Torou Elena, Katifori Akrivi, Vassilakis Costas, Lepouras Georgios, Halatsis Constantin
Proceedings of International Conference of Education, Research and Innovation (ICERI 2009), Madrid, November 16-18, 2009

Abstract:

This paper presents the results of a study on how historians conduct research in a historical archive, and the methodologies they use while searching. Historic research involves finding, using, interpreting and correlating information within primary and secondary sources, in order to understand past events. The collection of historical data is accomplished through methodical and comprehensive research in primary and secondary sources. An important factor in our study was to understand what kind of data and/or information historians are looking for in a library/historical archive, either printed or digitized, and which research methodologies or research models they use while they investigate a historical archive. Since this issue has not been addressed insofar, and therefore there are no methods for elucidating research methodologies or research models that historians employ / use, we formulated a questionnaire comprising of seven information retrieval tasks commonly addressed in the context of historic research. History researchers were asked to describe in detail how they would proceed in searching for the information they need for completing these tasks. Through this procedure we aimed to investigate the different ways a historian can use to tackle a specific question, examine whether there exists a common research methodology, and the historic researchers' expectations and preferences. The insight gained from this investigation can be used for educational purposes, since it could be useful in the creation / development of a methodology for conducting research on historical information. Furthermore, the findings can be exploited in the context of organizing documents within historical source repositories, so as to facilitate the retrieval of documents by historians; finally the presented findings can serve as a preliminary requirement analysis phase for building tools that will enable historians to access more rapidly and fully the information they need.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Torou Elena, Katifori Akrivi, Vassilakis Costas, Lepouras Georgios, Halatsis Constantin
Proceedings of the 1st International Conference on Digital Information Management (ICDIM 2006), Bangalore, India

Abstract:

Ontologies have been proven invaluable tools both for the semantic web and for personal information management. In the context of a historical archive an ontology may provide mean-ingful and efficient support for search tasks as well as be used as a tool for storage and presentation of historical data. The creation however of such an ontology is complex, since the digitized archive documents are not in text format and the concepts that must be captured may vary among different time periods. This work presents a user-centric methodological approach for ex-tracting the ontology of an historical archive focusing on the evaluation issues related to this process. The approach is exemplified through cases from its application in the University of Athens Historical Archive.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Maria Golemati, Akrivi Katifori, Costas Vassilakis, George Lepouras, Constantin Halatsis
Proceedings of the First IEEE International Conference on Research Challenges in Information Science (RCIS), Morocco 2007

Abstract:
User profiling is commonly employed nowadays to enhance usability as well as to support personalization, adaptivity and other user-centric features. Insofar, application designers model user profiles mainly in an ad-hoc manner, hindering thus application interoperability at the user profile level, increasing the amount of work to be done and the possibility of errors or omissions in the profile model. This work aims at creating a user profile ontology that incorporates concepts and properties used to model the user profile. Existing literature, applications and ontologies related to the domain of user context and profiling have been taken into account in order to create a general, comprehensive and extensible user model. This ontology can be used as a reference model, in order to alleviate the aforementioned issues. The model, available for download, is exemplified through its application in two different areas, personal information management and adaptive visualization.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Akrivi Katifori, Costas Vassilakis, George Lepouras, and Elena Torou
International Journal of Information Retrieval Research, 5(2), 2015

Abstract:
Incorporating digital tools in the business and scientific research workflows is at the moment an on-going process, challenging and demanding as every domain has its own needs in terms of data models and information retrieval methods. The information in some domains involves entity evolution, a characteristic that introduces additional tasks, such as finding all evolution stages of an entity, and poses additional requirements for the information retrieval process. In this paper, we present a user study aiming to investigate how the different aspects of ontology modelling affect the performance and effectiveness of users regarding information retrieval tasks that are carried out using visualization methods. The results of the user study are analyzed and guidelines for ontology design are offered.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Vassilis Poulopoulos, Costas Vassilakis, Angela Antoniou, Manolis Wallace, George Lepouras and Martin Lopez Nores
Proceedings of the Global Information Infrastructure and Networking Symposium (GIIS 2018), Special Session on IoT and Cultural Heritage Protection, 2018, Thessaloniki, Greece,

Abstract:
Creating stories for exhibitions is a fascinating and in parallel laborious task. As every exhibition is designed to tell a story, museum curators are responsible for analyzing each exhibit in order to extract messages that form a story and position accordingly the objects in correct order within the museum space. In this context, we analyze how the technological advances in the fields of sensors and the Internet of Things can be utilized in order to construct a “smart space”, where exhibits can communicate with the visitors and to each other and can be organized automatically so that they can generate rich, personalized, coherent and highly stimulating experiences. We present the architecture of the system named “exhiSTORY”, that intends to provide the appropriate infrastructure to be used in museums and places where exhibitions are held, in order to support smart exhibits. We discuss and analyze the architecture of the system and the ways of its application in a cultural space.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Alan Dix, Giorgos Lepouras, Akrivi Katifori, Costas Vassilakis, Tiziana Catarci, Antonella Poggi, Yannis Ioannidis, Miguel Mora, Ilias Daradimos, Nazihah Md.Akim, Shah Rukh Humayoun, Fabio Terella
Journal of Web Semantics, Volume 8, Issue 4, November 2010, Pages 394-408

