Abstract Sentiment analysis and opinion mining are valuable for extraction of useful subjective information out of text documents. These tasks have become of great importance, especially for business and marketing professionals, since online posted products and services reviews impact markets and consumers shifts. This work is motivated by the fact that automating retrieval and detection of sentiments expressed for certain products and services embeds complex processes and pose research challenges, due to the textual phenomena and the language specific expression variations. This paper proposes a fast, flexible, generic methodology for sentiment detection out of textual snippets which express people{\textquoteright}s opinions in different languages. The proposed methodology adopts a machine learning approach with which textual documents are represented by vectors and are used for training a polarity classification model. Several documents{\textquoteright} vector representation approaches have been studied, including lexicon-based, word embedding-based and hybrid vectorizations. The competence of these feature representations for the sentiment classification task is assessed through experiments on four datasets containing online user reviews in both Greek and English languages, in order to represent high and weak inflection language groups. The proposed methodology requires minimal computational resources, thus, it might have impact in real world scenarios where limited resources is the case.
}, keywords = {Online user reviews}, issn = {0957-4174}, doi = {http://dx.doi.org/10.1016/j.eswa.2016.10.043}, url = {http://www.sciencedirect.com/science/article/pii/S095741741630584X}, author = {Maria Giatsoglou and Manolis G. Vozalis and Konstantinos Diamantaras and Athena Vakali and George Sarigiannidis and Konstantinos Ch. Chatzisavvas} } @article {1959, title = {CityPulse: A platform prototype for smart city social data mining}, journal = {Journal of the Knowledge Economy}, volume = {7}, year = {2016}, pages = {344{\textendash}372}, author = {Maria Giatsoglou and Despoina Chatzakou and Gkatziaki, Vasiliki and Vakali, Athena and Anthopoulos, Leonidas} } @article {1925, title = {Cloud-based architectures for Geo-located blogosphere dynamics detection}, journal = {Smart Cities}, year = {2016}, abstract = {Social networking data threads emerge rapidly and such crowd-driven big data streams are valuable for detecting trends and opinions. For such analytics, conventional data mining approaches are challenged by both high-dimensionality and scalability concerns. Here, we leverage on the Cloud4Trends framework, for collecting and analyzing geo-located microblogging content, partitioned into clusters under cloud-based infrastructures. Different cloud architectures are proposed to offer flexible solutions for geo-located data analytics, with emphasis on incremental trend analysis. The proposed architectures are largely based on a set of service modules which facilitate the deployment of the experimentation on Cloud infrastructures. Several experimentation remarks are highlighted to showcase the requirements and testing capabilities of different cloud computing settings.
}, keywords = {cloud service deployment, geo-located blogosphere dynamics, social geo-located data clustering, social networks and wisdom of the crowd}, author = {Athena Vakali and Stefanos Antaris and Maria Giatsoglou} } @inproceedings {1924, title = {Early Malicious Activity Discovery in Microblogs by Social Bridges Detection}, year = {2016}, publisher = {16th International Symposium on Signal Processing and Information Technology}, organization = {16th International Symposium on Signal Processing and Information Technology}, address = {Limassol, Cyprus}, abstract = {With the emerging and intense use of Online Social Networks (OSNs) amongst young children and teenagers (youngters), safe networking and socializing on the Web has faced extensive scrutiny. Content and interactions which are considered safe for adult OSN users, might embed potentially threatening and malicious information when it comes to underage users. This work is motivated by the strong need to safeguard youngsters OSNs experience such that they can be empowered and aware. The topology of a graph is studied towards detecting the so called social bridges, i.e. the group(s) of malicious users and their supporters, who have links and ties to both honest and malicious user communities. A graph-topology based classification scheme is proposed to detect such bridge linkages which are suspicious for threatening youngsters networking vulnerability. The proposed scheme is validated by a Twitter network, at which potentially dangerous users are identified based on their Twitter connections. The achieved performance is higher compared to previous efforts, despite the increased complexity due to the variety of groups identified as malicious.
