Revista Romana de Interactiune Om-Calculator

111-126

Authors: Marian Cristian Mihaescu

This paper presents a study on a design methodology for the interface of a recommender system. A usability evaluation is designed for an intelligent interface of a recommender system that runs along Tesys e-Learning platform. Building intelligent e-Learning systems enables students to access the educational resources is such a way that the learning effort is optimal when a high degree of knowledge is required. The design of the interface follows an iterative process in which low fidelity prototypes are built and evaluated. The usability evaluation is performed in two ways. A questionnaire is proposed for evaluation of low fidelity models. For high quality results a data analysis procedure of task completion times is used.

141-154

Authors: Costin Pribeanu

In recent years the educational applications based on augmented reality (AR) gained interest due to the opportunities provided by the integration of real objects from the traditional didactics on a hardware-software platform. The implementation of the AR concept, which is based on the superposition of computer generated images over the observed image of a real object on the screen, may lead to specific usability problems that are reflected on the ease of learning how to operate, ease of use, and comfort in use. In this paper a model with causal indicators is presented that is influencing the ergonomic quality of an AR-based educational application. The results show that the ease of reading the information on the screen and the ease of selecting a chemical element are the most important causal indicators for the ergonomic quality of the application.

169-192

Authors: Adrian-Nicolae Zamfirescu, Traian Eugen Rebedea

At the border of natural language processing and information retrieval, named entity recognition has represented one of the most important research problems of the two domains, that has not been solved perfectly yet even for English texts. Furthermore, named entity recognition has opened up the path of solving other problems that use these linguistic contructs, such as the identification of quotes and declarations made by persons, in general, but also by companies or other types of organizations, or the extraction of events from texts. The problem of named entity identification and clasification has appeared from the necessity of being able to report the appearances of names of persons, organizations and other types of named entities relevant for various domains within written documents. In this article we shall present a solution for solving these three aforementioned problems for texts written in Romanian from various sources, like news items, blog articles or comments from social newtorks. The paper starts with a short overview of the theoretical underpinnings used for solving these problems, then we will present the methods actually used for the designed solution for Romanian. It combines machine learning algorithms with heuristics based on text patterns and regular expressions. At the end, we shall highlight the accuracy of the various methods used for solving the tasks, together with a comparison between the results obtained by each method.