%T National Conference on Human-Computer Interaction - RoCHI 2015 %C Bucharest %D 24-25 September 2015 %G ISSN 2344–1690 %E Marian Dârdală %E Traian Rebedea %P 148 %W http://rochi2015.utcluj.ro %T Human Computer Interaction and societal impact – Can HCI influence public policy making and IT politics? %A Gulliksen Jan %P 1-4 %X Digitalization is a concept to encompass the fastest growing trend for societal development of modern times. Digitali za - tion happens everywhere, in schools, in business, in health care and in our private life. The digitalization gives also op - por tunities for political decisions and policy making to sup - port turning our society into a modern and efficient society. Research and research funding organizations are becoming more and more aware of the need to conduct research that proves some form of utility to the society and has some form of practical impact. There are several different ways of making resear ch that has practical relevance and that can contribute to changing and improving society. This keynote paper aims at discussing ways to plan, conduct research with the aim of improving the society and also show how we should make use of our research knowl edge and positions to influence politics and public policy making. %K Digitalization; policymaking , usability, accessibility %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Gulliksen.pdf %T Social Computing, HCI, Social Change and Peace %A Zaphiris Panayiotis %P 5-10 %X This paper reports work regarding the design, development and evaluation of a surface computing a pplication to support collaborative decision making . . The domain - independent application, so called Ideas Mapping , builds on the principle of Affinity Diagramming to allow participants to analyze a problem and brainstorm around possible solutions while the y actively construct a consensus artifact - - a taxonomy of their ideas. During idea generation, Ideas Mapping replicates physical post - it notes on a multi - touch tabletop. Additional functionality supports student collaboration and interaction around the or ganization of ideas into thematic categories associated with the problem at hand. We report on the functionality and user experience while interacting with the application which was designed and developed using a user - centered approach. We also report init ial findings regarding the affordances of surface computing for collaborative decision making . %K surface computing, user experience, collaborative decision making, CSCL %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Zaphiris.pdf %T Multi - Criteria Decision Making Software Products - A Comparison and Ranking in Terms of Usability and Functionality %A Constanta Zoie Radulescu %A Alexandru Balog %A Lidia Băjenaru %A Delia Mihaela Radulescu %P 11-14 %X A large number of multi criteria decision making (MCDM) software products have been developed in aca demia and business . The selection of the appropriate MCDM software product to solve a given decision problem is a difficult task. Users need adequate MCDM software that meets quality standards regarding usability and functionality, utility, reliability and computer efficiency. In this paper we make a comparison of six MCDM software products regarding usability and functional suitability. Then we rank the MCDM software products included in comparison, first for criteria of usability and functionality and sec ond only for criteria of usability. Ranking the six MCDM software products is a multi - criteria problem itself. %K Multi criteria decision making; Usability; Software Quality; Functional Suitability; Alternatives; Criteria %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Radulescu.pdf %T Seeking New Insights: A Design Thinking Approach to the Development of Persuasive Technology Aimed at Supporting Clients on a Weight Management Program %A Paul Doney %A Marc Fabri %P 15-20 %X The application of persuasive technology has been shown to be effective in a weight management context. However, it has been observed that the impact is not as significant as predicted. The aim of this project was to investigate whether a Design Thinking approach could generate new insights that could be used to drive the development of an innovative application to help people on their weight management journey. Findings show that although no rad ically new user needs were identified, the needs that users did express most pertinently are not effectively met by currently available technology . Further, we examine d the Design Thinking approach itself and s ought to identify criteria for the design of s uccessful insight gathering activities , through end - user engagement. We summarize these at the end of this paper. %K Persuasive technology; design thinking, weight management, service design, behavior change %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Doney.pdf %T A Motivational Model for Facebook Acceptance by University Students %A Dragoș Daniel Iordache %A Alexandru Balog %A Costin Pribeanu %A Vincentas Lamanauskas %P 21-24 %X As social networking websites become more and more widespread there is an increasing interest to analyze and explain their usage. Facebook is a web - based service that is very popular among university students. In this