Abstract:
This paper takes as its premise that the web is a place of action, not just information, and that the purpose of global data is to serve human needs. The paper presents several component technologies, which together work towards a vision where many small micro-applications can be threaded together using automated assistance to enable a unified and rich interaction. These technologies include data detector technology to enable any text to become a start point of semantic interaction; annotations for web-based services so that they can link data to potential actions; spreading activation over personal ontologies, to allow modelling of context; algorithms for automatically inferring ¡typing¢ of web-form input data based on previous user inputs; and early work on inferring task structures from action traces. Some of these have already been integrated within an experimental web-based (extended) bookmarking tool, Snip!t, and a prototype desktop application On Time, and the paper discusses how the components could be more fully, yet more openly, linked in terms of both architecture and interaction. As well as contributing to the goal of an action and activity-focused web, the work also exposes a number of broader issues, theoretical, practical, social and economic, for the Semantic Web.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Katifori Akrivi, Torou Elena, Vassilakis Costas, Lepouras Georgios, Halatsis Constantin, Daradimos Elias
Proceedings of the First IEEE International Conference on Research Challenges in Information Science (RCIS), Morocco 2007

Abstract:
Most ontology development methodologies and tools for ontology management deal with ontology snapshots, i.e. they model and manage only the most recent version of ontologies, which is inadequate for contexts where the history of the ontology is of interest, such as historical archives. This work presents a set of requirements for the modeling and visualization of a temporal ontology used as a tool for the representation of historical information. In accordance to these requirements, a visualization plug-in was designed and implemented, featuring a set of tools that enable users to efficiently examine ontology temporal characteristics such as class and instance evolution along the timeline.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Torou Elena, Katifori Akrivi, Vassilakis Costas, Lepouras Georgios, Halatsis Constantin
to appear in International Journal of Digital Libraries, Springer-Verlag

Abstract:

Historic research involves finding, using and correlating information within primary and secondary sources, in order to communicate an understanding of past events. In this process, historians employ their scientific knowledge, experience and intuition to formulate queries (who was involved in an event, when did an event occur etc), and subsequently try to locate the pertinent information from their sources. In this paper, we investigate how historians formulate queries, which query terms are chosen, and how historians proceed in searching for related information in sources. The insight gained from this investigation can be subsequently used for organizing documents within historical source repositories and building tools that will enable historians to access the needed information more rapidly and fully.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Costas Vassilakis, Angeliki Antoniou, George Lepouras, Manolis Wallace, Ioanna Lykourentzou, and Yannick Naudet
In Proceedings of the 2nd International Conference on Digital Heritage (Euromed), 2016

Abstract:
Human History, is a huge mesh of interrelated facts and concepts, spanning beyond borders, encompassing global aspects and finally constituting a shared, global experience. This is especially the case regarding European history, which is highly interconnected by nature; however, most History-related experiences that are today offered to the greater public, from schools to museums, are siloed. The CrossCult project aims to provide the means for offering citizens and cultural venue visitors a more holistic view of history, in the light of cross-border interconnections among pieces of cultural heritage, other citizens viewpoints and physical venues. To this end, the CrossCult project will built a comprehensive knowledge base encompassing information and semantic relationships across cultural information elements, and will provide the technological means for delivering the contents of this knowledge base to citizens and venue visitors in a highly personalized manner, creating narratives for the interactive experiences that maximise situational curiosity and serendipitous learning. The CrossCult platform will also exploit the cognitive/emotional profiles of the participants as well as temporal, spatial and miscellaneous features of context, including holidays and anniversaries, social media trending topics and so forth.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Jenny Rompa, Christos Tryfonopoulos, Costas Vassilakis, George Lepouras
Demo at the 17th International Conference on Extending Database Technology, 2014, Athens, Greece

Abstract:

Users nowadays need to manage large amounts of information, including documents, e-mails, contacts, and multimedia content. To facilitate the tasks of organisation, maintenance, and retrieval of personal information, a number of semantics-based methods have emerged; these methods employ (personal) ontologies as an underlying infrastructure for organising and querying the personal information space. In this paper we present OntoFM, a novel personal information management tool that offers a mindmap-inspired interface to facilitate user interactions with the information base. Besides serving as an information retrieval aid, OntoFM allows the user to specify and update the semantic links between information items, constituting thus a complete personal information management tool.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Rompa, J., Lepouras, G., Vassilakis C., and Tryfonopoulos
Demo at the 10th International Web Conference, 2011, Bonn, Germany

