In our previous works, we presented Logic-Muse as an Intelligent Tutoring System that helps learners improve logical reasoning skills in multiple contexts. Logic-Muse components were validated and argued by experts throughout the designing process (ITS researchers, logicians, and reasoning psychologists). A catalog of reasoning errors (syntactic and semantic) has been established, in addition to an explicit representation of semantic knowledge and the structures and meta-structures underlying conditional reasoning. A Bayesian network with expert validation has been developed and used in a Bayesian Knowledge Tracing (BKT) process that allows the inference of the learner skills. This paper presents an evaluation of the learner-model components in Logic-Muse (a bayesian learner model). We conducted a study and collected data from nearly 300 students who processed 48 reasoning activities. These data were used to develop a psychometric model for initializing the learner's model and validating the structure of the initial Bayesian network. We have also developed a neural architecture on which a model was trained to support a deep knowledge tracing (DKT) process. The proposed neural architecture improves the initial version of DKT by allowing the integration of expert knowledge (through the Bayesian Expert Validation Network) and allowing better generalization of knowledge with few samples. The results show a significant improvement in the predictive power of the learner model. The analysis of the results of the psychometric model also illustrates an excellent potential for improving the Bayesian network's structure and the learner model's initialization process.

This paper presents a simple and intuitive technique to accelerate the convergence of first-order optimization algorithms. The proposed solution modifies the update rule, based on the variation of the direction of the gradient and the previous step taken during training. Results after tests show that the technique has the potential to significantly improve the performance of existing first-order optimization algorithms.

We present a serious game designed to help players/learners develop socio-moral reasoning (SMR) maturity. It is based on an existing computerized task that was converted into a game to improve the motivation of learners. The learner model is computed using a hybrid deep learning architecture, and adaptation rules are provided by both human experts and machine learning techniques. We conducted some experiments with two versions of the game (the initial version and the adaptive version with AI-Based learner modeling). The results show that the adaptive version provides significant better results in terms of learning gain.

Deep Knowledge Tracing (DKT), along with other machine learning approaches, are biased toward data used during the training step. Thus, for problems where we have few amounts of data for training, the generalization power will be low, the models will tend to give good results on classes containing many examples and poor results on those with few examples. Theses problems are frequent in educational data where for example, there are skills that are very difficult (floor) or very easy to master (ceiling). There will be less data on students that correctly answered questions related to difficult knowledge and that incorrectly answered questions related to knowledge easy to master. In that case, the DKT is unable to correctly predict the student's answers to questions associated with those skills. To improve the DKT, we penalize the model using a 'cost-sensitive' technique. To overcome the problem of the few amounts of data, we propose a hybrid model combining the DKT and expert knowledge. Thus, the DKT is combined with a Bayesian Network (built from domain experts) by using the attention mechanism. The resulting model can accurately track knowledge of students in Logic-Muse Intelligent Tutoring System (ITS), compared to the BKT and the original DKT.

Deep learning has been successfully applied to many tasks such as image classification, feature learning, Text classification (sentiments analysis or opinion mining) etc. However, little research has focused on extracting polarity of sentiments expressed in text using a multimodal architecture. In other words, no researches take in consideration the multimodal nature of human behaviors before classifying sentiments. The representation of a person (also call User Modeling in some domains such as Intelligent Tutoring Systems) is an important feature to take in consideration if one wants to extract subjective information such as the polarity of sentiments expressed by the person. To design an effective representation of a user, it is important to consider all sources of data informing about its current state. We present a usersensitive deep multimodal architecture which takes advantage of deep learning and user data to extract a rich latent representation of a user. This rich latent representation mainly helps in text classification tasks. The architecture consists of the combination of a Long Short-Term Memory (LSTM), LSTM-Auto-Encoder, Convolutional Neural Networks and multiple Deep Neural Networks, in order to support the multimodality of data. The resulting model has been tested on a public multimodal dataset and is able to achieve best results compared to state-of-the-art algorithms for a similar task: detection of opinion polarity. The results suggest that the latent representation learnt from multimodal data helps in the discrimination of polarity of opinion.