}, author = {Antonia Gogoglou and Zenonas Theodosiou and Tasos Kounoudes and Athena Vakali and Yannis Manolopoulos} } @inproceedings {1923, title = {Smart Cities Tales and Trails}, booktitle = {Internet Science - Third International Conference, INSCI 2016, Florence, Italy, September 12-14, 2016, Proceedings}, year = {2016}, doi = {10.1007/978-3-319-45982-0_24}, url = {http://dx.doi.org/10.1007/978-3-319-45982-0_24}, author = {Athena Vakali and Angeliki Milonaki and Ioannis Gkrosdanis} } @inproceedings {DBLP:conf/pakdd/GiatsoglouCSBFV15, title = {ND-SYNC: Detecting Synchronized Fraud Activities}, booktitle = {Advances in Knowledge Discovery and Data Mining, 19th Pacific-Asia Conference, PAKDD 2015, Ho Chi Minh City, Vietnam, May 19-22, 2015, Proceedings, Part II}, year = {2015}, pages = {201{\^a}{\texteuro}{\textquotedblleft}214}, doi = {10.1007/978-3-319-18032-8_16}, url = {http://dx.doi.org/10.1007/978-3-319-18032-8_16}, author = {Maria Giatsoglou and Despoina Chatzakou and Neil Shah and Alex Beutel and Christos Faloutsos and Athena Vakali} } @inproceedings {conf/pakdd/GiatsoglouCSFV15, title = {Retweeting Activity on Twitter: Signs of Deception}, booktitle = {PAKDD (1)}, series = {Lecture Notes in Computer Science}, volume = {9077}, year = {2015}, pages = {122-134}, publisher = {Springer}, organization = {Springer}, isbn = {978-3-319-18037-3}, author = {Maria Giatsoglou and Despoina Chatzakou and Neil Shah and Christos Faloutsos and Athena Vakali}, editor = {Cao, Tru and Lim, Ee-Peng and Zhou, Zhi-Hua and Ho, Tu-Bao and Cheung, David and Motoda, Hiroshi} } @article {giatsoglou2014user, title = {User communities evolution in microblogs: A public awareness barometer for real world events}, journal = {World Wide Web}, year = {2015}, pages = {1269-1299}, publisher = {Springer US}, abstract = {In social media, users{\textquoteright} interactions are affected by real-world events which influence emergence and shifts of opinions and topics. Interactions around an event-related topic can be captured in a weighted network, while identification of connectivity and intensity patterns can improve understanding of users{\textquoteright} interest on the topic. Community detection is studied here as a means to reveal groups of social media users with common interaction patterns in such networks. The proposed community detection approach identifies communities exploiting both structural properties and intensity patterns, while dynamics of communities{\textquoteright} evolution around an event are revealed based on an iterative community detection and mapping scheme. We investigate the importance of considering interactions{\textquoteright} intensity for community detection via a benchmarking process on synthetic graphs and propose a generic framework for: i) modeling user interactions, ii) identifying static and evolving communities around events, iii) extracting quantitative and qualitative measurements from the communities{\textquoteright} timeline, iv) leveraging measurements to understand the events{\textquoteright} impact. Two real-world case studies based on Twitter interactions demonstrate the framework{\textquoteright}s potential for capturing and interpreting associations among communities and events.
}, author = {Maria Giatsoglou and Despoina Chatzakou and Athena Vakali} } @article {journals/ras/AliSGVFVM14, title = {Contextual object category recognition for RGB-D scene labeling}, journal = {Robotics and Autonomous Systems}, volume = {62}, number = {2}, year = {2014}, pages = {241-256}, author = {Ali, Haider and Shafait, Faisal and Giannakidou, Eirini and Athena Vakali and Figueroa, Nadia and Varvadoukas, Theodoros and Mavridis, Nikolaos} } @proceedings {conf/adbis/2013-2, title = {New Trends in Databases and Information Systems, 17th East European Conference on Advances in Databases and Information Systems}, booktitle = {ADBIS (2)}, series = {Advances in Intelligent Systems and Computing}, volume = {241}, year = {2014}, month = {04/2013}, publisher = {Springer}, address = {Genoa, Italy}, isbn = {978-3-319-01863-8}, editor = {Barbara Catania and Cerquitelli, Tania and Chiusano, Silvia and