Foteini Grivokostopoulou

Utilizing semantic web technologies and data mining techniques to analyze students learning and predict final performance

E-learning systems are becoming a fundamental mean of education delivery. Recently, data mining techniques have been utilized by tutors and researchers to analyze students learning with the aim to get deeper sight of it and improve the quality of the educational procedures. In this paper, we present a methodology to analyze students learning and extract semantic rules that can be used to predict students final performance in the course. Specifically, the students performance at interim tests during the semester is analyzed and the methodology utilizes decision trees and extracts rules to make predictions regarding the students final performance in the course. The methodology has been integrated in an educational system used to assist students in learning the Artificial Intelligence (AI) course in our university. The educational system utilizes semantic web technologies such as ontologies and semantic rules to enhance the quality of the educational content and the delivered learning activities to each student. The methodology can assists the system and the tutor to get a deeper insight of the students performance, trace students that are underachieving or in the edge to fail the final exams and also offer proper recommendations and advises to each one and drive broader pedagogical improvements.

An Educational System for Learning Search Algorithms and Automatically Assessing Student Performance

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.

Assistance and Feedback Mechanism in an Intelligent Tutoring System for Teaching Conversion of Natural Language into Logic

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 (nu2009=u2009226), and that generic, template-based feedback sequences are comparable to the utility of problem-specific hints generated by human tutors (nu2009=u2009120).

An Innovative Educational Environment Based on Virtual Reality and Gamification for Learning Search Algorithms

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.

An Automatic Marking System for Interactive Exercises on Blind Search Algorithms

In this paper, we present a web-based automatic marking system that aims to assist the tutor in assessing the performance of students in interactive exercises related to breadth-first search (BFS) and depth-first search (DFS) algorithms. The system has been tested on a number exercises for BFS and DFS search algorithms and its performance has been compared against that of an expert tutor. The experimental results are quite promising.

An automatic marking system for FOL to CF conversions

The FOL to CF system is a web-based interactive system that aims at helping students in learning converting first order logic (FOL) formulas to their clause form (CF). In this paper, we present a system for automatic marking FOL to CF conversion exercises with feedback. First, the system checks a students answers in order to spot and recognize errors made. This is done after having analyzed each clause. Second, it automatically marks the answers based on the types of the errors and the structure of the clause. Each error type has a different contribution (weight) in the final mark. The final mark is composed of partial marks concerning different structural elements of a clause. By using the automatic marking system, we can mark tests automatically and also collect information about the learning status of each student. Also, it is able to provide feedback on errors made by students through interacting with them. Experimental results show good agreement between the system and the tutor. Also, questionnaire based evaluation shows satisfaction of the students from using the system.

Difficulty Estimator for Converting Natural Language into First Order Logic

The NLtoFOL system is an interactive web-based system for learning to convert natural language (NL) sentences into first order logic (FOL). In this paper, we present a difficulty estimating expert system that determines the difficulty level of a sentence’s conversion process. Our approach is based on the complexity of the corresponding FOL formula instead of the NL sentence itself. Parameters like the number, the type and the order of quantifiers, the number of implications and the number of different connectives are taken into account. Experimental results show that for a significant part of sentences the difficulty estimating system produces the correct outputs.

Estimating the Difficulty of Exercises on Search Algorithms Using a Neuro-Fuzzy Approach

The delivery of educational activities that are tailored and adapted to the student knowledge level is a fundamental aspect of educational systems. In order to provide exercises and learning activities of appropriate difficulty, their level of difficulty should be accurately determined. In this paper, we present a neuro-fuzzy approach that determines the difficulty level of exercises on search algorithms. More specifically, the methodology presented, analyzes the exercises and estimates the difficulty level for blind search and heuristic search algorithmic exercises. Given that search algorithms act on trees, parameters like the number of the exercises nodes, the children for each level, the max depth of the tree and the length of the solution are taken into account. The system has been tested on a number of exercises for blind and heuristic search algorithms and its performance has been compared against that of expert tutors. The experimental results indicate quite promising performance.

Using Semantic Web Technologies in a Web Based System for Personalized Learning AI Course

Utilization of semantic web technologies in educational systems is rapidly expanded, bringing new and more efficient teaching and learning capabilities. Semantic Web Based Educational Systems (SWBEs) rely on semantic web technologies and are proved to be more intelligent and personalized to the students learning needs. In this paper, we present a semantic web based adaptive educational system that is developed to assist the students in learning the challenging subjects of the Artificial Intelligence course. The system utilizes ontologies to represent the domain of the courses curriculum and the student model. Also, the Semantic Web Rule Language (SWRL) rules are used for making decisions on the learning activities to propose to the student according to his/her profile and knowledge level. The evaluation results indicate quite promising performance regarding the systems learning capabilities and functionality.

Teaching assistance and automatic difficulty estimation in converting first order logic to clause form

In this paper, two tools for helping tutors in teaching the conversion of first order logic (FOL) formulas into Clause Form (CF), in the context of an interactive web-based system, are presented. The first is a tutoring managing tool that assists the tutor in managing the teaching material and helps him/her in monitoring the students’ learning progress. The second tool is an expert system that aims at helping the tutor in determining the difficulty level of a formula’s conversion process. To this end, it combines two different approaches, one based on formula’s structure and the other on the conversion process steps. Experimental results show that the difficulty estimation systems perform very successfully.