Prediction of emotions is important for understanding human be-havior and modeling users in learning environments. In this paper,we present a deep multi-modal architecture for emotions predic-tion, which takes advantage of deep learning, user multimodal dataand the hierarchy of human memory. The architecture consists ofthe combination of Long Short-Term memory (LSTMs). One of thenovelty of our approach is that, we enhance the LSTM with anexplicit memory since in brain studies, the memory is often dividedinto two further main types: explicit (or declarative) memory andimplicit (or procedural) memory, the last one being the main pur-pose of LSTMs architectures. The resulting model has been testedon a public multi-modal dataset.

Autism spectrum disorder (ASD) is a neurological disorder affecting the way in which the brain processes information. It can affect all aspects of a person’s development. Autism is characterized by impairments in learning and communication, in the social interaction, imaginative ability as well as in repetitive and restricted patterns of behavior (Diagnostic and statistical manual of mental disorders: DSM-IV [ 12 ]). This research contributes to the advancement of intelligent tutoring systems by proposing a computational model in the field of specialized education in order to overcome the lack of individualized intervention, such as in the specialized education of individuals with autism. The affective intelligent tutoring system ISLA is an adaptive application evolving along with the learner’s needs. ISLA is unique and its contribution entails the model of accompaniment to help autistic children manage their emotions by analyzing the learning trace and considering the student’s current performance to respond accordingly to it during a mathematical learning situation such as addition.

In this paper we present a participatory approach to design Logic-Muse, an Intelligent Tutoring System that helps learners develop reasoning skills in multiple contexts (situations). The study was conducted jointly with the active participation of experts in the field of logic and the psychology of reasoning. An explicit catalogue of systematic errors in classical logic is built, followed by an explicit representation and encoding of the semantic knowledge behind reasoning as well as reasoning procedural structures and meta-structures. Logic-Muse innovates through its design rationale, which leads to strong structures on which learning is based. It also innovates with the projection of reasoning skills in a variety of well-defined classes of situations to ensure an absolute mastery of reasoning skills regardless of the content effect.

Along their lif-cycle, Ontologies typically undergo a number of structural operations that might deplete their structural quality. Ontology restructuring is a process of improving that quality by reconsidering the way the knowledge is spread across the class and property hierarchies. This often leads to the discovery of new abstractions whose relevance to the ontology must be assessed. We address the relevance assessment within a context where it is crucial: Our restructuring method performs a enhanced concept analysis on the initial ontology that outputs all abstractions of a predefined language. Thus, the key step is the selection of the abstractions to include into the restructured ontology. We propose a set of relevance metrics and a rule-based algorithm for combining them into a single filtering criterion. Their effectiveness is evaluated using a collection of ontologies that have been analyzed beforehand to provide ground truth.

Sequential rule mining is an important data mining problem with multiple applications. An important limitation of algorithms for mining sequential rules common to multiple sequences is that rules are very specific and therefore many similar rules may represent the same situation. This can cause three major problems: (1) similar rules can be rated quite differently, (2) rules may not be found because they are individually considered uninteresting, and (3) rules that are too specific are less likely to be used for making predictions. To address these issues, we explore the idea of mining “partially-ordered sequential rules” (POSR), a more general form of sequential rules such that items in the antecedent and the consequent of each rule are unordered. To mine POSR, we propose the RuleGrowth algorithm, which is efficient and easily extendable. In particular, we present an extension (TRuleGrowth) that accepts a sliding-window constraint to find rules occurring within a maximum amount of time. A performance study with four real-life datasets show that RuleGrowth and TRuleGrowth have excellent performance and scalability compared to baseline algorithms and that the number of rules discovered can be several orders of magnitude smaller when the sliding-window constraint is applied. Furthermore, we also report results from a real application showing that POSR can provide a much higher prediction accuracy than regular sequential rules for sequence prediction.