Guerrini, Giovanna and K{\"a}mpf, Mirko and Kemper, Alfons and Novikov, Boris and Palpanas, Themis and Pokorny, Jaroslav and Athena Vakali} } @inproceedings {conf/wims/GiannakidouVM14, title = {Towards a Framework for Social Semiotic Mining}, booktitle = {WIMS}, year = {2014}, pages = {21}, publisher = {ACM}, organization = {ACM}, isbn = {978-1-4503-2538-7}, author = {Giannakidou, Eirini and Athena Vakali and Mavridis, Nikolaos}, editor = {Akerkar, Rajendra and Bassiliades, Nick and Davies, John and Ermolayev, Vadim} } @proceedings {journals/tlsdkcs/2014-15, title = {Transactions on Large-Scale Data- and Knowledge-Centered Systems}, booktitle = {T. Large-Scale Data- and Knowledge-Centered Systems}, series = {Lecture Notes in Computer Science}, volume = {8920}, year = {2014}, publisher = {Springer}, isbn = {978-3-662-45760-3}, editor = {Hameurlain, Abdelkader and K{\"u}ng, Josef and Wagner, Roland and Barbara Catania and Guerrini, Giovanna and Palpanas, Themis and Pokorny, Jaroslav and Athena Vakali} } @article {journals/internet/GiatsoglouV13, title = {Capturing Social Data Evolution Using Graph Clustering}, journal = {IEEE Internet Computing}, volume = {17}, number = {1}, year = {2013}, pages = {74-79}, abstract = {The fast and unpredictable evolution of social data poses challenges for capturing user activities and complex associations. Evolving social graph clustering promises to uncover the dynamics of latent user and content patterns.
}, author = {Maria Giatsoglou and Athena Vakali} } @inproceedings {conf/wise/GiatsoglouCV13, title = {Community Detection in Social Media by Leveraging Interactions and Intensities}, booktitle = {WISE (2)}, series = {Lecture Notes in Computer Science}, volume = {8181}, year = {2013}, pages = {57-72}, publisher = {Springer}, organization = {Springer}, keywords = {community detection, user weighted interaction networks}, isbn = {978-3-642-41153-3}, author = {Maria Giatsoglou and Despoina Chatzakou and Athena Vakali}, editor = {Lin, Xuemin and Manolopoulos, Yannis and Srivastava, Divesh and Huang, Guangyan} } @inproceedings {conf/adbis/KastrinakisPV13, title = {Compact and Distinctive Visual Vocabularies for Efficient Multimedia Data Indexing}, booktitle = {ADBIS}, series = {Lecture Notes in Computer Science}, volume = {8133}, year = {2013}, pages = {98-111}, publisher = {Springer}, organization = {Springer}, abstract = {Multimedia data indexing for content-based retrieval has attractedsignificant attention in recent years due to the commoditizationof multimedia capturing equipment and the widespread adoption of social networking platforms as means for sharing media content online. Due to the very large amounts of multimedia content, notably images, produced and shared online by people, a very important requirement for multimedia indexing approaches pertains to their efficiency both in terms of computation and memory usage. A common approach to support query-by-example image search is based on the extraction of visual words from images and their indexing by means of inverted indices, a method proposed and popularized in the field of text retrieval.The main challenge that visual word indexing systems currently facearises from the fact that it is necessary to build very large visual vocabularies (hundreds of thousands or even millions of words) to support sufficiently precise search. However, when the visual vocabulary is large,the image indexing process becomes computationally expensive due to the fact that the local image descriptors (e.g. SIFT) need to be quantized to the nearest visual words.To this end, this paper proposes a novel method that significantly decreases the time required for the above quantization process. Instead of using hundreds of thousands of visual words for quantization, the proposed method manages to preserve retrieval quality by using a much smaller number of words for indexing. This is achieved by the concept of composite words, i.e. assigning multiple words to a local descriptor in ascending order of distance. We evaluate the proposed method in the Oxford and Paris buildings datasets to demonstrate the validity of the proposed approach.
