recruitment process of companies using it in a near-selection process of candidates for jobs.
... The impact of choice of the evaluation type is very important and can have direct consequences on how to structure the course content and individual learning. In literature, there are several articles about this topic, but often there is a tendency to translate classical educational materials into distant learning without any transformation [2][3][4][5]. As a result, evaluation is not considered as an integral part of the learning activity and one of its important components, but it is often isolated from it. ...
— the distance learning platforms are increasingly used in universities, colleges and companies seeking effective and continuous training of their employees without constraint of time and space. The effectiveness of such a learning system depends mainly on the evidence that students actually learn what it is supposed to learn. In this article, we focus on the implementation of a system for measuring competence for the computer sciences. This system uses the model of the theory of the response to the selected item. The results provided by this system are presented to the student, as a dashboard. They will allow the teacher or tutor to have the necessary elements to monitor their learning by identifying the causes blocking and checking its achievements. This system can also help to improve the recruitment process of companies using it in a near-selection process of candidates for jobs.
... The impact of choice of the evaluation type is very important and can have direct consequences on how to structure the course content and individual learning. In literature, there are several articles about this topic, but often there is a tendency to translate classical educational materials into distant learning without any transformation [2][3][4][5]. As a result, evaluation is not considered as an integral part of the learning activity and one of its important components, but it is often isolated from it. ...
... For educational resources, the broad sense, including learning objects, learners, academic records, school management, educational materials and other related information, including courseware, papers, teaching materials, case studies, literature and teaching involved in the learning objects in the narrow sense [2]. Grid environment, there are a variety of dynamic educational resources, they are geographically dispersed, but also can dynamically join or leave the different regional management organizations. ...
The distance learning platforms are increasingly used in universities, colleges and
companies seeking effective and continuous training of their employees without constraint of time
and space. The effectiveness of such a learning system depends mainly on the degree of information
assimilated by the learner at the end of training. In this article, we focus on the implementation of a
system for measuring competence for computer sciences. This system uses the model of item
response theory. The results provided by this system are presented to the student, as a dashboard.
They will allow the teacher or tutor to have the necessary elements to monitor their learning by
identifying the causes blocking and checking its achievements. This system can also help to improve
the recruitment process of companies using it in a near-selection process of candidates for jobs.
... Our current research goal is to keep working within IMS-LD frameworks enhanced with instructional design intelligent paradigms. We aim at integrating into the proposed model our previous work on assessment [7] as well. ...
Research in e-learning has shifted in recent years its emphasis from almost purely technical aspects to pedagogy oriented interest. This shift is an indication of a positive trend which testifies to the preoccupations of teachers and educators. Nevertheless, and despite declarations of good intentions, more research effort should be made to attract more teachers towards the use of learning technologies. In our work, we are in favor of developing pedagogical approaches. However, since the field of learning technologies (LTs) has made significant progress in recent years (LOM, DC, EML, LD), we have to support this trend. This paper describes our approach and some of our findings out of several experiments that we have conducted. We also give the architectural design of an e-learning environment that is being deployed, whereby advances in LTs information models and tools such as LD and MOT+LD are utilized.
... It also requires advanced approaches to assessment which are appropriate to distributed and open e-learning environments. In those environments, indeed, personalization plays an important role as the information derived from both assessment functionalities and learners' interaction with the environment enables a better selection and generation of learning and assessment strategies" (Cheniti-Belcadhi, Henze, and Braham, 2006). ...
Learning object repositories, eLearning systems, and other data management systems have built personalization for their learners through intelligent agents, user profiling (personality, role, needs, histories, “interest” measures, live online behaviors, and learning styles metrics), user-directed learning, social networking, and other strategies. “Online ‘Live Personalization’ of Learning and Implications for Learning Object Repositories and Automated eLearning” will explore what F2F (face-to-face) and online instructors bring to their teaching that personalizes the learning for unique individual learners. Finally, some ideas for personalizing learning object (and data) repositories and automated eLearning systems will be explored in the light of human-mediated F2F and online instructor customization strategies.
In the domain of e-learning and e-assessment, many different components are used to realise particular system features. Even for similar features using similar components there are different ways of realisation in terms of connection and integration. This paper presents results from literature review and design-space explorations that result in a catalogue of components and an overview on design alternatives.
Although every educational institution has a code of academic honesty, they still encounter incidents of plagiarism. These are difficult and time-consuming to detect and deal with. This paper explores the use of personalized assessments with the goal of reducing incidents of plagiarism, proposing a personalized assessment software framework through which each student receives a unique problem set. The framework not only auto-generates the problem set but also auto-marks the solutions when submitted. The experience of using this framework is discussed, from the perspective of both students and staff, particularly with respect to its ability to mitigate plagiarism. A comparison of personalized and traditional assignments in the same class confirms that the former had far fewer observed plagiarism incidents. Although personalized assessment may not be cost-effective in all courses (such as language courses), it still can be effective in areas such as mathematics, engineering, science, and computing. This paper concludes that personalized assessment is a promising approach to counter plagiarism.
The growing demand for user experiences on the web addressing individual needs, is driving the mainstream adoption of personalisation technologies across broad fields of interests. Adaptive Web Systems (AWSs) have traditionally attempted to deliver dynamically adapted and personalised experiences to users, through the sequencing and adaptation of recomposable content. The adaptivity offered by these systems however, can be restricted by a lack of sufficient resources, which represents a major obstacle to their widespread adoption. So as to serve the largest possible audience, common sense encouraged the labor intensive and limited production of such resources, to target the common and predictable needs of users in higher demand, by delivering one-size-fits-all recomposable material, of type and quantity predetermined in advance. However, as the number of internet users grows, so does the diversity of user information needs. As a result, the need for even greater volumes of resources, covering larger ranges of increasingly unpredictable and specific user needs, rises too. Existing approaches incorporating open web corpus content within these platforms have so far achieved very limited success, mostly due to their inability to supply resources in a form meeting specific content requirements of AWSs. Within this context, the ability to supply adequate content to AWSs could only be sustained if such resources were produced in large volumes, only as needs arose. Such a content delivery service would remove the necessity for any content type/quantity predictions to occur, which in turn would enable the delivery of more scalable personalisation experiences, covering a wider range of needs.
The primary contribution of this thesis therefore consists of an innovative approach to open web corpus reuse and incorporation within AWSs, named Slicepedia. Through the identification and development of dynamic means of open web content harvesting, customisation and delivery, a fully-automated tool-chain service can be made, which delivers recomposable open web corpus resources, as right fitted packages to independent AWSs. This approach differs significantly from those used by existing AWSs, as it enables the on demand reuse of open web corpus content, without any pre-determined conditions and based upon a variety of possible AWS content requirement combinations, undetermined in advance. In order to evaluate this research, a series of user-trials and component analysis are presented, which provide confidence in the ability of this service to deliver open web corpus resources to AWSs as customised packages, with a suitability similar to content purposely produced for such systems and with minimal loss in original quality. The analysis also provides confidence that the on demand customisation, delivery and reuse of open web corpus resources within AWSs is possible and that such a service could support the widespread adoption of more scalable AWSs.