Ontology is becoming the key knowledge capture structure in many domains. It plays a very important role in the area of semantic web and is widely used in multiple fields including Intelligent Tutoring Systems (ITS) and e-Learning. Ontologies are intensively used in domain knowledge modeling in specific areas which can evolve. However, current tools used to implement ontologies fail to provide functions to adequately ensure their evolution. To deal with this issue, we have developed an ontology evolution management system named «MS-ONTO», founded on a formal description of evolution operators. MS-ONTO allows the preservation of both the internal and external integrity constraints during the ontology evolution: the external integrity meaning the preservation of its usage while internal integrity means its conformity to the constraints (implicit or explicit) related to the ontology model itself. MS-ONTO should be integrated as a plug-in in existing ontology editors such as NeOn Toolkit and Protege.

In this article, we propose the Conscious-Emotional Learning Tutoring System technology, a biologically plausible cognitive agent based on human brain functions. This agent is capable of learning and remembering events and any related information such as corresponding procedures, stimuli and their emotional valences. In our model, emotions play a role in the encoding and remembering of events. This allows the agent to improve its behaviour or by remembering previously selected behaviours which were influenced by its emotional mechanism. Moreover, the architecture incorporates a realistic memory consolidation process based on a data mining algorithm.

It is now widely accepted that in order to optimize both their usage and their design and maintenance ontologies should comply to design quality criteria, e.g., absence of redundancies and appropriate level of abstraction. Yet given the variety and scope of activities comprised in the life-cycle of an ontological model (OM), such as adapting, splitting, populating, this quality is easily compromised, especially with ontologies of larger size and/or resulting from the merge of smaller ones. Conversely, restoring it through refactoring, i.e., restructuring of the ontology to improve defects, is knowingly a challenging task as relocating an ontology element can adversely affect its neighbors. We investigate here a holistic refactoring approach that, given an ontology, amounts to presenting its designer with a list of the most plausible abstract entities missing in it. The core of the approach is a recently devised concept analysis method, called 'relational', that allows deeper refactoring by feeding into the process various ontological relations, e.g., concept-to-property incidences. The focus here is put on the NLP-aspects of the refactoring, while we also provide some preliminary results from a series of validating experiments.

In previous works, we showed how sequential pattern mining can be used to extract a partial problem space from logged user interactions for a procedural and ill-defined domain where classic domain knowledge acquisition approaches don't work well. In this paper, we describe in details how such a problem space can support important tutoring services such as (1) recognizing the plan of a learner, (2) providing hints and (3) estimating the profile of a learner including its expertise level and missing or misunderstandood skills.

The reusability in learning objects has always been a hot issue. However, we believe that current approaches to e-Learning failed to find a satisfying answer to this concern. This paper presents an approach that enables capitalization of existing learning resources by first creating "content metadatardquo through text mining and natural language processing and second by creating dynamically learning knowledge objects, i.e., active, adaptable, reusable, and independent learning objects. The proposed model also suggests integrating explicitly instructional theories in an on-the-fly composition process of learning objects. Semantic Web technologies are used to satisfy such an objective by creating an ontology-based organizational memory able to act as a knowledge base for multiple training environments.

One of the goals of the knowledge puzzle project is to automatically generate a domain ontology from plain text documents and use this ontology as the domain model in computer-based education. This paper describes the generation procedure followed by TEXCOMON, the knowledge puzzle ontology learning tool, to extract concept maps from texts. It also explains how these concept maps are exported into a domain ontology. Data sources and techniques deployed by TEXCOMON for ontology learning from texts are briefly described herein. Then, the paper focuses on evaluating the generated domain ontology and advocates the use of a three-dimensional evaluation: structural, semantic, and comparative. Based on a set of metrics, structural evaluations consider ontologies as graphs. Semantic evaluations rely on human expert judgment, and finally, comparative evaluations are based on comparisons between the outputs of state-of-the-art tools and those of new tools such as TEXCOMON, using the very same set of documents in order to highlight the improvements of new techniques. Comparative evaluations performed in this study use the same corpus to contrast results from TEXCOMON with those of one of the most advanced tools for ontology generation from text. Results generated by such experiments show that TEXCOMON yields superior performance, especially regarding conceptual relation learning.