}, keywords = {composite visual word, local descriptors, multimedia data indexing, visual word}, isbn = {978-3-642-40682-9}, author = {Kastrinakis, Dimitrios and Symeon Papadopoulos and Athena Vakali}, editor = {Barbara Catania and Guerrini, Giovanna and Pokorny, Jaroslav} } @inproceedings {conf/pci/SamarasVGCA13, title = {Requirements and architecture design principles for a smart city experiment with sensor and social networks integration}, booktitle = {Panhellenic Conference on Informatics}, year = {2013}, pages = {327-334}, publisher = {ACM}, organization = {ACM}, isbn = {978-1-4503-1969-0}, author = {Samaras, Christos and Athena Vakali and Maria Giatsoglou and Despoina Chatzakou and Angelis, Lefteris}, editor = {Ketikidis, Panayiotis H. and Margaritis, Konstantinos G. and Vlahavas, Ioannis P. and Chatzigeorgiou, Alexander and Eleftherakis, George and Stamelos, Ioannis} } @inproceedings {conf/mmm/PapadopoulosSKV13, title = {Semi-supervised Concept Detection by Learning the Structure of Similarity Graphs}, booktitle = {MMM (1)}, series = {Lecture Notes in Computer Science}, volume = {7732}, year = {2013}, pages = {1-12}, publisher = {Springer}, organization = {Springer}, abstract = {We present an approach for detecting concepts in images bya graph-based semi-supervised learning scheme. The proposed approach builds a similarity graph between both the labeled and unlabeled images of the collection and uses the Laplacian Eigemaps of the graph as features for training concept detectors. Therefore, it offers multiple options for fusing different image features. In addition, we present an incremental learning scheme that, given a set of new unlabeled images, efficiently performs the computation of the Laplacian Eigenmaps. We evaluate the performance of our approach both on synthetic datasets and on MIR Flickr, comparing it with high-performance state-of-the-art learning schemes with competitive and in some cases superior results.
}, isbn = {978-3-642-35725-1}, author = {Symeon Papadopoulos and Sagonas, Christos and Yiannis Kompatsiaris and Athena Vakali}, editor = {Li, Shipeng and El-Saddik, Abdulmotaleb and Wang, Meng and Mei, Tao and Sebe, Nicu and Yan, Shuicheng and Hong, Richang and Gurrin, Cathal} } @inproceedings {conf/icc/VakaliAG13, title = {Sensors talk and humans sense Towards a reciprocal collective awareness smart city framework}, booktitle = {ICC Workshops}, year = {2013}, pages = {189-193}, publisher = {IEEE}, organization = {IEEE}, abstract = {Smart city infrastructures provide unique opportunities for innovative applications developing and testing. Sensor city installations offer the ground for experimenting with user-oriented services, which at the same time can test and improve the infrastructure itself. The proposed work summarizes principles and methodology for and experiment, entitled SEN2SOC which will bridge sensor measurements and social networks interactions via natural language generation for supporting smart city services. SEN2SOC aims at exploiting the SmartSantander infrastructure in a sensor to social reciprocal fashion such that the sensor measurements will be and communicated to the public (citizens,authorities, etc), while social networks users activities in relevance to sensors social postings will be analyzed and summarized both to verify sensors reporting and to develop collective aware applications.
}, keywords = {collective aware applications, sensors data management, smart city, social networks mining}, author = {Athena Vakali and Angelis, Lefteris and Maria Giatsoglou} } @article {journals/jiis/GiannakidouKVK12, title = {In \& out zooming on time-aware user/tag clusters}, journal = {J. Intell. Inf. Syst.}, volume = {38}, number = {3}, year = {2012}, pages = {685-708}, abstract = {The common ground behind most approaches that analyze social taggingsystems is addressing the information challenge that emerges from the massiveactivity of millions of users who interact and share resources and/or metadata online.However, lack of any time-related data in the analysis process implicitly deniesmuch of the dynamic nature of social tagging activity. In this paper we claim thatholding a temporal dimension, allows for tracking macroscopic and microscopicusers{\^a}{\texteuro}{\texttrademark} interests, detecting emerging trends and recognizing events. To this end, wepropose a time-aware co-clustering approach for acquiring semantic and temporalpatterns out of the tagging activity. The resulted clusters contain both users and tagsof similar patterns over time, and reveal non-obvious or {\^a}{\texteuro}{\'s}hidden{\^a}{\texteuro}{\v t} relations amongusers and topics of their common interest. Zoom in \& out views serve as visualizationmethods on different aspects of the clusters{\^a}{\texteuro}{\texttrademark} structure, in order to evaluate theefficiency of the approach.
