Romanian Journal of
Human - Computer InteractionVol.7, No.4, 2014
ISSN 1843-4460
Contents
Named entities identification.
Liviu Sebastian Matei, Ştefan Trăuşan Matu
273 - 288 Some aspects of the internet influence on the health-related behavior of the Romanian students.
Valentina Marinescu
289 - 304 Using semantic resources in an image retrieval system.
Alexandra-Mihaela Siriţeanu, Adrian Iftene
305 - 320 The analysis of interactions in a collaborative learning session on instant messagery.
Sibel Denisleam (Molomer), Ştefan Trăuşan Matu
321 - 330 User Interaction Techniques based on 3D Graphical Annotation in eLearning Environments.
Teodor Ştefănuţ, Dorian Gorgan
331 - 350
Abstracts
Named entities identification
Liviu Sebastian Matei1, Ştefan Trăuşan-Matu1,2
1University "Politehnica" of Bucharest, Faculty of Automatic Control and Computers
313 Splaiul Independentei, 060042, Bucharest, Romania
E-mail: liviumat@gmail.com
2Artificial Intelligence Research Institute
13 Calea 13 Septembrie, Bucharest, 050711, Bucharest, Romania
E-mail: stefan.trausan@cs.pub.ro
Abstract. An important topic in natural language processing is represented by named entities recognition inside texts. This article describes a novel approach used for detecting named entities that tries to improve the results obtained with the named entity recognition module from Stanford NLP library. In order to determine and classify named entities, this new model uses the Naive Bayes classifier. Our method is focused on named entities of type person and organization but it can be easily extended to other types of named entities. As training data we are using text that is manually annotated, text annotated with Stanford NLP toolkit and a set of XML files containing rules that describe different patterns. After the training, we are using the naive Bayes classifier in order to classify new entities. As test data we are using a Reuters collection of approximate 25000 articles among which 150 articles were manually annotated and used as training data. In order to evaluate the method we are computing the precision, the recall and the F1 factor.
Keywords: named entities, Bayes, machine learning, natural language processing.
Cite this paper as:
Matei, L.S., Trausan-Matu, S. Named entities identification. Revista Romana de Interactiune Om-Calculator 7(4), 273-288, 2014.
Some aspects of the internet influence on the health-related behavior of the Romanian students
Valentina Marinescu
University of Bucharest
E-mail: vmarinescu9@yahoo.com
Abstract. The present article starts from the premise that the debate about the health system offers a privileged perspective to address themes that are at the intersection of media discourse, public health policies, institutions and organizations in the field of medical and social issues. ”What is the influence of the Internet on the health behavior of Romanian students?”– this was the research question at the basis of the present article. A survey on a sample 330 students from the University of Bucharest was made in order to offer an answer. The findings suggest that the Internet plays an important role in modelling healthy behaviors of Romanian students.
Keywords: health literacy, mass media, internet, health-related behavior.
Cite this paper as:
Marinescu, V. Some aspects of the internet influence on the health-related behavior of the Romanian students. Revista Romana de Interactiune Om-Calculator 7(4), 289-304, 2014.
Using semantic resources in an image retrieval system
Alexandra-Mihaela Siriţeanu, Adrian Iftene
Alexandru Ioan Cuza University of Iasi, Faculty of Computer Science
General Berthelot 16, Iasi
E-mail: {alexandra.siriteanu, adiftene}@info.uaic.ro
Abstract. In the recent years, with the development of the intelligent devices, users are sharing more and more multimedia data across the Internet using social networks. This is the reason why, web search has also become the main method for people to fulfill their information needs. Nevertheless, searching for diverse data is not that straightforward, since most information retrieval systems base their algorithms on popularity, relevance, rather than dissimilarity. In the CHIST-ERA project MUCKE (Multimedia and User Credibility Knowledge Extraction), we created a multimedia retrieval system that takes into consideration both relevance and diversity. To address the problem of diversification, we explore two approaches: (1) using semantic resources (like YAGO) in the processing of the initial query, and (2) the operations of clustering the results provided by us, based on the images titles or based on their content. In this paper, we present the first approach and we compare the results of our solution with the results provided by the Google search engine.
Keywords: Image retrieval, Search diversification, Semantic resources, YAGO.
Cite this paper as:
Siriteanu, A.M., Iftene, A. Using semantic resources in an image retrieval system. Revista Romana de Interactiune Om-Calculator 7(4), 305-320, 2014.
The analysis of interactions in a collaborative learning session on instant messagery
Sibel Denisleam (Molomer)1, Ştefan Trăuşan-Matu1,2
1University "Politehnica" of Bucharest, Faculty of Automatic Control and Computers
313 Splaiul Independentei, 060042, Bucharest, Romania
E-mail: d_sybelle@yahoo.com
2Artificial Intelligence Research Institute
13 Calea 13 Septembrie, Bucharest, 050711, Bucharest, Romania
E-mail: stefan.trausan@cs.pub.ro
Abstract. The paper analyzes the interaction in a group of students who use instant messaging (IM) Yahoo Messenger to write a sorting algorithm. This analysis aims to identify words in a natural language and the methods of extracting important words, sentences, utterances and implicit links. Words are analyzed in terms of coherence and cohesion in text followed by a combination of words based on different ontologies. Keyword Analysis, searches the words or the sets of words using PolyCAFe system. Studying the relations between words, we can determine the meaning of words using WordNet ontology. The relations between words can rely on Latent Semantic Analysis algorithm that performs association between words in different lines and in the same space. In this paper we introduce the concept of breaks in collaboration analyzed both face to face and one online. Breaks can be viewed as silences, hesitations and can be analyzed from several aspects such as time, participant response.
Keywords: CSCL, conversation analysis, extracting words, pauses.
Cite this paper as:
Denisleam, S., Trausan-Matu, S. The analysis of interactions in a collaborative learning session on instant messagery. Revista Romana de Interactiune Om-Calculator 7(4), 321-330, 2014.
User Interaction Techniques based on 3D Graphical Annotation in eLearning Environments
Teodor Ştefănuţ, Dorian Gorgan
Technical University Cluj-Napoca, Computer Science Department
Str. Memorandumului nr. 28, Cluj-Napoca, 400114
E-mail: {teodor.stefanut, dorian.gorgan}@cs.utcluj.ro
Abstract. Multimedia eLearning resources (i.e. images, video files, and 3D models) allow the exemplification and intuitive representation of high complexity concepts. At the same time, the interaction with these resources cannot be efficiently implemented nu based on text communication and analysis (i.e. chat, email, forums). In order to enable the users involved in didactic activities, either trainers or trainees, to focus on the content of the materials and less on learning the interaction tools and methods, we propose the use of graphical annotations as the base of a new user interaction style. Specific interaction techniques will be described throughout the article, for each phase of the teaching process: resources creation, resources analysis, communication between participants in the context of the information presented, knowledge evaluation. In order to enable natural integration of 3D graphical annotations in the lesson model we will also describe a new modelling approach, both at the control level (e.g. creating new resources or modifying the visual structure of existing ones) and analysis/representational level (e.g. represent student answers to specific problems).
Keywords: interaction techniques, eLearning, 3D graphical annotation.
Cite this paper as:
Stefanut, T., Gorgan, D. User Interaction Techniques based on 3D Graphical Annotation in eLearning Environments. Revista Romana de Interactiune Om-Calculator 7(4), 331-350, 2014.