Data Mining Practical Machine Learning Tools and Techniques

Ontologies are the backbone of the Semantic Web, a semantic-aware version of the World Wide Web. To the end of making available large-scale, high quality domain ontologies, effective and usable methodologies are needed to facilitate the process of Ontology Building. Many of the methods proposed so far only partly refer to well-known and widely used standards from other areas, like software engineering and knowledge representation. In this paper we present UPON, a methodology for ontology building derived from the Unified Software Development Process. A comparative evaluation with other methodologies, as well as the results of its adoption in the context of the Athena Integrated Project, are also discussed.

A proposal for a unified process for ontology building : UPON

The increasing interconnections of city services, the explosion of available urban data, and the need for multidisciplinary analysis and decision making for city sustainability require new technological solutions to cope with such complexity. Ontologies have become viable and effective tools to practitioners for developing applications requiring data and process interoperability, big data management, and automated reasoning on knowledge. We investigate how and to what extent ontologies have been used to support smart city services and we provide a comprehensive reference on what problems have been addressed and what has been achieved so far with ontology-based applications. To this purpose, we conducted a systematic literature review finalized to presenting the ontologies, and the methods and technological systems where ontologies play a relevant role in shaping current smart cities. Based on the result of the review process, we also propose a classification of the sub-domains of the city addressed by the ontologies we found, and the research issues that have been considered so far by the scientific community. We highlight those for which semantic technologies have been mostly demonstrated to be effective to enhance the smart city concept and, finally, discuss in more details about some open problems.

https://www.mdpi.com/2071-1050/13/10/5578/pdf

Smart City Ontologies and Their Applications: A Systematic Literature Review

This study provides a systematic review of the recent advances in designing the intelligent tutoring robot (ITR) and summarizes the status quo of applying artificial intelligence (AI) techniques. We first analyze the environment of the ITR and propose a relationship model for describing interactions of ITR with the students, the social milieu, and the curriculum. Then, we transform the relationship model into the perception-planning-action model to explore what AI techniques are suitable to be applied in the ITR. This article provides insights on promoting a human-robot teaching-learning process and AI-assisted educational techniques, which illustrates the design guidelines and future research perspectives in intelligent tutoring robots.

Artificial Intelligence in Intelligent Tutoring Robots: A Systematic Review and Design Guidelines

The main objective of exams consists in performing an assessment of students' expertise on a specific subject. Such expertise, also referred to as skill or knowledge level, can then be leveraged in different ways (e.g., to assign a grade to the students, to understand whether a student might need some support, etc.). Similarly, the questions appearing in the exams have to be assessed in some way before being used to evaluate students. Standard approaches to questions' assessment are either subjective (e.g., assessment by human experts) or introduce a long delay in the process of question generation (e.g., pretesting with real students). In this work we introduce R2DE (which is a Regressor for Difficulty and Discrimination Estimation), a model capable of assessing newly generated multiple-choice questions by looking at the text of the question and the text of the possible choices. In particular, it can estimate the difficulty and the discrimination of each question, as they are defined in Item Response Theory. We also present the results of extensive experiments we carried out on a real world large scale dataset coming from an e-learning platform, showing that our model can be used to perform an initial assessment of newly created questions and ease some of the problems that arise in question generation.

R2DE: a NLP approach to estimating IRT parameters of newly generated questions

The field of adaptive e-learning is continuously developing. More research is being conducted in this area as adaptive e-learning aims to provide learners with adaptive learning paths and content, according to their individual characteristics and needs, which makes e-learning more efficient and effective. The learner model, which is a representation of different learner’s characteristics, plays a key role in this adaptation. This paper presents a systematic literature review about learner modelling during the last 5 years, describing the different modelled characteristics and the adopted modelling techniques and modeling types: automatic modeling and collaborative modeling. 107 publications were selected and analyzed, and six categories of the modelled characteristics were identified. This literature review contributes to the identification of the learners’ individual traits and presents the most used modelling techniques for each of them. It also identifies the latest research trends of Learner Modeling and generates future research directions in this field.

Learner modelling: systematic review of the literature from the last 5 years

One of the biggest challenges of Adaptive e-learning systems is learner modelling. The learner model should represent the learner's characteristics as faithfully as possible in order to provide adaptive learning. Among these characteristics, the learner's knowledge is considered to be the core characteristic of the learner model, as adaptive e-learning systems are centered on the learner's knowledge, since acquiring « knowledge » about a specific domain or concept is considered the main goal of learning and instruction. In this paper, we propose a novel adult learner's knowledge model using ontologies and rule reasoning, by trying to define the different components that construct the learner's knowledge in an exhaustive yet a simple way. The proposed model takes into account different elements of the learner's knowledge, such as the different knowledge types and categories, the learner's prior knowledge accumulated through his/her experiences, his/her misconceptions, errors and the previously learned but forgotten knowledge.

An adult learner's knowledge model based on ontologies and rule reasoning

Differences in the learners' personality have an impact on their learning outcomes and achievements. Therefore, there is a need to automatically predict and identify their personalities in an unobtrusive way, and build the learner model accordingly. In this paper, we try to identify the learner's personality dimensions, according to the big five personality model, using educational data features in order to develop an automatic classifier that predicts the learner's personality discreetly based on his/her traces in an online learning system. We applied seven different supervised learning classification algorithms, using personality scores for each dimension (high or low) as target values, and analyzed the results. The findings were encouraging and revealed that most of Big Five personality dimensions can in fact be predicted using mainly educational data features, which could have an added value on unobtrusive dynamic learner modelling.

Predicting the learner's personality from educational data using supervised learning

Online learning environments are in a continuous and rapid evolution. Multiple approaches are used to model these environments, but only a few of them deal with adult education, which is becoming more and more important, as adult learners are increasingly interested in online education. In fact, learner models-, which are the foundation of adaptive learning systems-that exist nowadays, are limited to modeling only a few learner's characteristics such as learner's knowledge and competencies, but they neglect other parameters that are as important for the adult learner. This paper aims to identify adult learners' different characteristics, and to define a taxonomy that can aid the design of a model that incorporate the adult learner in an adaptive learning environment.

Abir Abyaa

Papers

Learner modelling: systematic review of the literature from the last 5 years

An adult learner's knowledge model based on ontologies and rule reasoning

Predicting the learner's personality from educational data using supervised learning

Towards an adult learner model in an online learning environment