}, keywords = {Events, Social tagging systems, Time-aware clustering, Users{\textquoteright} interests over time}, author = {Giannakidou, Eirini and Vassiliki A. Koutsonikola and Athena Vakali and Yiannis Kompatsiaris} } @inproceedings {conf/www/VakaliGA12, title = {Social networking trends and dynamics detection via a cloud-based framework design}, booktitle = {WWW (Companion Volume)}, year = {2012}, pages = {1213-1220}, publisher = {ACM}, organization = {ACM}, keywords = {cloud service deployment, microblogs and blogosphere dynamics, Social networks social, Web Data Clustering}, isbn = {978-1-4503-1230-1}, author = {Athena Vakali and Maria Giatsoglou and Antaris, Stefanos}, editor = {Mille, Alain and Gandon, Fabien L. and Misselis, Jacques and Rabinovich, Michael and Staab, Steffen} } @inproceedings {conf/fia/SrivastavaV12, title = {Towards a Narrative-Aware Design Framework for Smart Urban Environments}, booktitle = {Future Internet Assembly}, series = {Lecture Notes in Computer Science}, volume = {7281}, year = {2012}, pages = {166-177}, publisher = {Springer}, organization = {Springer}, isbn = {978-3-642-30240-4}, author = {Srivastava, Lara and Athena Vakali}, editor = {Alvarez, Federico and Cleary, Frances and Daras, Petros and Domingue, John and Galis, Alex and Garcia, Ana and Gavras, Anastasius and Karnouskos, Stamatis and Krco, Srdjan and Li, Man-Sze and Lotz, Volkmar and M{\"u}ller, Henning and Salvadori, Elio and Sassen, Anne-Marie and Schaffers, Hans and Stiller, Burkhard and Tselentis, Georgios and Turkama, Petra and Zahariadis, Theodore B.} } @inproceedings {conf/fia/AnthopoulosV12, title = {Urban Planning and Smart Cities: Interrelations and Reciprocities}, booktitle = {Future Internet Assembly}, series = {Lecture Notes in Computer Science}, volume = {7281}, year = {2012}, pages = {178-189}, publisher = {Springer}, organization = {Springer}, isbn = {978-3-642-30240-4}, author = {Anthopoulos, Leonidas G. and Athena Vakali}, editor = {Alvarez, Federico and Cleary, Frances and Daras, Petros and Domingue, John and Galis, Alex and Garcia, Ana and Gavras, Anastasius and Karnouskos, Stamatis and Krco, Srdjan and Li, Man-Sze and Lotz, Volkmar and M{\"u}ller, Henning and Salvadori, Elio and Sassen, Anne-Marie and Schaffers, Hans and Stiller, Burkhard and Tselentis, Georgios and Turkama, Petra and Zahariadis, Theodore B.} } @inbook {books/daglib/p/NikolopoulosGKPV11, title = {Combining Multi-modal Features for Social Media Analysis}, booktitle = {Social Media Modeling and Computing}, year = {2011}, pages = {71-96}, publisher = {Springer}, organization = {Springer}, isbn = {978-0-85729-435-7}, author = {Nikolopoulos, Spiros and Giannakidou, Eirini and Yiannis Kompatsiaris and Patras, Ioannis and Athena Vakali}, editor = {Hoi, Steven C. H. and Luo, Jiebo and Boll, Susanne and Xu, Dong and Jin, Rong} } @inproceedings {conf/acii/TsagkalidouKVK11, title = {Emotional Aware Clustering on Micro-blogging Sources}, booktitle = {ACII (1)}, series = {Lecture Notes in Computer Science}, volume = {6974}, year = {2011}, pages = {387-396}, publisher = {Springer}, organization = {Springer}, abstract = {Microblogging services have nowadays become a very popularcommunication tool among Internet users. Since millions of usersshare opinions on different aspects of life everyday, microblogging websites are considered as a credible source for exploring both factual and subjective information. This fact has inspired research in the area of automatic sentiment analysis. In this paper we propose an emotional aware clustering approach which performs sentiment analysis of users tweets onthe basis of an emotional dictionary and groups tweets according to the degree they express a specific set of emotions. Experimental evaluations on datasets derived from Twitter prove the efficiency of the proposed approach.
