Romanian Journal of
Human - Computer InteractionVol.3, No.2, 2010
ISSN 1843-4460
Contents
An Intra and Inter-Topic Evaluation and Cleansing Method.
Claudiu Muşat, Andrei Rizoiu, Ştefan Trăuşan-Matu
81 - 96 Analysis of three instruments for measuring usability, satisfaction, and user experience in Romanian context.
Daniela-Maria Andrei, Adriana-Mihaela Guran
97 - 124 Researches regarding the acceptance of e-learning technologies
Dragoş Daniel Iordache
125 - 138 Developing and Using Teaching Materials in eGLE Environment
Dorian Gorgan, Teodor Ştefănuţ, Mircea Mărginean, Victor Bâcu
139 - 156 Software tools for the analysis of sublimal testing tasks in facial microexpressions recognition
Mihai Aniţei, Mihaela Chraif, Claudiu Papasteri, Andrei Neacşu
157 - 170
Abstracts
An Intra and Inter-Topic Evaluation and Cleansing Method
Claudiu Muşat1, Marian-Andrei Rizoiu2, Ştefan Trauşan-Matu1,3
1Universitatea Politehnica Bucureşti
Bd. Splaiul Independenţei, nr. 313 060032, Bucureşti
E-mail: claudiu.musat@cs.pub.ro
2Laboratoire ERIC, Université Lyon 2
5, Avenue P. Mendès France 69676 Bron
E-mail: Marian-Andrei.Rizoiu@univ-lyon2.fr3Institutul de Cercetări pentru Inteligenţa Artificială
Calea 13 Septembrie nr.13, Bucureşti
E-mail: trausan@cs.pub.ro
Abstract. Topic modeling is a growing research field and novel ways of interpreting and evaluating results are necessary. We propose a method for evaluating and improving the performance of topic models generating algorithms relying on WordNet data. We first propose a measure for determining a topic model’s fitness factoring in its broadness and redundancy. Then, for each individual topic, the amount of relevant information it provides, along with its most important words and related concepts are determined by defining a cohesion function based on the topic’s projection on WordNet concepts. The model as a whole is improved by eliminating each topic’s outliers with respect to the ontology projection. We define a inter topic ontology based distance and we further use it to investigate the impact of removing redundant topics from a model with regard to the overlap between topics’ ontological projections. Clustering similar topics into conceptually cohesive groups is tried as an alternative to pruning less relevant topics. Results show that evaluating and improving statistical models with WordNet is a promising research track that leads to more coherent topic models.
Keywords: Topic Modeling, WordNet, Ontology, LDA, Subtree, Evaluation, Improvement
Analysis of three instruments for measuring usability, satisfaction, and user experience in Romanian context
Daniela Maria Andrei, Adriana-Mihaela Guran
Babeş-Bolyai University, Faculty of Psychology and Education Sciences
No. 37, Republicii Street, Cluj-Napoca, Romania
E-mail: danielaandrei@psychology.ro, adriana@ics.ubbcluj.ro
Abstract. This paper focuses on the relation between the main concepts used in Human-Computer Interaction domain in order to study users’ perception of interactive products quality like usability, satisfaction, and user experience. In order to achieve this goal, we have proposed a reseach that verifies the psychometric qualities of the instruments used to measure the above mentioned concepts. Three such instruments have beean translated and adapted for romanian users – AttrakDiff 2.0., Questionnaire for User Interaction Satisfaction şi Software Usability Measurement Inventory. These instruments have been filled in by 213 users of the web site www.psychology.ro. The obtained results show that there are some deficiencies of the scales construct validity.
Keywords: usability, satisfaction, user experience, construct validity.
Researches regarding the acceptance of e-learning technologies
Dragoş Daniel Iordache
National Institute for Research and Development in Informatics – ICI Bucharest
8-10 Mareşal Averescu Street, 011455, Bucharest
E-mail: iordache@ici.ro
Abstract. Nowadays, the e-learning applications are integrated in most of curricular areas and scholar cycles. In this context, the perceived utility of these applications at end-user level is an important issue. A series of theories and models (Technology Acceptance Model - TAM, Innovation Diffusion Theory – IDT, Student Integration Model - SIM) have been developed regarding the acceptance of informatics technologies in general and the e-learning technologies in particular. This paper is focussing on the main aspects of the acceptance theories and models in the context of e-learning applications.
Keywords: acceptance, e-learning, TAM.
Developing and Using Teaching Materials in eGLE Environment
Dorian Gorgan, Teodor Ştefănuţ, Mircea Mărginean, Victor Bâcu
Universitatea Tehnică din Cluj-Napoca, Str. Memorandumului, Nr.28, Cluj-Napoca
E-mail: {dorian.gorgan, teodor.stefanut, victor.bacu}@cs.utcluj.ro, margineanmircea@yahoo.com
Abstract. The eLearning platforms have been intensively developed in the last decade by providing performant educational services at lower costs than the classical methods. Even so, the development has been significantly limited by the extensive requirement of the eLearning applications for high processing capacity and performant resources. The Grid architecture, which substitutes the single server based architecture, provides solutions for the domains such as management and processing of huge quantities of data (e.g. satellite images, 3D simulations, etc), distributed data processing, and distributed processing over a great number of computing workstations. This paper presents the eGLE platform that supports the using of resources for data storage and distributed processing in Grid systems, and the approach through which the lessons can be developed and executed in domains such as Earth Observation, massive spatial data processing, medicine, etc. It is highlighted as well a new possibility of developing educational materials by efficient mechanisms of repurposing and adapting of teaching objects already available.
Keywords: eGLE, eLearning platform, lesson, teaching material, user interaction, Grid computing.
Software tools for the analysis of subliminal testing tasks in facial microexpressions recognition
Mihai Aniţei, Mihaela Chraif, Claudiu Papasteri, Andrei Neacşu
Faculty of Psychology and Educational Sciences
University of Bucharest Panduri, no. 90
E-mail: anitei_mihai@yahoo.com , mihaelapopa14@yahoo.com
Abstract: The facial microexpresions had been situated in the main stream of research for over 5 decades. Therefore, Eakman highlighted two main directions: the possibility to learn the facial microepressions and to learn how to code and analyze the facial microexpresion in different situations. This study highlights the importance of facial microexpressions simulation in human memory retrieval. Learning to code and analyze the facial microexpressions od relevant for selection interview, education, selling and marketing. This way people can express conscious and unconscious the facial microexpressions. The role of the psychologist is focused on the facial microexpressions interpretation making the differences between the true or simulated emotions.
Keywords: emotions, memory retreival facial microexpressions, emotions detections.