Entrepreneurship education constitutes a top priority in policy agendas across the globe as a means to promote economic growth, fight unemployment and create social capital. An important premise of entrepreneurship education is that it can be learned and students can be taught to formulate entrepreneurial mentality, skills and competencies, something that can result in the formulation of startups and business initiatives. Given the importance of entrepreneurship, the necessity to formulate efficient entrepreneurship education frameworks and training programs arise. In this work, we present the design of an entrepreneurship educational environment that is based on learning in 3D virtual worlds. Innovative 3D virtual reality technologies were utilized to provide immersive and efficient learning activities. Various topics of entrepreneurship education courses were designed and formulated to offer students the opportunity to obtain theoretical knowledge of entrepreneurship. The 3D virtual reality educational environment utilizes pedagogical approaches that are based on gamification principles, allowing students to study in immersive ways as well as in game-based learning activities on real challenges that can be found in business environments. The game-based learning activities can help students gain necessary skills, helping them to tackle everyday obstacles on their entrepreneurial pathways. An experimental study was performed to explore the learning efficiency of the environment and the gamified learning activities as well as assess their learning impact on student’s motivation, attitude, and overall learning experience. The evaluation study revealed that the framework offers efficient gamified learning activities that increase students’ motivation and assist in the formulation of entrepreneurship mentality, skills and competencies.

Over the last years, the successful integration of virtual reality in distance education contexts has led to the development of various frameworks related to the virtual learning approaches. 3D virtual worlds are an integral part of the landscape of education and demonstrate novel learning possibilities that can open new directions in education. An important aspect of virtual worlds relates to the intelligent, embodied pedagogical agents that are employed to enhance the interaction with students and improve their overall learning experience. The proper design and integration of embodied pedagogical agents in virtual learning environments are highly desirable. Although virtual agents constitute a vital part of virtual environments, their exact impact needs are yet to be addressed and assessed. The aim of the present study is to thoroughly examine and deeply understand the effect that embodied pedagogical agents have on the learning experience of students as well as on their performance. We examine how students perceive the role of pedagogical agents as learning companions during specific game-based activities and the effect that their assistance has on students’ learning. A concrete experimental study was conducted in AVARES, a 3D virtual world educational environment that teaches the domain of environmental engineering and energy generation. The results of the study point out that embodied pedagogical agents can improve students’ learning experience, enhance their engagement with learning activities and, most of all, improve their knowledge construction and performance.

Attention-based methods for deep neural networks constitute a technique that has attracted increased interest in recent years. Attention mechanisms can focus on important parts of a sequence and, as a result, enhance the performance of neural networks in a variety of tasks, including sentiment analysis, emotion recognition, machine translation and speech recognition. In this work, we study attention-based models built on recurrent neural networks (RNNs) and examine their performance in various contexts of sentiment analysis. Self-attention, global-attention and hierarchical-attention methods are examined under various deep neural models, training methods and hyperparameters. Even though attention mechanisms are a powerful recent concept in the field of deep learning, their exact effectiveness in sentiment analysis is yet to be thoroughly assessed. A comparative analysis is performed in a text sentiment classification task where baseline models are compared with and without the use of attention for every experiment. The experimental study additionally examines the proposed models’ ability in recognizing opinions and emotions in movie reviews. The results indicate that attention-based models lead to great improvements in the performance of deep neural models showcasing up to a 3.5% improvement in their accuracy.

In this paper, first we present an educational system that assists students in learning and tutors in teaching search algorithms, an artificial intelligence topic. Learning is achieved through a wide range of learning activities. Algorithm visualizations demonstrate the operational functionality of algorithms according to the principles of active learning. So, a visualization process can stop and request from a student to specify the next step or explain the way that a decision was made by the algorithm. Similarly, interactive exercises assist students in learning to apply algorithms in a step-by-step interactive way. Students can apply an algorithm to an example case, specifying the algorithm’s steps interactively, with the system’s guidance and help, when necessary. Next, we present assessment approaches integrated in the system that aim to assist tutors in assessing the performance of students, reduce their marking task workload and provide immediate and meaningful feedback to students. Automatic assessment is achieved in four stages, which constitute a general assessment framework. First, the system calculates the similarity between the student’s and the correct answer using the edit distance metric. In the next stage, it identifies the type of the answer, based on an introduced answer categorization scheme related to completeness and accuracy of an answer, taking into account student carelessness too. Afterwards, the types of errors are identified, based on an introduced error categorization scheme. Finally, answer is automatically marked via an automated marker, based on its type, the edit distance and the type of errors made. To assess the learning effectiveness of the system an extended evaluation study was conducted in real class conditions. The experiment showed very encouraging results. Furthermore, to evaluate the performance of the assessment system, we compared the assessment mechanism against expert (human) tutors. A total of 400 students’ answers were assessed by three tutors and the results showed a very good agreement between the automatic assessment system and the tutors.

Search algorithms constitute an important domain of computer science and is considered necessary for students and freshmen to get a deep and complete understanding of their operation. In this work, we present an innovative 3D virtual reality educational environment that aims to assist tutors in teaching and students in better learning the search algorithms. The educational environment utilizes innovative educational infrastructure and pedagogical approaches based on visualization of procedures and learning activities that rely on gamification to promote deeper understanding of the challenging concepts of blind and heuristic search algorithms. Algorithm visualization approaches in the virtual environment aim to help students connect abstract concepts and procedures to concrete experiences and examples which promotes robust learning. Learning activities based on the principles of gamification was designed to actively engage students and make learning more entertaining and efficient. The educational environment has been evaluated in real classroom conditions and the evaluation results indicate that the utilization of suitable learning activities in terms of students' active engagement and can motivate students and improve learning efficiency.

Logic as a knowledge representation and reasoning language is a fundamental topic of an Artificial Intelligence (AI) course and includes a number of sub-topics. One of them, which brings difficulties to students to deal with, is converting natural language (NL) sentences into first-order logic (FOL) formulas. To assist students to overcome those difficulties, we developed the NLtoFOL system and equipped it with a strong assistance and feedback mechanism. In this work, first, we present that feedback mechanism. The mechanism can provide assistance before an answer is submitted, if requested, but mainly it provides assistance after an answer is submitted. To that end, it characterizes the answer in terms of completeness and accuracy to determine the level of incorrectness, based on an answer categorization scheme, introduced in this paper. The automatically generated natural language feedback sequences grow from general to specific and can include statements on a student’s metacognitive state. Feedback is provided as natural language sentences automatically generated through a template-based natural language generation mechanism. Second, we present an extensive evaluation of the effectiveness of the assistance and feedback mechanism on students’ learning. The evaluation of feedback with students showed that full feedback sequences lead to greater learning gains than sequences consisting of only flag feedback and bottom-out hints (n = 226), and that generic, template-based feedback sequences are comparable to the utility of problem-specific hints generated by human tutors (n = 120).