}, keywords = {Microblogging services, Sentiment analysis, web clustering}, isbn = {978-3-642-24599-2}, author = {Tsagkalidou, Katerina and Vassiliki A. Koutsonikola and Athena Vakali and Konstantinos Kafetsios}, editor = {D{\textquoteright}Mello, Sidney K. and Graesser, Arthur C. and Schuller, Bj{\"o}rn and Martin, Jean-Claude} } @inbook {series/sci/NikolopoulosCGPKV11, title = {Leveraging Massive User Contributions for Knowledge Extraction}, booktitle = {Next Generation Data Technologies for Collective Computational Intelligence}, series = {Studies in Computational Intelligence}, volume = {352}, year = {2011}, pages = {415-443}, publisher = {Springer}, organization = {Springer}, isbn = {978-3-642-20343-5}, author = {Nikolopoulos, Spiros and Chatzilari, Elisavet and Giannakidou, Eirini and Symeon Papadopoulos and Yiannis Kompatsiaris and Athena Vakali}, editor = {Bessis, Nik and Xhafa, Fatos} } @inbook {series/sci/GiatsoglouPV11, title = {Massive Graph Management for the Web and Web 2.0}, booktitle = {New Directions in Web Data Management 1}, series = {Studies in Computational Intelligence}, volume = {331}, year = {2011}, pages = {19-58}, isbn = {978-3-642-17550-3}, author = {Maria Giatsoglou and Symeon Papadopoulos and Athena Vakali}, editor = {Athena Vakali and Jain, Lakhmi C.} } @inproceedings {conf/webi/GabrielSSV11, title = {Summarization Meets Visualization on Online Social Networks}, booktitle = {Web Intelligence}, year = {2011}, pages = {475-478}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, abstract = {Getting an overview of a large online social networkand deciding which communities to join is a challengingtask for a new user. We propose a method that maps a largenetwork into a smaller graph with two kinds of nodes: a nodeof the first kind is representative of a community; a node ofthe second kind is neighbor to a representative and reflectsthe semantics of that community. Our approach encompassesa learning and ranking algorithm that derives this smallergraph from the original one, and a visualization algorithmthat returns a graph layout to the observer. We report on ourresults on inspecting the network of a folksonomy.
}, keywords = {Clustering, communities, community representatives, social network summarization, social network visualization, Social networks, visualization}, isbn = {978-0-7695-4513-4}, author = {Gabriel, Hans-Henning and Spiliopoulou, Myra and Stachtiari, Emmanouela and Athena Vakali}, editor = {Boissier, Olivier and Benatallah, Boualem and Papazoglou, Mike P. and Ras, Zbigniew W. and Hacid, Mohand-Said} } @inproceedings {conf/vsgames/ZigkolisKCKGKV11, title = {Towards a User-Aware Virtual Museum}, booktitle = {VS-GAMES}, year = {2011}, pages = {228-235}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, keywords = {user groups, user preferences, virtual museum}, isbn = {978-1-4577-0316-4}, author = {Christos Zigkolis and Vassiliki A. Koutsonikola and Despoina Chatzakou and Karagiannidis, Savvas and Maria Giatsoglou and Kosmatopoulos, Andreas and Athena Vakali}, editor = {Liarokapis, Fotis and Doulamis, Anastasios D. and Vescoukis, Vassilios} } @inproceedings {conf/pci/GiatsoglouKSVZ10, title = {Dynamic Code Generation for Cultural Content Management}, booktitle = {Panhellenic Conference on Informatics}, year = {2010}, pages = {21-24}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, isbn = {978-1-4244-7838-5}, author = {Maria Giatsoglou and Vassiliki A. Koutsonikola and Stamos, Konstantinos and Athena Vakali and Christos Zigkolis} } @inproceedings {conf/wiamis/GiannakidouKVK10, title = {Exploring temporal aspects in user-tag co-clustering}, booktitle = {WIAMIS}, year = {2010}, pages = {1-4}, publisher = {IEEE}, organization = {IEEE}, abstract = {Tagging environments have become an interesting topic ofresearch lately, focused mainly on clustering approaches, inorder to extract emergent patterns that are derived from tagsimilarity and involve tag relations or user interconnections.Apart from tag similarity, an interesting parameter to be analyzedduring the clustering/mining process in such data isthe actual time that each tagging activity occurred. Indeed,holding a temporal dimension unfolds macroscopic and microscopicviews of tagging, highlights links between objectsfor specific time periods and, in general, lets us observe howthe users{\^a}{\texteuro}{\texttrademark} tagging activity changes over time. In this article,we propose a time-aware user/tag clustering approach, whichgroups together similar users and tags that are very {\^a}{\texteuro}{\'s}active{\^a}{\texteuro}{\v t}during the same time periods. Emphasis is given on usingvarying time scales, so that we distinguish between clustersthat are robust at many time scales and clusters that are somehowoccasional, i.e. they emerge, only at a specific time period.