Abstract:

OntoFM is a novel file manager that bases its interactivity on the user¢s personal ontology, offering semantic browsing and searching mechanisms for locating files, a mind map inspired ontology visualization, and simple-to-use intuitive functionality that encourages less experienced users. The implementation of OntoFM is based on Protege, an extensible open source ontology editor and knowledge-base framework. The file manager is implemented as a Protege tab widget, retrieving information from your personal ontology. Ontology visualization is based upon the OntoGraf plug-in which has been extended to comply with the mind map paradigm. Currently the ontology visualization pane permits only navigational functions, while other ontology management functions have been hidden to ease the complexity of the user interface.

Demo material:http://www.uop.gr/~trifon/OntoFM

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Akrivi Katifori, Costas Vassilakis, Alan Dix
Cognitive Systems Research, Special Issue on Brain Informatics, Volume 11, Issue 1, March 2010, Pages 25-41

Abstract:

Ontologies, as knowledge engineering tools, allow information to be modelled in ways resembling to those used by the human brain, and may be very useful in the context of personal information management (PIM) and Task Information Management (TIM). This work proposes the use of ontologies as a long-term knowledge store for PIM-related information, and the use of spreading activation over ontologies in order to provide context inference to tools that support TIM. Details on the ontology creation and content are provided, along with a full description of the spreading activation algorithm and its preliminary evaluation.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Akrivi Katifori, Costas Vassilakis
poster presentation in the International Symposium on "Information & communication technologies in cultural heritage", Ioannina, Greece, October 16-18, 2008

Abstract:

Ontologies have been proven invaluable tools in areas like the semantic web and personal information management. There have been many research efforts to create ontologies and supporting tools for Natural Sciences and Biology in particular (e.g. the GO (http://www.geneontology.org/) ontology and supporting tools). However, the domain of History, the science of studying, recording and organizing the knowledge of the past, has yet to benefit from adopting ontologies. In this work, we present our findings in this area, focusing on the aspects of ontology modeling and ontology visualization.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Akrivi Katifori, Constantin Halatsis, George Lepouras, Costas Vassilakis, Eugenia Giannopoulou
ACM Computing Surveys, Volume 39 , Issue 4

Abstract:

Ontologies, as sets of concepts and their interrelations in a specific domain, have proven to be a useful tool in the areas of digital libraries, the semantic web and personalized information management. As a result, there is a growing need for effective ontology visualization for design, management and browsing. There exist several ontology visualization methods and also a number of techniques used in other contexts that could also be adapted for ontology representation. The purpose of this work is to present these techniques and categorize their characteristics and features in order to assist method selection and promote future research in the area of ontology visualization.

Article available through the ACM Author-izer service:

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Katifori, V., Golemati, M., Lepouras, G., Halatsis, C.
proceedings of the CSITeA-04 conference, December 27-29, Cairo, Egypt, 2004.

Abstract:

In the age of digital information more and more digital libraries and historical archives are using information systems in order to facilitate the document retrieval and provide better visualization of the search results and document presentation. Much research has been done in the field of digital libraries, but in the case of historical archives, which have particular needs, this is not the case. To this end, we investigate the use of new tools, which are based on the ontology of the historical archive in order to provide a new and effective method for document retrieval in a dynamic environment which will take into account the collaboration needs of the users.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Akrivi Katifori, Costas Vassilakis, Ilias Daradimos, George Lepouras, Yannis Ioannidis, Alan Dix, Antonella Poggi, Tiziana Catarci
Proceedings of PIM, CHI 2008

Abstract:

Ontologies offer a flexible and expressive layer of abstraction, very useful for capturing the semantics of information repositories and facilitating their retrieval either by the user or by the system to support user tasks. This work presents an ontology-based user profiler, in the context of a Personal Interaction Management System (PIMS). The profiler, based on an ontology of the users¢ domain, enables them to create their personal ontology by initially choosing one of the available template ontologies as a starting point, which they subsequently populate and customize. The profiler employs a web interface which allows users to populate their personal ontology through forms, hiding ontology complexities and peculiarities. Forms are dynamically generated through ontology views, which are specified by ontology designers.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Vassilis Poulopoulos, Costas Vassilakis, Angela Antoniou, George Lepouras and Manolis Wallace
Proceedings of Euromed 2018, October 2018, Cyprus,