We describe two fundamental learning mechanisms implemented in a cognitive autonomous agent, CTS (conscious tutoring system). They are meant to allow the ITS discover regularities (frequent situations and contexts), and improve its reaction time.

This paper describes how a knowledge model allows training software to evaluate spatial cognitive maps and provide tailored assistance.

E-learning has advanced considerably in the last decades allowing the interoperability of different systems and different kinds of adaptation to the student profile or learning objectives. However, some of its aspects, such as E-testing are still in their early age. As a consequence of this delay, most of the actual e-learning platforms only offer basic e-testing functionalities. By making efficient use of well known techniques in artificial intelligence, theories in psychometry and standards in E-learning, it could be possible to integrate adaptive testing functionalities in the actual e-learning platform. This is one of the goals for the platform that we developed namedPersonFit. In this paper we will present some of its architectural elements and the algorithms used.

Competence-based learning models have great importance for learning resources: they constitute a meaningful structure for just-in-time and just-enough learning. In this paper, we present an ontology-based competence model that allows the on-the-fly generation of learning knowledge objects (LKOs). The automatic aggregation process relies on knowledge objects and ontologies created through text mining and natural language processing. It is guided by instructional theories encoded declaratively through SWRL. Our framework offers a constructivist learning approach through the presentation of the LKO's context to the learner based on domain ontology. Finally, it allows the standardization of the generated learning objects in SCORM and IMS-LD.

Learning with Tutoring Systems implies large amounts and varied types of information that the Tutor should take into account in order to better adapt the learning session to student’s needs. Managing all this information to optimize learning is not an easy task. This paper claims that «consciousness» mechanisms can help to overcome this problem. We describe how they are implemented and used to effectively diagnose learners’ errors in the specific context of Canadarm2 manipulation.

Probabilistic roadmaps (PRM) have been demonstrated to be very promising for planning paths for robots with high degrees of freedom in complex 3D workspaces. In this paper we describe a PRM path-planning method presenting three novel features that are useful in various real-world applications. First, it handles zones in the robot workspace with different degrees of desirability. Given the random quality of paths that are calculated by traditional PRM approaches, this provides a mean to specify a sampling strategy that controls the search process to generate better paths by simply annotating regions in the free workspace with degrees of desirability. Second, our approach can efficiently re-compute paths in dynamic environments where obstacles and zones can change shape or move concurrently with the robot. Third, it can incrementally improve the quality of a generated path, so that a suboptimal solution is available when required for immediate action, but get improved as more planning time is affordable

In this paper, we present The Knowledge Puzzle, an ontology-based platform designed to facilitate domain knowledge acquisition for knowledge-based systems and especially for intelligent tutoring systems. We present a new content model, the Knowledge Puzzle Content Model, that aims to create Learning Knowledge Objects (LKOs) from annotated content. Annotations are performed semi-automatically using natural language processing algorithms. These LKOs are then aggregated in an Organizational memory (OM) which serves as a knowledge base for an intelligent tutoring system (ITS)

We present an approach to managing the side effect of information updates in the student model (SM). The approach is based on fuzzy logic and fuzzy reasoning on the knowledge structure in the SM. The SM includes three parts: a cognitive model, a behavioural model and an inference engine. The cognitive model is an overlay on curriculum knowledge structures, the behaviour model contains affective and conative values of the student and the inference engine aims to manage updates occurring in the SM during the learning process. As updates imply the evolution of the knowledge structure of the student the propagation module evaluates the possible impacts of the updated information on other related information. This is done by activating a fuzzy reasoning on knowledge networks in the curriculum and deducing new information in the SM. The control module handles conflict situations by considering factors such as the information source and the confidence degree.

Shows how fuzzy logic has been used in the course building process. This process is based on the curriculum modeling approach that we have proposed, and exploits several knowledge sources, such as target-public knowledge and training requirements. By using these parameters, a fuzzy algorithm generates a course which is adapted to the given target public that can produce the required knowledge. The obtained course can be edited by the designer through graphical interfaces and can be delivered by an object-oriented intelligent tutoring system (ITS).