Recently, bio-inspired systems have become increasingly intriguing to solve complex optimization problems without centralized control, making them an effective solution for developing efficient applications. Addressing the behavioral analysis of cognitive populations in these systems represents the cornerstone of the robustness of real-time applications. In this paper, we simulate an Ant Colony Optimization (ACO) system guided by simple local rules enabling ants to build cognitive maps, learn multiple objectives, and plan their paths. The accumulation of local learning leads to the emergence of collective behaviors such as specialization, selfishness, or altruism. The latter results in actions where some ants favor collective success. Thus, simple behaviors at the individual level produce self-organized and efficient dynamics at the global level. The simulation results in this paper describe how the local learning with the accumulation of individual decisions advocates the creation of new structures that allow altruistic Ants to improve their adaptive behavior in unknown environments. The data center location problem constitutes a canonical testbed for the deployment of this system, enabling the strategic placement of data centers to meet highdemand regional requirements. In-depth characterization of its time complexity is pivotal for the development of scalable, realtime optimization algorithms.

In the digital era, Artificial Intelligence is increasingly developing. In recent years, one of the promising development in this field is ChatGPT which has sparked considerable interest. ChatGPT is a language model developed by OpenAI that allows people to interact with a computer in a more natural and conversational way. It offers students and educators personalized learning experiences Linked to ChatGPt open AI API. Therefore, we present in this paper a virtual tutor, named NAJEH, integrated into the student engagement portal and mobile application (MYU) and have access to the Student Information System (SIS) and Learning Management System (LMS) of the Honoris United Universities(1), which includes 6 institutions in Tunisia. Around five thousand students from the Universite Centrale had the learning experience with NAJEH. A survey was carried out in order to explore students satisfaction and acceptance of NAJEH. Thus, with a 76% response rate, results show that more than 80% of students find this chatbot tutor very useful, easy and use it at least once a day. As perspective, we propose to investigate on the impact of these interactions on the students' academic performance and teaching efficiency. In fact, an in-depth study requires more data available over a longer period, even several years.

Clustering analysis is one of the data analysis techniques that organizes items into clusters according to their degrees of similarities. In this context, bio-inspired algorithms have found success in solving clustering problems.Inspired by nature, Ant Colony based Clustering arises from ant colony behavior in organizing nests and clustering ants corpses. Accordingly, several researchers proposed different clustering algorithms that mimic the real ants behavior in forming cemeteries. However, the performance of a given algorithm depends strongly on its parameters settings. Indeed, it holds a large number of adjustable parameters that need to be instantiated by suitable values. In this paper, we study the parameters influence, more precisely the parameter α which is responsible for adjusting similarity between objects. In fact, we analyze the impact of α values on the performance of some well known Ant Colony based Clustering Algorithms applied to constructing team-works in a collaborative learning environment. After various bench tests, the choice of α value is determined based on the best algorithm accuracy for each learning data-set. The experimental results prove that Ant Colony algorithms performance strongly depends on α, especially when applied to high-dimensional data-sets. However, α has a negligible influence on the algorithm’s accuracy when applied to low-dimensional data-sets. Obviously, the feature selection step could be ignored since it has a negligible influence on the algorithm performance even with different values of α.

Recently, analysing the students' creative writing has become increasingly an interesting subject in the literature to improve the students' performance, awareness and thinking, especially after the emergence of AI tools. The majority of the researchers have focused only on dealing with these new tools to not limit the students' creativity, critical thinking and socialisation. Exceptionally, this paper presents the results of the international educational innovative project: “EcoApreNdemos 2023: narrating learning for the betterment of the environment” that combines social action and creative writing to promote the students' critical thinking and awareness. It introduces a holistic analysis to understand how creativity learning through social engagement takes place, with the help of data analytics and the aim of being able to improve it. It analyses the students' creative writing before and after social actions to help instructors find the best pedagogical design to enhance their students' writing capabilities. Additionally, it defines an application of students' grouping according to their creative writing features using an intelligent algorithm.