Abstract:
Nowadays, more and more cultural venues tend to utilize social media as a main tool for marketing, spreading their messages, engaging public and raising public awareness towards culture. It comes to a point where the massive of content in social media makes it a tedious procedure to contact the appropriate audience, the people that would really be stimulated by cultural information. In this notion, we assume that establishing conversations of high impact can possibly guide the cultural venues to audiences that can benefit more. These conversations usually include the so called influencers, users whose opinion can affect many people on social media; the latter usually referred to as followers. In this research paper we examine the characteristics of the influencers that can affect the procedures of a cultural venue on social media. The research is done within the scope of "CrossCult" EU funded project.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Stavroula Bampatzia, Ioannis Bourlakos, Angeliki Antoniou, Costas Vassilakis, George Lepouras, Manolis Wallace
Proceedings of the 2016 Games and Learning Alliance Conference (GALA 2016)

Abstract:
Wishing to connect cultural heritage, games and social networks, the present work describes games to be used within the framework of a European H2020 project. For the purposes of supporting the museum visit, before, during and after, 5 games were designed for social networks to accomplish user profiling, to promote the museum and the application through social network dissemination, to introduce museum items and themes and to also function as visit souvenirs. The games are also presented in a generic framework for games in cultural heritage, which has been used successfully in the past.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Alan Dix, Akrivi Katifori, Giorgos Lepouras, Costas Vassilakis and Nadeem Shabir
International Journal of Semantic Computing, Special issue on Web Scale Reasoning, Volume: 4, Issue: 1(2010) pp. 59-102

Abstract:
This paper describes methods to allow spreading activation to be used on web-scale information resources. Existing work has shown that spreading activation can be used to model context over small personal ontologies, which can be used to assist in various user activities, for example, in autocompleting web forms. This previous work is extended and methods are developed by which large external repositories, including corporate information and the web, can be linked to the user’s personal ontology and thus allow automated assistance that is able to draw on the entire web of data. The basic idea is augment the personal ontology with cached data from external repositories, where the choice of what data to fetch or discard is related to the level of activation of entities already in the personal ontology or cached data. This relies on the assumption that the working set of highly active entities is relatively small; empirical results are presented, which suggest these assumptions are likely to hold. Implications of the techniques are discussed for user interaction and for the social web. In addition, warm world reasoning is proposed, applying rule-based reasoning over activate entities, potentially merging symbolic and sub-symbolic reasoning over web-scale knowledge bases.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Nazihah Md. Akim, Alan Dix, Akrivi Katifori, Giorgos Lepouras, Nadeem Shabir, Costas Vassilakis
ACM WebSci 11, poster presentation

Abstract:
Various forms of spreading activation has been used in a number of web systems, not least in the PageRank algorithm. In our own work we have been using this as a technique for managing context over small and large ontologies, and both our own work and that in LarKC suggests that spreading activation has the potential to aid in reasoning over web-scale data sets including the growing set of linked open data resources. Of particular importance is that spreading activation can be applied locally to a dynamic self-selecting working set of an (practically) unbound linked data collection, as well as globally to the entire collection. However, this potential does not come without problems, some concerning the nature of the algorithm on any large data set, and some more to do with the particular nature of linked open data.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Costas Vassilakis, Angeliki Antoniou, George Lepouras, Vassilis Poulopoulos, Manolis Wallace, Stavroula Bampatzia and Ioannis Bourlakos
Social Networks Analysis and Mining, Springer, 7(40), December 2017

Abstract:
In this paper, we examine how social media can be linked to cultural heritage and in particular how we can incorporate games, social networks, history reflection and culture. More specifically, we explore the following aspects: (a) how social media sites can be integrated into the museum user experience (b) how user interactions within the social media, both within the context of the museum experience and outside it, can be exploited to enhance the quality of recommendations made to the users, (c) how trending topics from social media can be used to link museum exhibits with today’s topics of interest and (d) how multi-level related terms extraction from social media data can lead to proposals for reflections to users. The end goal is to provide increased stimuli for users to study exhibits deeper and reflect on them, as well as to trigger discussion between the users, thus maximizing the impact of a museum visit.

Read the article online via

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Manolis Wallace, Panos Alexopoulos, Ioannis Papafragkos and Costas Vassilakis
Proceedings of the 6th International Workshop on Semantic media adaptation and personalization, December 1-2, 2011 Vigo (Spain), IEEE press. Abstract
Manual ontology development is clearly a strenuous task. Whilst a variety of ontological engineering methodologies exist, their actual application is far from trivial, mainly due to the widely diverse nature of the tasks involved. In this work we study these tasks and identify the different types of human experts that are best suited to perform each one. As a result, we present a cooperative version of an ontological engineering methodology, together with a graphical tool that supports it.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Vassilis Poulopoulos, Costas Vassilakis, Manolis Wallace, Angela Antoniou and George Lepouras
Proceedings of SMAP 2018, 6-7 September 2018, Zaragoza, Spain,

