Search

Text entry in smartphones remains a critical element of mobile HCI. It has been widely studied in lab settings, using primarily transcription tasks, and to a far lesser extent through in-the-wild (field) experiments. So far it remains unknown how well user behaviour during lab transcription tasks approximates real use. In this paper, we present a study that provides evidence that lab text entry behaviour is clearly distinguishable from real world use. Using machine learning techniques, we show that it is possible to accurately identify the type of study in which text entry sessions took place. The implications of our findings relate to the design of future studies in text entry, aiming to support input with virtual smartphone keyboards., Comment: Work carried out Oct 2016-Jun 2017, manuscript produced in June 2018

Future Time Traveller is a European project that aims at transforming career guidance of generation Z through an innovative, games-based scenario approach and to prepare the next generation for the jobs of the future. The pro-ject objective is to foster innovative thinking and future-oriented mindset of young people, through an innovative game-based virtual world environment. This environment helps them explore the future world, understand the trends that shape the future world of work, the emerging jobs, and the skills they will require. The Future Time Traveller project is implemented by a team of experts in 7 European countries (Bulgaria, Germany, Greece, Italy, Poland, Portugal, and United Kingdom). The project target groups include young people (genera-tion Z), career guidance practitioners and experts, and policymakers. This paper presents, in brief, the Future Time Traveller project and introduces the reader to the main features and functionalities of the 3-dimensional virtual world and the games developed in this environment., Comment: Published at the 10th International IEEE Conference on Information Intelligence Systems & Applications, IISA 2019, Patras, Greece, 15-17 July 2019

We introduce EigenRec; a versatile and efficient Latent-Factor framework for Top-N Recommendations that includes the well-known PureSVD algorithm as a special case. EigenRec builds a low dimensional model of an inter-item proximity matrix that combines a similarity component, with a scaling operator, designed to control the influence of the prior item popularity on the final model. Seeing PureSVD within our framework provides intuition about its inner workings, exposes its inherent limitations, and also, paves the path towards painlessly improving its recommendation performance. A comprehensive set of experiments on the MovieLens and the Yahoo datasets based on widely applied performance metrics, indicate that EigenRec outperforms several state-of-the-art algorithms, in terms of Standard and Long-Tail recommendation accuracy, exhibiting low susceptibility to sparsity, even in its most extreme manifestations -- the Cold-Start problems. At the same time EigenRec has an attractive computational profile and it can apply readily in large-scale recommendation settings., Comment: 23 pages. Journal version of the conference paper "Factored Proximity Models for Top-N Recommendation"

Making recommendations in the presence of sparsity is known to present one of the most challenging problems faced by collaborative filtering methods. In this work we tackle this problem by exploiting the innately hierarchical structure of the item space following an approach inspired by the theory of Decomposability. We view the itemspace as a Nearly Decomposable system and we define blocks of closely related elements and corresponding indirect proximity components. We study the theoretical properties of the decomposition and we derive sufficient conditions that guarantee full item space coverage even in cold-start recommendation scenarios. A comprehensive set of experiments on the MovieLens and the Yahoo!R2Music datasets, using several widely applied performance metrics, support our model's theoretically predicted properties and verify that NCDREC outperforms several state-of-the-art algorithms, in terms of recommendation accuracy, diversity and sparseness insensitivity., Comment: To appear in the Web Intelligence Journal as a regular paper

In the standard Random Surfer Model, the teleportation matrix is necessary to ensure that the final PageRank vector is well-defined. The introduction of this matrix, however, results in serious problems and imposes fundamental limitations to the quality of the ranking vectors. In this work, building on the recently proposed NCDawareRank framework, we exploit the decomposition of the underlying space into blocks, and we derive easy to check necessary and sufficient conditions for random surfing without teleportation., Comment: 13 pages. Published in the Volume: "Algorithms, Probability, Networks and Games, Springer-Verlag, 2015". (The updated version corrects small typos/errors)

In spite of the growing interest in interaction design, there remains a large user population that needs special interest: users with special needs. These users can dramatically benefit from software that better responds to their interaction needs, not to mention the fact that designing software that takes into account the special needs of such users makes software more easy to use for everyone. This paper presents PERIGRAMMA, a system designed to offer an integrated environment for the support of people with movement or cognitive impairments who offer secretarial support in a modern office environment. The system is currently in its final stage of implementation and offers an easily accessible environment of four applications: a word processor, and e-mail client, a calendar, and a Web publisher. Design considerations of the system, architecture and functionalities, and future work are discussed. (Author/AEF)

This paper describes the experience and the problems solved in the process of developing and integrating advanced World Wide Web-based services into the University of Patras (Greece) system. In addition to basic network services (e.g., e-mail, file transfer protocol), the final system will integrate the following set of advanced services: a Web-based information service, intranet services to support administrative operations within the campus, distance learning by means of online teletraining via the Web, teleworking facilities, videoconferencing facilities, and applications supporting collaborative work. The paper describes in detail the services provided by the system, system architecture, and the implementation and introduction of the services to users. This project has shown that the development of the services, as well as their integration and introduction to the users, has to follow a well-defined, user-oriented implementation plan. Two figures present the representation of Web servers in the campus network and the intranet architecture. Contains 19 references. (AEF)

This paper describes the design of an adaptive user model and its implementation in an advanced Web-based Virtual University environment that encompasses combined and synchronized adaptation between educational material and well-known communication facilities. The Virtual University environment has been implemented to support a postgraduate course. It aims to cover the fundamental needs of a student, providing a wide range of automatically renewable educational material on any subject chosen under the umbrella of a powerful set of supportive tools homogenized with the user's topic of interest. An overview of the Virtual University framework is given, followed by a description of the user profile model. Discussion then moves to curriculum and course adaptation and intelligent filtering in communication data. (Contains 24 references.) (AEF)