paper a motivational model is presented that explains Facebook acceptance by university students with two key factors: perceived usefulness and perceived enjoyment. The results show that perceived enjoyment is a stronger determinant than perceived usefulness. %K Facebook , motivational model, TAM , structural equation modeling %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Iordache.pdf %T Accessibility of Romanian Municipal Websites – Conformance with WCAG2 %A Costin Pribeanu %A Maria Gheorghe-Moisii %A Paul Fogarassy-Neszly %P 25-28 %X Several initiatives at European level exist that promote e - inclusion and web accessibility . Despite all concerns , the accessibility of municipal websites is still low. This paper presents a study regarding the con formance of 60 municipal websites in 2014 with WCAG2 ( Web Content Accessibility Guidelines ) . A comparison of results with similar data in 2011 shows a decrease in web accessibility that could be explained by the lack of regulations at national level and ba d practices in web development. Moreover, the evaluation revealed instability of results in time which makes it difficult assessing the progress . %K Web accessibility, WCAG2, accessibility checking tools, conformance, municipal websites %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Pribeanu.pdf %T Realistic Simulation of Environmental Phenomena – Snow Fall and Accumulation %A Sandra Al - Assaf %A Dorian Gorgan %P 29-36 %X One particular case of the intersection between the photorealistic presentation and the dynamics of 3D scene of objects is snow in nature, which presents behavioral aspects of the environment such as accumulation, partic le movement, and redistribution, with the added time element that allows change and progress analysis. Due to the complexity of the phenomenon, little to no attention has been given to the realism of the interaction, the attention being channeled only on t he visual aspects of it. The focus of this paper is to analyze different approaches of representing snow fall and accumulation effects in real time in such a digital ensemble in order to add a layer of realism and accurately reflect natural processes. The emphasis is put on the actual manifestations that take place in nature and the micro physics that pertain to the processes. Comparisons are made between different existing approaches to snow accumulation and a new particle hierarchy is imposed to suit both the technological requirements and to maintain the realism of scenes . %K Photorealistic Presentation; Environmental Phenomena; Snowing Phenomenon; Snow Fall; Snow Accumulation %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Al-Assaf.pdf %T Gamepad Vibration Methods to Help Blind People Perceive Colors %A Vlad Trifănică %A Alexandru Butean %A Alin Moldoveanu %P 37-40 %X Visually impaired people, completely or partially blind cannot perceive the surrounding environment as normal healthy peopl e can. Not knowing how colors and shapes look like is a serious penalty and they have to live with it an entire life. It is known that the human brain adapts and compensates with greater capabilities for hearing and touch when vision is low or missing , tha t is why blind people develop special skills and perform so good when it comes to music and kinetotherapy . Based on this information we are proposing a method that explains colors using vibration s. In this paper we would like to present a new way of transf orming an image to vibration by using the capabilities of an Xbox gamepad . During the study on real blind volunteers, t his kind of approach proved to be very effective and promising, allowing them to slightly understand how an image, painting or friend loo ks like. %K Vibration; colors, modern devices; visually impaired %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Trifanica.pdf %T Analyzing Computer Game Strategies through Visual Techniques %A Mircea Catalin Catana %A Dorian Gorgan %P 41-48 %X The paper presents and analyzes an application that can emulate different types of strategy games and provide significant specifications as to how the strategy impacts the outcome of the player experience. This application is meant to be used as a tool both by game developers, which can use it to calibrate their products and also by the game players , who will want to use it as a means to improve their strategies. The research explores the concept of strategy in games and tri es to define a metric for evaluating this concept. Due to the complexity of videogames, the computation of every outcome for every possible decision a player can make is impossible, so the research proposes a method of combining the human familiarity with the game concept and the processing power of the computer to search the wide solution space. The paper analyses a concrete example by building a test bed for the tower defense type games . %K Game Strategy; Visual Analytics; Visual Techniques; Tower Defense Games %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Catana.pdf %T Developing a Navigational 3D Audio Game with Hierarchical Levels of Difficulty for the Visually Impaired Players %A Oana Bălan %A Alin Moldoveanu %A Florica Moldoveanu %A Alexandru Butean %P 49-54 %X The Binaural Navigation Game is a 3D audio game with