Abstract:
Social media have gained the majority of attention on the Internet having an extreme number of daily visitors worldwide. The amount of information exchanged is vast, while users have become equally producers and consumers of data. Words like “trending”, “influencers”, “likes” and “viral” are in the daily agenda of data analyzers, as they are associated with factors that play an important role in the influence of social media content to its audience. These aspects are nowadays strongly taken into account by organizations that want to draw the public’s attention to the content they deliver, and in this context cultural institutions have already started to take under great consideration not only their presence in social media, but also the monitoring and exploitation of social media dynamics. In this paper we propose a method that can enable cultural venues to benefit from matches between their own content and ongoing discussions on social media. More specifically we extract trending topics that can be related semantically with the content of a cultural institute and examine how a venue can benefit by exploiting these matches. The proposed approach has been developed in the scope of the “CrossCult” H2020 project, and has been experimentally tested by analyzing the case of Twitter in Greek language.

Stavroula Bampatzia, Omar Gustavo Bravo-Quezada, Angeliki Antoniou, Martin Lopez Nores, Manolis Wallace, George Lepouras, and Costas Vasilakis
In Proceedings of the 2nd International Keystone Conference (IKC), 2016

Abstract:
CrossCult is a newly started project that aims to make reflective history a reality in the European cultural context. In this paper we examine how the project aims to take advantage of advances in semantic technologies in order to achieve its goals. Specifically, we see what the quest for reflection is and, through practical examples from two of the project's flagship pilots, explain how semantics can assist in this direction.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

George Lepouras, Akrivi Katifori, Costas Vassilakis, Angeliki Antoniou, Nikos Platis
Proceedings of the 5th Conference on Information, Intelligence, Systems & Application (IISA2014)

Abstract:

In this paper, we present the vision of an open source learning analytics platform, able to harvest data from different sources, including e-learning platforms and environments, registrar's information systems, alumni systems, etc., so as to provide all stakeholders with the necessary functionality to make decisions on the learning process. The platform's architecture is modular, allowing the introduction of new functionality or connection to new systems to collect needed data. All data can be analyzed and presented though interactive visualizations to find correlations between metrics, to make predictions for students or student groups, to identify best practices for instructors and let them explore 'what-if' scenarios, to offer students personalized recommendations and personalized detailed feedback, etc. Our objective is to inform and empower all stakeholders to improve the learning experience.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

M. Golemati, A. Katifori, C. Vassilakis, G. Lepouras, C. Halatsis
An extendable ontology for user profiles

Stavroula Bampatzia, Angeliki Antoniou, George Lepouras, Costas Vasilakis, and Manolis Wallace
In Proceedings of the International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP), 2016

Abstract:
CrossCult H2020 is a European project, the aim of which is the reflection of history in a cultural setting. In this paper, we describe how social media can be linked to cultural heritage and in particular how we can incorporate games, social networks, history reflection and culture. The paper presents the case study of one of the project pilots, to show how history reflection can be enhanced with the use of social networks.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Akrivi Katifori, Costas Vassilakis, Alan Dix
Proceedings of CSKGOI, within IUI 2008

Abstract:

Recent research in the domain of Personal Information Management has recognized the need for a paradigm shift towards a more activity-oriented system. Ontologies, as semantic networks with a structure not dissimilar to the one used by the human brain for storing long-term knowledge, may be very useful as the basis of such a system. This work proposes the use of spreading activation over ontologies in order to provide to a task-based system and its associated tools with methods to record semantics related to documents and tasks and to support user context inference.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

I. Daradimos, A. Katifori, C. Vassilakis,
Proceedings of IEEE RCIS 2008

Abstract:
The recent progress of the World Wide Web has created new needs for information sharing in virtual communities. WhereRU is a multiuser GPS position reporting system that allows users to make their location publicly available as well as associate it with information on places, persons and events that may later also serve as reminders of the their experiences when traveling.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Costas Vassilakis, Vassilis Poulopoulos, Angeliki Antoniou, Manolis Wallace, George Lepouras, and Martín Lopez Nores
Future generation of computer systems, Elsevier, vol. 81, p.p. 542-556, April 2018

Abstract:
Museum exhibitions are designed to tell a story; this story is woven by curators and in its context a particular aspect of each exhibit, fitting to the message that the story is intended to convey, is highlighted. Adding new exhibits to the story requires curators to identify for each exhibit its aspects that fit to the message of the story and position the exhibit at the right place in the story thread. The availability of rich semantic information for exhibits, allows for exploiting the wealth of meanings that museum exhibits express, enabling the automated or semi-automated generation of practically countless stories that can be told. Personalization algorithms can then be employed to choose from these stories the ones most suitable for each individual user, based on the semantics of the stories and information within the user profile. In this work we examine how opportunities arising from technological advances in the fields of IoT and semantics can be used to develop smart, self-organizing exhibits that cooperate with each other and provide visitors with comprehensible, rich, diverse, personalized and highly stimulating experiences. These notions are included in the design of a system named exhiSTORY, which also exploits previously ignored information and identifies previously unseen semantic links. We present the architecture of the system and discuss its application potential.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Costas Vassilakis, George Lepouras, Akrivi Katifori
Technical Report TR-SSDBL-06-001, SDBS Lab, University of Peloponnese, 2006.