The task of assessing, grouping and arranging data into meaningful groups or clusters based on their similarities/dissimilarities measures known as cluster analysis. Thereby, there are numerous clustering algorithms: hierarchical and partitional. In the last decade, clustering using bio-inspired algorithms received more attention, specifically the ant clustering algorithms. Regardless, they have required a lot of processing power due to the massive amount of data that has been generated during the last years. As a consequence, determining the computational cost of these algorithms is one of the most interesting tasks in the quest for optimal clustering solutions in a real-time system. This study presents a research guide for the researchers working in the same field. A series of experiments are elaborated to investigate the computational complexity of the most promising algorithms applied to students grouping problem. The results indicate two challenges that arise when using ant clustering algorithms: the difficulty in adjusting parameters and extended computation time.

Regulating learners' negative emotions during a learning session is an important factor in educational settings that aims at enhancing learner's cognitive performance and achievement outcomes. In this context, many researchers in psychology have proposed emotion regulation questionnaires that help to assess the use of emotion regulation strategies by learners in order to regulate their emotions while learning. However, the number of items in each questionnaire is large which may annoy the learner and prevent him/her from completing all of the items; this may lead to inappropriate emotional regulation. Thus, we propose in this paper a machine learning method for mining items in order to reduce the fully associated ones to one item. First of all, the paper presents a critical overview on statistical methods applied for reducing the large number of items in questionnaires. Then, after the introduction of the selected data set about the emotion regulation questionnaires, we detail the association rules mining method and discuss the obtained results about the significant association rules between the items. This can lead to uphold the items' reduction without loss of reliability.

There is strong evidence that emotional states affect the Human’s performance and decision making. Therefore, understanding Human emotions has become of great concern in the field of Human Computer Interaction (HCI). One way to online emotion recognition is through Keystroke Dynamics. It addresses the drawbacks of current methods which are intrusive and not user-friendly, expensive to implement, and neither realistic nor applicable in a real-world context. The keystroke dynamics approach focuses on analyzing the particular way a person types on a keyboard. In our research work, we start by developing a web application (EmoSurv) in order to collect the data and build a dataset. We generate datasets for free-text and fixed-text entries. These datasets are labeled with emotional states of the participants (Angry, Happy, Sad, Calm, and Neutral state). The obtained datasets are used for training and building models using machine learning algorithms. Outstanding accuracy rates are obtained reaching 93.922% and Kappa equal to 0.9197 using Random Committee algorithm. We finally provide a set of recommendations for future experimentation by comparing the different models generated.

Writer identification/recognition from off-line Arabic handwriting on sentence-level is still a tough task. In this paper, we start by investigating the performance of textural extractors for writer identification of divergent writing types. Taking into account their strengths and limits, we propose a new method that keeps the main features of the writing and handles the sensitivity of systems towards the available samples of text at the pre-processing phase. We also analyze the influence of the handwriting types on the efficiency of the writer identification process. In this regard, we perform a comparative study between handcrafted and automated features. Under multiple classifiers (RF, XGB, KNN and SVM). We find that writers with good and well clear handwriting have fewer similarities, thus, provides enhanced experimental identification rates. However, Bad handwriting presents more similarities between the writers, which explains the reduction in the identification rate.

Emotion regulation (ER) is a process responsible for altering emotions' reactions and expressions as well as situations that simulate such feelings to better respond to environmental issues.Hence, ER is actually a mere mental and behavioral process that many of us already perform consciously and unconsciously. In this issue, with the imperious role of emotions in learning process which they crucially influence student's cognitive performances and academic outcomes, several researchers proposed different methods and tools for regulating learners' negative emotions while learning in online environment. In the present paper, we discuss the current and original research works that apply different strategies and methods for emotion regulation in different smart environments (i.e., Intelligent Tutoring Systems) by adopting a Systematic Literature Review (SLR) approach.

There is strong evidence that emotional states affect the Human's performance and decision-making. Therefore, understanding Human emotions has become of great concern in the field of Human-Computer Interaction (HCI). One way to an online emotion recognition is through keystroke dynamics. Keystroke Dynamics focuses on the particular way a person types on a keyboard. To provide insight, assess recent works, and guide future researches in this field, a Systematic Literature Review (SLR) is conducted. An SLR adopts a rigorous procedure with the definition of a formal review protocol. The primary aim of this paper is to highlight the effectiveness of using keystroke dynamics biometrics in recognizing emotions by systematically presenting research efforts in the past decade. We provide insight into such an approach by summarizing and discussing the data acquisition procedures, datasets, extracted features, classification methods, and performance measures used in previous researches. In light of these findings and the noticed scarcity of datasets related to emotion recognition through keystroke dynamics, we develop and host an interactive web application to construct a new dataset. The findings of this work reveal new interesting research directions and may motivate the research community to develop automatic emotion recognition systems based on keystroke dynamics.