hierarchical levels of difficulty that can be used by both normal sighted or visually impaired players. The pur pose of the game is to test and train the sound localization skills, to entertain and to provide an alternative to the common video games available on the market nowadays. The sonification technique is based on the perception of 3D binaural sounds synthesi zed with non - individualized Head Related Transfer Functions (HRTFs) and on the inversely proportional sound intensity encoding of distance. Furthermore, we use an original method based on the simultaneous perception of two types of noise that aims to reduc e the incidence of front - back confusions. This game has been tested in an experimental procedure (comprised of a pre - test, a haptic - auditory feedback based training and a post - test session) in which 10 visually impaired subjects (with a percent of residual vision ranging from 0% to 15%) have participated. This paper aims to present the design and development of the Binaural Navigation Game, the Game Editor (an application that allows the experimenter to set the layout of new sets of levels) and the Binaural Game Analyzer, a tool used to visualize and evaluate the players’ performances. %K 3D sound; HRTF; audio game; navigation skills; orientation and mobility skills %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Balan.pdf %T Text Generation Starting From an Ontology %A Dragoş Alexandru Cojocaru %A Ștefan Trăușan-Matu %P 55-60 %X The subject of this paper is the development of an application which generates natural language text, starting from an OWL ontology. The Natural Language Generation , in the context of Semantic Web , represents a relatively new field of research, but due to the capabilities of the ontologies (central element of the Semantic Web) of being dynamically modified and completed with new information, the theme of the application is of great importance. The project employs Rhetorical Structure Theory to structure hie rarchically the ontological content, resulting in a human - like discourse structure. Since the Semantic Web is continuously adding machine - readable content , the user can take advantage of this impressive database of knowledge transformed into coherent texts for human w ith the aid of our application. %K Semantic Web; ontology; Rhetorical Structure Theory; natural language generation %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Cojocaru.pdf %T A Design Framework for Foreign Language Learning Applications %A Mihaela Colhon %P 61-66 %X In this article we present a method for generating and applying syntactic motivated patte rns in order to develop a foreign language learning mechanism. The patterns have been extracted from a parallel corpus that has been automatically annotated for morpho - syntactic descriptions and syntactic constituents. The proposed language learning framew ork is not design ed around the well - known list of words . Using this application, the user does not necessarily practice the foreign language lexicon, which is supposed to be known at a medium level. Instead, with this application, the user is guided to lea rn the so - called “ translation knowledge ”. %K Machine Translation, Learning Schema, Human - Computer Interaction %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Colhon.pdf %T Opinion Summarization for Hotel Reviews %A Bogdan Cristian Marchis %A Alexandru Tifrea %A Mihai - Cristian Volmer %A Traian Eugen Rebedea %P 67-74 %X This paper presents a new approach for finding the best n - grams that efficiently summarize a large set of reviews. The proposed unsupervised method uses a readability score and a representativeness score to select those n - grams that best convey the m ain opinions contained in the processed reviews. In order to further refine the selected n - grams, we use sentiment analysis and part of speech (POS) tagging to impose certain requirements that the n - grams that we are looking for should meet. Furthermore, t he best n - grams were classified into several topics, which allowed a better prevent ion of redundancy among the summarizing n - grams. Therefore we offer an unsupervised, mostly non - aspect based, unstructured opinion summarization algorithm that can be easily implemented for any web platform that accepts reviews, due to its genericity. In order to assess the results of our algorithm, we summarized hotel reviews extracted for the TripAdvisor 1 website. The algorithm produces readable results that convey relevant opinions about the hotels that we used for testing. %K Opinion summarization, opinion mining, natural language processing, n - grams, micropinions %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Marchis.pdf %T Automated Paper Annotation with ReaderBench %A Ionut Cristian Paraschiv %A Mihai Dascălu %A Ștefan Trăușan-Matu %A Philippe Dessus %P 75-80 %X The annotation of articles from a given domain and the generation of semantic me tadata can be considered a reliable foundation for creating a paper recommender system. Within this paper, the models from other previous researches are extended with the capability of visualiz ing articles and the most important concepts from a domain with in imposed timeframe s . This can be very useful for researchers to check out the