Abstract:

This work is an extension of the Protégé tool to accommodate the modeling and presentation of entity history, i.e. past values of properties and/relationships; each such value is timestamped with the period that it was (or will be) valid in the real world. To this end, the presented extension provides:

1. integrated support for data types expressing time quantities - more specifically dates (individual points in time) and periods (anchored segments of the time axis).
2. data types for storing histories of properties of different types (strings, integers, floats, booleans and instances [i.e. relationships]).

The extension can be used in contexts that the modeling of entities' history is important, such as historical archives, museums, etc.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Panagiotis Giannikopoulos and Costas Vassilakis
International Journal of Web Engineering and Technology, vol 7(3), 2012

Abstract:
In contemporary internet architectures, including server farms and blog aggregators, web log data may be scattered among multiple cooperating peers. In order to perform content personalization through provision of recommendations on such architectures, it is necessary to employ a recommendation algorithm; however the majority of such algorithms are centralized, necessitating excessive data transfers and exhibiting performance issues when the number of users or the volume of data increase. In this paper we propose an approach where the clickstream information is distributed to a number of peers, which cooperate for discovering frequent patterns and for generating recommendations, introducing (a) architectures that allow the distribution of both the content and the clickstream database to the participating peers and (b) algorithms that allow collaborative decisions on the recommendations to the users, in the presence of scattered log information. The proposed approach may be employed in various domains, including digital libraries, social data, server farms and content distribution networks.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Ioanna Lykourentzou, Xavier Claude, Yannick Naudet, Eric Tobias, Angeliki Antoniou, George Lepouras and Costas Vasilakis
Proceedings of MASIE 2013 Workshop, co-located with the 9th International Conference on Intelligent Environments IE'13

Abstract:
This paper investigates the effect that smart routing and recommendations can have on improving the Quality of Experience of museum visitors. The novelty of our approach consists of taking into account not only user interests but also their visiting styles, as well as modeling the museum not as a sterile space but as a location where crowds meet and interact, impacting each visitor’s Quality of Experience. The investigation is done by an empirical study on data gathered by a custom-made simulator tailored for the museum user routing problem. Results are promising and future potential and directions are discussed.

Note:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris, Costas Vassilakis, and Panayiotis Georgiadis
chapter in: Current Trends on Knowledge-Based Systems: Theory and Applications, to be published at January 2017
Abstract:

We introduce a novel knowledge-based recommendation algorithm for leisure time information to be used in social networks, which enhances the state-of-the-art in this algorithm category by taking into account (a) qualitative aspects of the recommended places (restaurants, museums, tourist attractions etc.), such as price, service and atmosphere, (b) influencing factors between social network users, (c) the semantic and geographical distance between locations and (d) the semantic categorization of the places to be recommended. The combination of these features leads to more accurate and better user-targeted leisure time recommendations.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Transactions on Large-scale Data and Knowledge-Centered Systems (to appear)

Abstract:
The most widely used similarity metrics in collaborative filtering, namely the Pearson Correlation and the Adjusted Cosine Similarity, adjust each individual rating by the mean of the ratings entered by the specific user, when computing similarities, due to the fact that users follow different rating practices, in the sense that some are stricter when rating items, while others are more lenient. However, a user’s rating practices change over time, i.e. a user could start as lenient and subsequently become stricter or vice versa; hence by relying on a single mean value per user, we fail to follow such shifts in users’ rating practices, leading to decreased rating prediction accuracy. In this work, we present a novel algorithm for calculating dynamic user averages, i.e. time-in-point averages that follow shifts in users’ rating practices, and exploit them in both user-user and item-item collaborative filtering implementations. The proposed algorithm has been found to introduce significant gains in rating prediction accuracy, and outperforms other dynamic average computation approaches that are presented in the literature.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Transactions on Large-scale Data and Knowledge-Centered Systems, to appear

