In recent years, offensive, abusive and hateful language, sexism, racism and other types of aggressive and cyberbullying behavior have been manifesting with increased frequency, and in many online social media platforms. In fact, past scientific work focused on studying these forms in popular media, such as Facebook and Twitter. Building on such work, we present an 8-month study of the various forms of abusive behavior on Twitter, in a holistic fashion. Departing from past work, we examine a wide variety of labeling schemes, which cover different forms of abusive behavior, at the same time. We propose an incremental and iterative methodology, that utilizes the power of crowdsourcing to annotate a large scale collection of tweets with a set of abuse-related labels. In fact, by applying our methodology including statistical analysis for label merging or elimination, we identify a reduced but robust set of labels. Finally, we offer a first overview and findings of our collected and annotated dataset of 100 thousand tweets, which we make publicly available for further scientific exploration.
}, author = {Antigoni-Maria Founta and Constantinos Djouvas and Despoina Chatzakou and Ilias Leontiadis and Jeremy Blackburn and Gianluca Stringhini and Athena Vakali and Michael Sirivianos and Nicolas Kourtellis} } @proceedings {1943, title = {Detecting Aggressors and Bullies on Twitter}, booktitle = {Proceedings of the 26th International Conference on World Wide Web Companion}, series = {WWW {\textquoteright}17 Companion}, year = {2017}, pages = {767--768}, publisher = {ACM}, address = {Perth, Australia}, abstract = {Online social networks constitute an integral part of people{\textquoteright}s every day social activity and the existence of aggressive and bullying phenomena in such spaces is inevitable. In this work, we analyze user behavior on Twitter in an effort to detect cyberbullies and cuber-aggressors by considering specific attributes of their online activity using machine learning classifiers.
}, keywords = {crowdsourcing, cyber-aggression, cyberbullying, Twitter}, issn = {978-1-4503-4914-7}, doi = {10.1145/3041021.3054211}, url = {http://dl.acm.org/citation.cfm?id=3054211}, author = {Despoina Chatzakou and Nicolas Kourtellis and Jeremy Blackburn and Emiliano De Cristofaro and Gianluca Stringhini and Athena Vakali} } @article {1954, title = {Detecting Variation of Emotions in Online Activities}, journal = {Expert Systems with Applications}, volume = {89}, year = {2017}, pages = {318 - 332}, abstract = {Online text sources form evolving large scale data repositories out of which valuable knowledge about human emotions can be derived. Beyond the primary emotions which refer to the global emotional signals, deeper understanding of a wider spectrum of emotions is important to detect online public views and attitudes. The present work is motivated by the need to test and provide a system that categorizes emotion in online activities. Such a system can be beneficial for online services, companies recommendations, and social support communities. The main contributions of this work are to: (a) detect primary emotions, social ones, and those that characterize general affective states from online text sources, (b) compare and validate different emotional analysis processes to highlight the most efficient, and (c) provide a proof of concept case study to monitor and validate online activity, both explicitly and implicitly. The proposed approaches are tested on three datasets collected from different sources, i.e., news agencies, Twitter, and Facebook, and on different languages, i.e., English and Greek. Study results demonstrate that the methodologies at hand succeed to detect a wider spectrum of emotions out of text sources.
}, keywords = {Emotion detection, Hybrid process, Lexicon-based approach, Machine learning}, issn = {0957-4174}, doi = {http://dx.doi.org/10.1016/j.eswa.2017.07.044}, url = {http://www.sciencedirect.com/science/article/pii/S0957417417305213}, author = {Despoina Chatzakou and Athena Vakali and Konstantinos Kafetsios} } @article {1956, title = {DynamiCITY : Revealing city dynamics from citizens social media broadcasts}, journal = {Information Systems}, year = {2017}, pages = {-}, keywords = {crowdsourcing, Data Mining, Smart City Applications, Social Data Mining, Urban Dynamics}, issn = {0306-4379}, doi = {https://doi.org/10.1016/j.is.2017.07.007}, url = {http://www.sciencedirect.com/science/article/pii/S0306437917300650}, author = {Vasiliki Gkatziaki and Maria Giatsoglou and Despoina Chatzakou and Athena Vakali} } @article {1955, title = {Experience of emotion in face to face and computer-mediated social interactions: An event sampling study}, journal = {Computers in Human Behavior}, volume = {76}, year = {2017}, pages = {287 - 293}, abstract = {The present study compared the experience of emotion in social interactions that take place face to face (FtF), co-presently, and those that take place online, in computer-mediated communications (CMC). For a period of ten days participants reported how intensely they experienced positive and negative emotions in CMC and in FtF interactions they had with persons from their social network. Results from factor analyses discerned a three factor emotion structure (positive, negative, and anxious emotions) that was largely shared between CMC and FtF social interactions. Multilevel analyses of emotion across modes of interaction found that in FtF social encounters participants experienced more positive and less negative emotion and higher satisfaction than in CMC; there was no difference in anxious emotion. Positive, but not negative emotions or anxiety partially mediated levels of satisfaction differences between interactions in CMC and those taking place FtF. The results point to similarities and differences in emotion experience in FtF and CMC, underlining in particular the affiliative function of positive emotion in peoples{\textquoteright} encounters.