Building Collaborative e-Learning Teams in a Smart Education Environment Abstract: Collaborative learning is a teaching method requiring to group students according to various ways and types, it is the most used approaches to arrange students for an effective learning in the classroom. However, with the large number of students in e-learning context, and their different settings, the task to establish cooperation and collaboration among them becomes harder and complex. Hence, several researchers proposed different approaches to overcome this diversity and find the best solution for building a good collaborative learning environment. In this context, this work discuss the Ant Colony optimisation (ACO) bio-inspired approaches and their added values in Data Analysis which leads us to assume the collaborative e-learning teams (CeLT) formation as a data clustering problem. Therefore, we analyse and discuss some ant clustering algorithms, and adapt the best one so it can be applied on an educational data sets. The results show a good starting point for future works on a real smart education Environment.

Emotions affect the learning and the performance of learners. They are considered as a part of the school daily life. Hence, currently, there is a variety of methods which aim to explore and extract emotions during the learning process. In addition, a multitude of e-learning platforms are built according to traditional (teacher-based) or collaborative (learner-based) approaches. The objective of this paper is to propose a solution that integrates the emotion extraction method in a chosen platform. We have previously justified the choice of Moodle as a platform and a method of emotion extraction based on the text given by the learner. As a perspective, this proposal will prepare an emotion extraction and regulation of the learners in order to improve their performances.

essing web sites is considered as a Multiple Criteria Decision Making problem (MCDM), with a massive number of criteria; a reduction phase is needed.Text mining is applied for this SLR to construct a dataset of criteria.Association Rules Mining are used to study interdependencies between criteria and the category of the web site. Nowadays society is deeply affected by web content. A web site, regardless of its category, can provide or not for users their needs. To identify its strengths and weaknesses, a process of analyzing and assessing its quality, via some criteria, is necessary. Assessing web sites is considered as a Multiple Criteria Decision Making problem (MCDM), with a massive number of criteria; a reduction phase is needed. This paper presents, firstly a Systematic Literature Review (SLR) to identify the purposes of recent researches from the assessment and determine the affected categories; secondly, it proposes a process of collecting and extracting data (criteria featuring web sites) from a list of studies. Text mining is applied for this SLR to construct a dataset. Then, a method based on Apriori algorithm is assigned and implemented to find association rules between criteria and the category of the web site, and to get a set of frequent criteria. This paper also presents a review on soft computing assessing methods. It aims to help the research community to have a scope in existing research and to derive future developments. The obtained results motivate us to further probe datasets and association rule mining.

Collaborative learning is an educational method used by teachers to impact learning in a positive way and enhance the learners' performances. It can occur within a group of two or more students. Therefore, the learners' grouping is an essential task for establishing collaboration and cooperation among them to achieve a common goal. However, with the increasing number of students as well as their different settings (academic, cognitive, emotional, social, etc.), the students grouping task becomes harder and more complex to build a good collaborative learn- ing environment. Hence, several researchers proposed different approaches for obtaining approximate solutions to handle this diversity and take advantages from it. In this context, this paper presents a systematic literature review (SLR) to pinpoint the relevant research works that address the students grouping problem. We also we focus on the ACO bio-inspired approach to discuss its advantages and how students group formation can be initially constructed by ACO method. In accordance with this, we adapt and simulate an existing ACO algorithm with randomly generated data. The obtained results show an interesting starting point for further works in order to develop a new approach based on real educational data.

Predicting students’ academic performance is one of the oldest and most popular applications of educational data mining. It helps to estimate the unknown evaluation of a student’s performance. However, a huge amount of data with different formats and from multiple sources may contain a large number of features supposed as not-relevant that could influence the prediction results. The main objective of this paper is to improve the effectiveness of a predictive model for students’ academic performance. For this purpose, we propose a methodology to carry out a comparative study for evaluating the influence of feature selection techniques on the prediction of students’ academic performance. In our study, F-measure parameter is used to evaluate the effectiveness of the selected techniques. Two real data sources are used in this work, Mathematics and language courses. The outcomes are compared and discussed in order to identify the technique that has the best influence for an accurate predictive model.