Abstract:
The most widely used similarity metrics in collaborative filtering, namely the Pearson Correlation and the Adjusted Cosine Similarity, adjust each individual rating by the mean of the ratings entered by the specific user, when computing similarities, due to the fact that users follow different rating practices, in the sense that some are stricter when rating items, while others are more lenient. However, a user’s rating practices change over time, i.e. a user could start as lenient and subsequently become stricter or vice versa; hence by relying on a single mean value per user, we fail to follow such shifts in users’ rating practices, leading to decreased rating prediction accuracy. In this work, we present a novel algorithm for calculating dynamic user averages, i.e. time-in-point averages that follow shifts in users’ rating practices, and exploit them in both user-user and item-item collaborative filtering implementations. The proposed algorithm has been found to introduce significant gains in rating prediction accuracy, and outperforms other dynamic average computation approaches that are presented in the literature.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Transactions on Large-Scale Data- and Knowledge-Centered Systems, special issue on Consistency and Inconsistency in Data-centric Applications, Springer
Abstract:

Recommender systems are based on information about users' past behavior to formulate recommendations about their future actions. However, as time goes by the interests and likings of people may change: people listen to different singers or even different types of music, watch different types of movies, read different types of books and so on. Due to this type of changes, an amount of inconsistency is introduced in the database since a portion of it does not reflect the current preferences of the user, which is its intended purpose.
In this paper, we present a pruning technique that removes old aged user behavior data from the ratings database, which are bound to correspond to invalidated preferences of the user. Through pruning (1) inconsistencies are removed and data quality is upgraded, (2) better rating prediction generation times are achieved and (3) the ratings database size is reduced. We also propose an algorithm for determining the amount of pruning that should be performed, allowing the tuning and operation of the pruning algorithm in an unsupervised fashion.
The proposed technique is evaluated and compared against seven aging algorithms, which reduce the importance of aged ratings, and a state-of-the-art pruning algorithm, using datasets with varying characteristics. It is also validated using two distinct rating prediction computation strategies, namely collaborative filtering and matrix factorization. The proposed technique needs no extra information concerning the items' characteristics (e.g. categories that they belong to or attributes' values), can be used in all rating databases that include a timestamp and has been proved to be effective in any size of users-items database and under two rating prediction computation strategies.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris, Dionysios Vasilopoulos, Costas Vassilakis, Dimitris Spiliotopoulos
SoDa Technical report TR-19001

Abstract:
In this technical report, we present the experimental findings from applying an algorithm that considers virtual near neighbors (VNNs) in the rating prediction formulation process, in order to increase coverage in the context of sparse datasets.
To this end, the algorithm is applied to seven sparse datasets, which are widely used in recommender system research. Additionally, the algorithm is applied to one dense dataset, in order to gain insight on the performance of the proposed algorithm in this class of datasets, as well.
In short, the algorithm introduces the concept of VNNs i.e. virtual users, which are created from the combination of real ones, in order to be used as candidate NNs in the rating prediction computation process.
In these experiments, the optimal values for the parameters that are used in the algorithm are investigated and more specifically, the thresholds that two individual users can constitute a VNN.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Service Oriented Computing and Applications, Springer, 11(4), pp. 393–409, December 2017

Abstract:
In this paper, we introduce a novel recommendation algorithm, which exploits data sourced from web services provided by the Internet of Things in order to produce more accurate venue recommendations. The proposed algorithm provides added value for the web services offered by the Internet of Things and enhances the state-of-the-art in this algorithm category by taking into account (a) web of things data regarding the contexts of the user and the context of the venues to be recommended (restaurants, movie theatres, etc.), such as the user’s geographical position, road traffic and weather conditions, (b) qualitative aspects of the venues, such as price, atmosphere or service, (c) the semantic similarity of venues and (d) the influencing factors between social network users, derived from user participation in social networks. The combination of these features leads to more accurate and better user-targeted recommendations. We also present a framework which incorporates the above characteristics, and we evaluate the presented algorithm, both in terms of performance and recommendation quality.

Read the article online via

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Informatics, 5(21): Special Issue “Advances in Recommender Systems”, 2018

Abstract:
One of the major problems that social networks face is the continuous production of successful, user-targeted information in the form of recommendations, which are produced exploiting technology from the field of recommender systems. Recommender systems are based on information about users’ past behavior to formulate recommendations about their future actions. However, as time goes by, social network users may change preferences and likings: they may like different types of clothes, listen to different singers or even different genres of music and so on. This phenomenon has been termed as concept drift. In this paper: (1) we establish that when a social network user abstains from rating submission for a long time, it is a strong indication that concept drift has occurred and (2) we present a technique that exploits the abstention interval concept, to drop from the database ratings that do not reflect the current social network user’s interests, thus improving prediction quality.