}, isbn = {978-88-905328-0-1}, author = {Giannakidou, Eirini and Vassiliki A. Koutsonikola and Athena Vakali and Yiannis Kompatsiaris} } @inproceedings {CEUR-WS.org/Vol-700/Paper9, title = {Integrating Web 20 Data into Linked Open Data Cloud via Clustering}, booktitle = {CEUR Workshop Proceedings ISSN 1613-0073}, volume = {700}, year = {2010}, month = {February}, keywords = {FIA-LOD2010 imported}, author = {Giannakidou, Eirini and Athena Vakali}, editor = {Auer, S{\textquoteright}oren and Decker, Stefan and Hauswirth, Manfred} } @inproceedings {conf/dasfaa/StampouliGV10, title = {Tag Disambiguation through Flickr and Wikipedia}, booktitle = {DASFAA Workshops}, series = {Lecture Notes in Computer Science}, volume = {6193}, year = {2010}, pages = {252-263}, publisher = {Springer}, organization = {Springer}, abstract = {Given the popularity of social tagging systems and the limitationsthese systems have, due to lack of any structure, a common issue that arises involves the low retrieval quality in such systems due to ambiguities of certain terms. In this paper, an approach for improving the retrieval in these systems, in case of ambiguous terms, is presented that attempts to perform tag disambiguation and, at the same time, provide users with relevant content. The idea is based on a mashup that combines data and functionality of two major web 2.0 sites, namely Flickr and Wikipedia and aims at enhancing content retrieval for web users. A case study with the ambiguous notion {\^a}{\texteuro}{\'s}Apple{\^a}{\texteuro}{\v t} illustrates the value of the proposed approach.
}, keywords = {DBpedia project, flick, mashup, term disambiguation, Wikipedia}, isbn = {978-3-642-14588-9}, author = {Stampouli, Anastasia and Giannakidou, Eirini and Athena Vakali}, editor = {Yoshikawa, Masatoshi and Meng, Xiaofeng and Yumoto, Takayuki and Ma, Qiang and Sun, Lifeng and Watanabe, Chiemi} } @inproceedings {conf/wise/KoutsonikolaVGK09, title = {Clustering of Social Tagging System Users: A Topic and Time Based Approach}, booktitle = {WISE}, series = {Lecture Notes in Computer Science}, volume = {5802}, year = {2009}, pages = {75-86}, publisher = {Springer}, organization = {Springer}, abstract = {Under Social Tagging Systems, a typical Web 2.0 application,users label digital data sources by using freely chosen textual descriptions(tags). Mining tag information reveals the topic-domain ofusers interests and significantly contributes in a profile construction process.In this paper we propose a clustering framework which groups usersaccording to their preferred topics and the time locality of their taggingactivity. Experimental results demonstrate the efficiency of the proposedapproach which results in more enriched time-aware users profiles.
}, keywords = {Social tagging systems, time, topic, user clustering}, isbn = {978-3-642-04408-3}, author = {Vassiliki A. Koutsonikola and Athena Vakali and Giannakidou, Eirini and Yiannis Kompatsiaris}, editor = {Vossen, Gottfried and Long, Darrell D. E. and Yu, Jeffrey Xu} } @inproceedings {conf/waim/GiannakidouKVK08, title = {Co-Clustering Tags and Social Data Sources}, booktitle = {WAIM}, year = {2008}, pages = {317-324}, publisher = {IEEE}, organization = {IEEE}, abstract = {Under social tagging systems, a typical Web 2.0 application,users label digital data sources by using freely chosentextual descriptions (tags). Poor retrieval in the aforementionedsystems remains a major problem mostly due toquestionable tag validity and tag ambiguity. Earlier clusteringtechniques have shown limited improvements, since theywere based mostly on tag co-occurrences. In this paper,a co-clustering approach is employed, that exploits jointgroups of related tags and social data sources, in whichboth social and semantic aspects of tags are consideredsimultaneously. Experimental results demonstrate the effi-ciency and the beneficial outcome of the proposed approachin correlating relevant tags and resources.
