Search

Over the last two decades, a great deal of work has been devoted to the algorithmic aspects of the frequent itemset (FI) mining problem, leading to a phenomenal number of algorithms and associated implementations, each of which claims supremacy. Meanwhile, it is generally well agreed that developing a unifying theory is one of the most important issues in data mining research. Hence, our primary motivation for this work is to introduce a high-level formalism for this basic problem, which induces a unified vision of the algorithmic approaches presented so far. The key distinctive feature of the introduced model is that it combines, in one fashion, both the qualitative and the quantitative aspects of this basic problem. In this paper, we propose a new model for the FI-mining task based on formal series. In fact, we encode the itemsets as words over a sorted alphabet and express this problem by a formal series over the counting semiring $$(\mathbb N,+,\times ,0,1)$$(N,+,×,0,1), whose range represents the itemsets, and the coefficients are their supports. The aim is threefold: First, to define a clear, unified and extensible theoretical framework through which we can state the main FI-approaches. Second, to prove a convenient connection between the determinization of the acyclic weighted automaton that represents a transaction dataset and the computation of the associated collection of FI. Finally, to devise a first algorithmic transcription, baptized Wafi, of our model by means of weighted automata, which we evaluate against representative leading algorithms. The obtained results show the suitability of our formalism.

Learning and teaching systems have seen fast transformations being increasingly applied in emerging formal and informal education contexts. Indeed, the shift to open learning environments is remarkable, where the number of students is extremely high. To allow a huge amount of learners gaining new knowledge and skills in an open education framework, the recourse to e-assessment systems able to cover this strong demand and respective challenges is inevitable. Facing Office skills as those most frequently needed in education and business settings, in this paper, we address the design of a novel assessment system for automated assessment of Office skills in an authentic context. This approach exploits the powerful potential of the Extensible Markup Language (XML) format and related technologies by transforming the model of both students’ documents and answers to an XML format and extracting from the teacher’s correct document the required skills as patterns. To assign a mark, we measure similarities between the patterns of the students’ and the teacher’s documents. We conducted an experimental study to validate our approach for Word processing skills assessment and developed a system that was evaluated in a real exam scenario. The results demonstrated the accuracy and suitability of this research direction.

It is well-known that developing a unifying theory is one of the most important issues in Data Mining research. In the last two decades, a great deal has been devoted to the algorithmic aspects of the Frequent Itemset (FI) Mining problem. We are motivated by the need of formal modeling in the field. Thus, we introduce and analyze, in this theoretical study, a new model for the FI mining task. Indeed, we encode the itemsets as words over an ordered alphabet, and state this problem by a formal series over the counting semiring (N,+,x,0,1), whose the range constitutes the itemsets and the coefficients their supports. This formalism offers many advantages in both fundamental and practical aspects: The introduction of a clear and unified theoretical framework through which we can express the main FI-approaches, the possibility of their generalization to mine other more complex objects, and their incrementalization and/or parallelization; in practice, we explain how this problem can be seen as that of word recognition by an automaton, allowing an efficient implementation in O(|Q|) space and O(|FL||Q|]) time, where Q is the set of states of the automaton used for representing the data, and FL the set of prefixial maximal FI.

The need for IT skills assessment and certification is indisputable for both persons and institutions. Thus, the recourse to automatic assessment systems able to answer the strong demand of such assessment or certification is inevitable. In this paper, we propose a new approach to automatically assess IT skills in authentic context. This approach relies on the potential of XML format and its related efficient technologies which allow the extraction of information from XML documents. We divide our assessment approach into two steps. In the first, we transform both Students documents and answers model to an intermediate representation using XML format for which some preprocessing is done. In the second step, we extract from the teacher's correct document the required skills as paths of the tree representation of the XML document. In order to assign a mark we measure similarities between these paths and those of the student document. We have conducted an experimental study to validate our approach. Thus, we have developped a tool based on the proposed approach to automatically assess Word Processing skills using Microsoft Office Word program. The evaluation of our tool is performed on a real exam with one hundred students. The results show the accuracy and the suitability of this solution for assessing IT skills.