An intelligent Tutoring System (ITS) is a computer-based instructional system, involving intelligent algorithms and strategies, which brings a remarkable progress in the learning processes when the internet is “always on”. In fact, ITS makes inferences about a student's proficiency level in order to dynamically adapt the learning content or the tutoring style. Around the same time, emotions, whether positive or negative, affect the learning process. Accordingly, the regulation of learners' negative emotional state, is an imperious factor in learning, in order to optimize learners' performances and to improve learning productivity during an ITS episode. Firstly, this paper presents a systematic literature review (SLR) on strategies for regulating the emotional state of learners in the point of view of (a) emotion recognition, (b) emotion modelling, (c) emotion recognition theories, and (d) emotion recognition approaches and methods. Secondly, the paper proposes a new intelligent method, and presents its architecture as a Fuzzy Emotional Regulation for ITS distributed under the Multiagent Approach. This architecture will be used to generate an Emotionally Intelligent Tutoring Sys-tem (EITS) allowing learner to achieve his educational purpose adaptively, anywhere and at any time.

Testing and assessing are core activities in the development cycle of software applications, dedicated to evaluating interactive products in order to improve their quality by identifying various usability problems and defects. For complex system such as multiagent ones, usability evaluation is still an issue, and requires new test techniques to assess autonomous and interactive behaviors. This paper deals with investigation about the evaluation of the Human-Machine Interaction (HMI) in Complex Systems: A review on evaluation methods and introduce domain-specific requirements is presented; A mechanism for the evaluation of HMI is proposed. Also, an implementation of an automatic tool dedicated to the assessment of complex interactive systems based on fuzzy logic approaches is explained; A solution to automate the evaluation of the HMI that reduces the need for expert assessment and fully integrates end-users into the HMI evaluation loop is suggested. These are assessed in the urban transit control room in the city of Valenciennes, France. The comparative study deals with acceptance, motivation and perceived happiness.

Nowadays society is deeply affected by web content. A web site, regardless of its category, can provide or not for users their needs. To identify its strengths and weaknesses, a process of analyzing and assessing its quality, via some criteria, is necessary. Assessing web sites is considered as a Multiple Criteria Decision Making problem (MCDM), with a massive number of criteria; a reduction phase is needed. This paper presents, firstly a Systematic Literature Review (SLR) to identify the purposes of recent researches from the assessment and determine the affected categories; secondly, it proposes a process of collecting and extracting data (criteria featuring web sites) from a list of studies. Text mining is applied for this SLR to construct a dataset. Then, a method based on Apriori algorithm is assigned and implemented to find association rules between criteria and the category of the web site, and to get a set of frequent criteria. This paper also presents a review on soft computing assessing methods. It aims to help the research community to have a scope in existing research and to derive future developments. The obtained results motivate us to further probe datasets and association rule mining.

With the increasing diversity of learners, forming suitable learning groups, in collaborative learning, represents a complex and a time-consuming task. Several researchers focus on the theory of teamwork organizations, based on academic performances, learning styles, learning settings, gender, etc. Therefore, grouping learners based on their predicted academic performance level in each subject separately may be more effective in a collaborative learning environment, but it still a challenging subject. First of all, we present in this paper a systematic literature review (SLR) to identify the relevant studies that address the problem of predicting academic performance and to extract the used data mining methods such as Decision Tree, Naïve Bayes, Neural Network, Support Vector Machine, etc. At the beginning, a set of 658 papers were selected. After applying the different SLR's steps, this selection has been filtered to 12 papers using specific selection criteria and a careful analysis of each paper. Then, the selected studies were used to answer the defined research questions. Finally, synthesis data, current research gaps and recommendations for further work are discussed in this paper.

The new Information, communication, and mobile technologies empower the users to learn anywhere and anytime. They also need conversational systems that could be aware of their mobile context in order to adjust it dynamically. The actual research field is focusing on adaptive conversational systems, especially in the case of Mobile-learning. This paper presents a comparative study of some related works. Then, it proposes an M-learning architecture based on hybrid cooperative agents (mobile, conversational, cognitive), with the possibility integrating Multi-Language ontology for the development of a Conversational Agent (CA) speaking Multi-Language especially Arabic language. A prototype of text-to-speech mobile agent (MobiSpeech) is presented and discussed. MobiSpeech is intended for mobile users, and provide all services to read any text and any text file extension for the user while considering the existing context-awareness.