most important publications from a given period , to view which are the trends and how a domain has evolved. Our previous analyses used the articles to build a paper graph and t o suggest the most relevant articles , given a user defined query in natural language. This research contains a use case and creates visual graph representations to enhance the overall perception of the evolution of a domain . %K Scientometrics; paper recommendation system; time analysis; discourse analysis; semantic similarity %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Paraschiv.pdf %T Conversational Agent that Models a Historical Personality %A Adrian Bogatu %A Dorin Rotarescu %A Traian Eugen Rebedea %A Stefan Ruseti %P 81-86 %X n this paper we discuss the current approaches in question answering (QA) and their applicability in building a conversational agent that models a historical figure that gives informative and relevant answers to user questions about the life of that personality. We analyze two main methods: one in which we use an ontology to build our knowledge base and one where we don't have a knowle dge base and we solve the answer sentence selection problem for question answering. We observed that the first method is better for answering more general questions and the second method can deal with more specific and complex lexically and syntactically q uestions. The implementation of the conversational agent relies on the two combined approaches, the second being a fallback option if the first method is not able to provide an answer. %K Conversational agent; natural language processing; information retrieval; question answering; ontologies; answer sentence selection %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Bogatu.pdf %T Disruptive Technologies – UV Protect – Smart Watch Application %A Andrei - Bogdan Baran %A Adrian Iftene %P 87-90 %X Health care industry is one of the most interesting domains where we can bring innovative and smart technologies that can have a big positive impact on our health. These days p eople are starting to be more and more concerned about their health and they are interested in having small wearable devices that allow them to be able to get real time data through different sensors regarding the environment or different activities they a re involved in. In this paper we will show how new disruptive technologies can be used to monitored the level of the ultraviolet radiation and then how the user can be notified about that. %K Disruptive Technologies; Smart Watch; Samsung Gear S; Ultraviolet Radiation %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Baran.pdf %T Introducing Basic Geometric Shapes to Visually Impaired People Using a Mobile App %A Bogdan Troanca %A Alexandru Butean %A Alin Moldoveanu %A Oana Bălan %P 91-94 %X The problem of blindness and other eye disabilities is highly important as it affects millions of people on the globe. In the same time, the number of modern touchscreen devices is increasing fast. They are widely spread and becom ing accessibl e for education purposes . For those who suffer from congenital visual disabilities is very difficult to imagine the world as it is and the struggle begins from the early school stages and continues for the rest of their lives. Modern touchscreen devices, a lso called smart devices, represent a viable solution for people with sight problems due to their rich multimedia experience. Thus, they can be used as assistive devices. This paper describes how learning basic geometric shapes using a smartph one or a tabl et can improve several important aspects like: general feeling of using touchscreen devices, perception of a basic figure’s shape by simply touching t he screen , intuition on how to follow a GPS map. This methodology repr esents only the initial stage from a long - term learning process that aims to help visually impaired people to understand and use the power of smart d evices in order to perceive the world around them as normal people do. %K Sound; vibration; mobile devices; visually impaired %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Troanca.pdf %T Indoor Localization and Navigation Using Phone Sensors and a 3D Model of the Building %A Szabolcs Orban %A Teodor Ștefănuț %P 95-100 %X This article presents an innovative approach in offer ing indoor navigation assistance based on mobile device sensors and a 3D model of the building . We will discuss the three main stages that are required in order to implement the proposed solution : (1) creation of the 3D model, (2) definition of the navigation attributes ( built to also support localization ) and (3) implementation of all the required functiona li ties in an Android application. One of our main concern s is related to the identification of the current location of the user in an indoor environment efficiently using the device's sensors. For this purpose w e will describe an algorithm that relies on t he accelerometer and the compass to provide accurate location information and to si mulate the movement of the user into the environment, without consuming too much energy . %K indoor localization, mobile device sensors, indoor navigation, virtual representation %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Orban.pdf %T An Approach for