}, isbn = {978-0-7695-3185-4}, author = {Giannakidou, Eirini and Vassiliki A. Koutsonikola and Athena Vakali and Yiannis Kompatsiaris} } @inproceedings {conf/semco/GiannakidouKV08, title = {SEMSOC: SEMantic, SOcial and Content-Based Clustering in Multimedia Collaborative Tagging Systems}, booktitle = {ICSC}, year = {2008}, pages = {128-135}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, isbn = {978-0-7695-3279-0}, author = {Giannakidou, Eirini and Yiannis Kompatsiaris and Athena Vakali} } @inproceedings {conf/iccsa/PetridouKVP06, title = {A Divergence-Oriented Approach for Web Users Clustering}, booktitle = {ICCSA (2)}, series = {Lecture Notes in Computer Science}, volume = {3981}, year = {2006}, pages = {1229-1238}, publisher = {Springer}, organization = {Springer}, abstract = {Clustering web users based on their access patterns is a quite significanttask in Web Usage Mining. Further to clustering it is important to evaluatethe resulted clusters in order to choose the best clustering for a particular framework.This paper examines the usage of Kullback-Leibler divergence, aninformation theoretic distance, in conjuction with the k-means clusteringalgorithm. It compares KL-divergence with other well known distance measures(Euclidean, Standardized Euclidean and Manhattan) and evaluates clusteringresults using both objective function{\^a}{\texteuro}{\texttrademark}s value and Davies-Bouldin index.Since it is imperative to assess whether the results of a clustering process aresusceptible to noise, especially in noisy environments such as Web environment,our approach takes the impact of noise into account. The clusters obtainedwith KL approach seem to be superior to those obtained with the otherdistance measures in case our data have been corrupted by noise.}, isbn = {3-540-34072-6}, author = {Petridou, Sophia G. and Vassiliki A. Koutsonikola and Athena Vakali and Papadimitriou, Georgios I.}, editor = {Gavrilova, Marina L. and Gervasi, Osvaldo and Kumar, Vipin and Tan, Chih Jeng Kenneth and Taniar, David and Lagan{\u A} , Antonio and Mun, Youngsong and Choo, Hyunseung} } @inproceedings {conf/ideas/StamosPTV06, title = {A similarity based approach for integrated Web caching and content replication in CDNs}, booktitle = {IDEAS}, year = {2006}, pages = {239-242}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, abstract = {Web caching and content replication techniques emergedto solve performance problems related to the Web. We proposea generic non-parametric heuristic method that integratesboth techniques under a CDN. We provide experimentationshowing that our method outperforms the so farseparate implementations of Web caching and content replication.Moreover, we show that the performance improvementcompared with an existing algorithm is significant. Wetest all these techniques in a simulation environment undera flash crowd event and a workload of a typical lightweightedCDN operation.
}, author = {Stamos, Konstantinos and Pallis, George and Thomos, Charilaos and Athena Vakali}, editor = {Desai, Bipin C. and Gupta, Shyam K.} } @inproceedings {conf/icde/ArefCEFGHIMPRTTTVZ02, title = {A Distributed Database Server for Continuous Media}, booktitle = {ICDE}, year = {2002}, pages = {490-491}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, abstract = {In our project, we adopt a new approach for handlingvideo data. We view the video as a well-defined datatype with its own description, parameters, and applicablemethods. The system is based on PREDATOR, the opensource object relational DBMS. PREDATOR uses Shoreas the underlying storage manager (SM). Supporting videooperations (storing, searching by content, and streaming)and new query types (query by examples and multi-featuressimilarity search) requires major changes in many ofthe traditional system components. More specifically,the storage and buffer manager will have to deal withhuge volumes of data with real time constraints. Queryprocessing has to consider the video methods and operatorsin generating, optimizing and executing query plans.}, isbn = {0-7695-1531-2}, author = {Aref, Walid G. and Catlin, Ann Christine and Elmagarmid, Ahmed K. and Fan, Jianping and Guo, J. and Hammad, Moustafa A. and Ilyas, Ihab F. and Marzouk, Mirette S. and Prabhakar, Sunil and Rezgui, Abdelmounaam and Teoh, S. and Terzi, Evimaria and Tu, Yi-Cheng and Athena Vakali and Zhu, Xingquan}, editor = {Agrawal, Rakesh and Dittrich, Klaus R.} }