Full text

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Proceedings of the 19th IEEE International Conference on business informatics (CBI17)

Abstract:
Users that populate ratings databases, such as IMDB, follow different marking practices, in the sense that some are stricter, while others are more lenient. This aspect has been captured by the most widely used similarity metrics in collaborative filtering, namely the Pearson Correlation and the Adjusted Cosine Similarity, which adjust each individual rating by the mean of the ratings entered by the specific user, when computing similarities. However, relying on the mean value presumes that the users' marking practices remain constant over time; in practice though, it is possible that a user's marking practices change over time, i.e. a user could start as strict and subsequently become lenient, or vice versa. In this work, we propose an approach to take into account marking practices shifts by (1) introducing the concept of dynamic user rating averages which follow the users' marking practices shifts, (2) presenting two alternative algorithms for computing a user's dynamic averages and (3) performing a comparative evaluation among these two algorithms and the classic static average (unique mean value) that the Pearson Correlation uses.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Proceedings of the 22nd IEEE Symposium on Computers and Communications (ISCC17)

Abstract:
In this paper, we introduce a pruning algorithm which removes aged user ratings from the rating database used by collaborative filtering algorithms, in order to (1) improve prediction quality and (2) minimize the rating database size, as well as the rating prediction generation time. The proposed algorithm needs no extra information concerning the items' characteristics (e.g. categories that they belong to or attributes' values) and can be used with all rating databases that include a timestamp. Furthermore, we propose and validate a method for identifying the most prominent combination of a pruning algorithm and a pruning level for datasets, allowing thus to perform the selection of pruning algorithm and pruning level in an unsupervised fashion.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Proceedings of The Fourth IEEE International Conference on Big Data Intelligence and Computing (DataCom 2018)

Abstract:
When rating predictions are computed in user-user collaborative filtering, each individual rating is typically adjusted by the mean of the ratings entered by the specific user. This practice takes into account the fact that users follow different rating practices, in the sense that some are stricter when rating items, while others are more lenient. However, users’ rating practices may also differ in rating variability, in the sense that some user may be entering ratings close to her mean, while another user may be entering more extreme ratings, close to the limits of the rating scale. In this work, we (1) propose an algorithm that considers users’ ratings variability in the rating prediction computation process, aiming to improve rating prediction quality and (2) evaluate the proposed algorithm against seven widely used datasets considering three widely used variability measures and two user similarity metrics. The proposed algorithm, using the “mean absolute deviation around the mean” variability measure, has been found to intro-duce considerable gains in rating prediction accuracy, in every dataset and under both user similarity metrics tested.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris and Costas Vassilakis
Proceedings of The Fourth IEEE International Conference on Big Data Intelligence and Computing (DataCom 2018)

Abstract:
Collaborative filtering systems analyze the ratings databases to identify users with similar likings and preferences, termed as near neighbors, and then generate rating predictions for a user by examining the ratings of his near neighbors for items that the user has not yet rated; based on rating predictions, recommenda-tions are then formulated. However, these systems are known to exhibit the “gray sheep” problem, i.e. the situation where no near neighbors can be identified for a number of users, and hence no recommendation can be formulated for them. This problem is more intense in sparse datasets, i.e. datasets with relatively small number of ratings, compared to the number of users and items. In this work, we propose a method for alleviating this problem by exploiting user dissimilarity, under the assumption that if some users have exhibited opposing preferences in the past, they are likely to do so in the future. The proposed method has been eval-uated against seven widely used datasets and has been proven to be particularly effective in increasing the percentage of users for which personalized recommendations can be formulated in the context of sparse datasets, while at the same time maintaining or slightly improving rating prediction quality.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris, Costas Vassilakis, Dimitris Spiliotopoulos

SoDa Technical report TR-19002v2

Note: this version extends and supersedes the first version of the report, which is available here.

Abstract:
In this technical report, we present the experimental findings from applying an algorithm that (1) considers the characteristics of Social Networks (SNs) user reviews which affect the review-to-rating conversion procedure, (2) computes a confidence level for each rating, which reflects the uncertainty level for each conversion process and (3) exploit this metric both in the users’ similarity computation and in the prediction formulation phases in recommender systems.
More specifically, we evaluate the performance of the proposed approach in terms of (i) SN users’ satisfaction and (ii) precision, regarding the recommendations formulated based on the rating predictions generated by the proposed algorithm.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Dionisis Margaris, Costas Vassilakis, Dimitris Spiliotopoulos

SoDa Technical report TR-19002

Note: a newer version of this report is available here.

Abstract:
In this technical report, we present the experimental findings from applying an algorithm that (1) considers the characteristics of Social Networks (SNs) user reviews which affect the review-to-rating conversion procedure, (2) computes a confidence level for each rating, which reflects the uncertainty level for each conversion process and (3) exploit this metric both in the users’ similarity computation and in the prediction formulation phases in recommender systems.
More specifically, we evaluate the performance of the proposed approach in terms of SN users’ satisfaction regarding the recommendations formulated based on the rating predictions generated by the proposed algorithm.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.