Detecting ID Frauds in a Traditional Voting System Using a Smartphone Stand %A Paul Strimbeanu %A Alexandru Butean %A Diana Butean %A Florica Moldoveanu %P 101-104 %X All over the world , the v oting systems are very important tools that contribute to the basic principles of democracy and equality . In every developing country , t he problem of online voting becomes a necessity, ther efore solutions must be found. Nowadays mobile smart devices are equipped with high performance lens and cameras, therefore they can capture high quality pictures in almost no time. Optical character recognition methods (OCR) are getting 99% accuracy on st andard font document s with little or no noise at all. Having this in mind we propose a system that verifies in real - time the ID of an elector, right before a traditional voting system procedure . This solution is based on a stand containing a mobile device that takes a quality picture of that ID and sends it to a server to extract the data. The use of such a system does not a ffect the actual voting process and does not interfere or relate with the voter’s choice at all. %K Mobile devices, E - government; voting system %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Strimbeanu.pdf %T Socialization Techniques in Virtual 3D Space %A George Marian Hotca %A Teodor Ștefănuț %A Dorian Gorgan %P 105-110 %X This paper presents the LivingRoom platform for online socialization within the 3D virtual space. The user is represented by an avatar that is moving around the virtual space and can communicate with other avatars. The audio and video communication among avatars is triggered by their interactions similarly with the human action within the real world. %K Virtual Space; Visual Techniques; User Interaction Techniques; Audio Communication; Video Communication; Avatar %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Hotca.pdf %T Gestural Recognition by a Four - Kinect Module in a CAVE "Le SAS" %A Saleh Salous %A Julien Newton %A Laure Leroy %A Safwan Chendeb %P 111-114 %X Among the various types of interactions in a virtual reality ( VR ) room, physical gestures such as moving one’s hands are one of the ways to communicate with the virtual environment. It is possible to capture those gestures with sensors, in our case the Microsoft Kinect. In the context of a large CAVE, not one but four Kinects are used to track the user and capture its gestures . However, the question of the detect ion of specific gestures by this system comes into play as the CAVE requires recognizing the user’s gestures in order to interpret them into an input . In this paper we focus on the gestural recognition ability of our CAVE applied to three specific gestures : Raising the right hand, raising the left hand and short hopping. Moreover, we provide experimental results showing that a Four - Kinect system provides more effective gesture recognition than a single sensor. %K Multi - Kinect; gestural interaction; gesture recognition; virtual reality; CAVE %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Salous.pdf %T Immersive Virtual Reality application using Google Cardboard and Leap Motion technologies %A Mihai Chifor %A Teodor Ștefănuț %P 115-120 %X Virtual Reality applications have known an accelerated development in the past few years stimulated by the advancements in the hardware capabilities and als o by the benefits from the similarity with the real world. However, the available solutions for immersive VR are still very expensive and often lack the friendliness expected on user interaction techniques. In this paper we will present a low cost, immersi ve , VR capable setup based on two new technologies: Google Cardboard and Leap Motion. The proposed solution is showcased using an educational application that allows its users to virtually visit Elmwood Park Zoo , Pennsylvania and learn more on the wild ani mals in the process. Most of the user interactions are performed through hand described gestures inspired from the real world, helping the users to accommodate more easily and perform naturally in the virtual environment. %K Virtual Reality; Google Cardboard; Leap Motion; immersive; educational %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Chifor.pdf %T Real Time Visualization of Crowd Dynamics Scenarios %A Dan Razvan Ilies %A Adrian Sabou %A Dorian Gorgan %P 121-128 %X This paper presents an approach to real - time simulation of crowd dynamics on GPU enabled computing architectures. We discuss challenges with parallelization of agent - based models, implementing parallel simulation algorithms, visualization and interaction with the simulated scene and, most importantly, ensuring communica tion and synchronization between all these processes. Our main objective is to provide interactive simulation of realistic models such as pedestrian dynamics, in which large crowds move and interact among themselves and with the environment. Simulation p arameters like scene complexity, scene composition, as well as the number of agents are varied in order to simulate different scenarios and to assess the impact on performance. %K Visualization; Crowd dynamics; Interactive simulation; Social forces; Social models; Graphics Processing Unit %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Ilies.pdf %T Real - time Video Processing in Web Applications %A Cristian Ionita %A Alexandru Barbulescu %P 129-132 %X The OpenGL ES standard is implemented in modern desktop and mobile browsers through the WebGL API. This paper explores the potential for using OpenGL ES hardware acceleration for real time video processing in standard HTML5 applications. We analy z e the WebGL performance across device types and compare it with the standard JavaScript and canvas performance. %K WebGL; GLSL; OpenGL ES; kernel; convolution matrix; JavaScript %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Ionita.pdf %T Diversifying Search Results Using Semantic Resources %A Cristian Neamtu %A Adrian Iftene %P 133-136 %X In the last years, multimedia content has grown increasingly over the Internet, especially in social networks (like Facebook or Flickr) , where users often post images using their mobil e devices. In these networks , the content is later used in search operations , when some users want to find something using a specific query. Nowadays, searching into these networks is primarily made using the title , description and the keywords associated to resources added by users that have posted the content. In this paper we address the problem of query ambiguity. T he usage of semantic resources, like ConceptNet and DBpedia ontologies , has been proven to retrieve a better set of results. %K Image Retrieval; Search Diversification; Semantic Resources; ConceptNet; DBpedia %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Neamtu.pdf %T Motives and Characteristics of Facebook Use by Students from a Romanian University %A Alexandru Balog %A Costin Pribeanu %A Ion Ivan %P 137-140 %X The increasing popularity of Facebook among university students is raising several research questions regarding the characteristics of use. In the context of modern school , the academic use and the us ag e relat ed to the university context are of special interest. This paper aims at analyzing the motives for the use of Facebook and the characteristics of Facebook use by students from a Romanian u niversity . The results show that the motives of using Facebook are m ainly related to communicat ing with friends, to find out what happens in their university and to keep in touch with former high school colleagues. The results revealed significant differences between male and female students in terms of motives of using, network size, frequency and duration of use. Female students have more Facebook friends and spend more time on Facebook tha n male students. Moreover, s ignificant differences exist between undergraduate and master students. %K Facebook, social networks, educational use of Facebook, motives of using Facebook %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Balog.pdf %T Movies Classification %A Daniel Gavril %A Adrian Iftene %P 141-144 %X Every device that is released nowadays has the capability to display videos. From small devices like smart phones to bigger ones likes desktops or smart TVs, movies are available at any time. Therefore, getting important, fast and reliable data about movies at any time and everywhere is very important when it comes to money. Computer users like to get live experiences based on their interests, searc hes or their personal profile a nd their needs include movies. When people g ather to someone’s place or a family unites on holidays, finding a good movie to watch for that moment becomes hard. There are different tastes in movies, persons that like drama more than science - fiction or some that will enjoy movies based on the directo r of that movie or important actors. Using a good search e ngine that might understand users desires based on recent searches or interests might come in handy. Movies Classification application runs on Windows operating systems and tries to understand user perspective when he tries to find a movie that might suit his tastes. The app updates live the suggested movies based on the customizable profile that every registered user must set. %K Movies Classification; Client - Server Architecture; User Profiling %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Gavril.pdf %T A Software Component for Polyglot Text - to - Speech Synthesis: User Interface and Beta Testing Results %A Paul Fogarassy-Neszly %A Zlatomir Zinveliu %A Costin Pribeanu %P 145-148 %X ext - to - speech synthesis has many applications in the area of assistive technologies for visually impaired people. Some applications require multilingual text - to - speech synthesis . In this case, multilingual text analysis and voice switching are desirable . In this paper an improved functional version (beta) of a software component for polyglot text - to - speech synthesis is presented. Beta testing results are useful to reveal the optimal level of par ameters and suggest new directions to improve the method and algorithms. Testing results show that the new version of the component is able to automatically detect the language with a reasonable accuracy from texts with a variable degree of fragmentation. %K Multilingual speech synthesis, language recognition, text - to - speech synthesis, assistive technologies beta testing, usability, accessibility %W http://rochi.utcluj.ro/articole/3/RoCHI-2015-Fogarassy-Neszly.pdf