}, keywords = {Computer-mediated communication, Emotion, FtF, Internet, Social interaction}, issn = {0747-5632}, doi = {https://doi.org/10.1016/j.chb.2017.07.033}, url = {http://www.sciencedirect.com/science/article/pii/S0747563217304557}, author = {Konstantinos Kafetsios and Despoina Chatzakou and Nikolaos Tsigilis and Athena Vakali} } @proceedings {1944, title = {Hate is not Binary: Studying Abusive Behavior of $\#$GamerGate on Twitter}, series = {HT {\textquoteright}17}, year = {2017}, publisher = {ACM}, address = {Prague, Czech Republic}, abstract = {Over the past few years, online bullying and aggression have become increasingly prominent, and manifested in many different forms on social media. However, there is little work analyzing the characteristics of abusive users and what distinguishes them from typical social media users. In this paper, we start addressing this gap by analyzing tweets containing a great amount of abusiveness. We focus on a Twitter dataset revolving around the Gamergate controversy, which led to many incidents of cyberbullying and cyberaggression on various gaming and social media platforms. We study the properties of the users tweeting about Gamergate, the content they post, and the differences in their behavior compared to typical Twitter users.
We find that while their tweets are often seemingly about aggressive and hateful subjects, {\textquoteleft}{\textquoteleft}Gamergaters{\textquoteright}{\textquoteright} do not exhibit common expressions of online anger, and in fact primarily differ from typical users in that their tweets are less joyful. They are also more engaged than typical Twitter users, which is an indication as to how and why this controversy is still ongoing. Surprisingly, we find that Gamergaters are less likely to be suspended by Twitter, thus we analyze their properties to identify differences from typical users and what may have led to their suspension. We perform an unsupervised machine learning analysis to detect clusters of users who, though currently active, could be considered for suspension since they exhibit similar behaviors with suspended users. Finally, we confirm the usefulness of our analyzed features by emulating the Twitter suspension mechanism with a supervised learning method, achieving very good precision and recall.
}, issn = {978-1-4503-4708-2/17/07}, author = {Despoina Chatzakou and Nicolas Kourtellis and Jeremy Blackburn and Emiliano De Cristofaro and Gianluca Stringhini and Athena Vakali} } @proceedings {1939, title = {Mean Birds: Detecting Aggression and Bullying on Twitter}, series = {WebSci {\textquoteright}17}, year = {2017}, publisher = {ACM}, address = {Troy, NY, USA}, abstract = {In recent years, bullying and aggression against users on social media have grown significantly, causing serious consequences to victims of all demographics. In particular, cyberbullying affects more than half of young social media users worldwide, and has also led to teenage suicides, prompted by prolonged and/or coordinated digital harassment. Nonetheless, tools and technologies for understanding and mitigating it are scarce and mostly ineffective. In this paper, we present a principled and scalable approach to detect bullying and aggressive behavior on Twitter. We propose a robust methodology for extracting text, user, and network-based attributes, studying the properties of cyberbullies and aggressors, and what features distinguish them from regular users. We find that bully users post less, participate in fewer online communities, and are less popular than normal users, while aggressors are quite popular and tend to include more negativity in their posts. We evaluate our methodology using a corpus of 1.6M tweets posted over 3 months, and show that machine learning classification algorithms can accurately detect users exhibiting bullying and aggressive behavior, achieving over 90\% AUC.
}, issn = {978-1-4503-4896-6/17/06}, url = {https://arxiv.org/abs/1702.06877}, author = {Despoina Chatzakou and Nicolas Kourtellis and Jeremy Blackburn and Emiliano De Cristofaro and Gianluca Stringhini and Athena Vakali} } @proceedings {1940, title = {Measuring $\#$GamerGate: A Tale of Hate, Sexism, and Bullying}, booktitle = {Proceedings of the 26th International Conference on World Wide Web Companion}, series = {WWW {\textquoteright}17 Companion}, year = {2017}, pages = {1285-1290}, publisher = {ACM}, address = {Perth, Australia}, abstract = {Over the past few years, online aggression and abusive behaviors have occurred in many different forms and on a variety of platforms. In extreme cases, these incidents have evolved into hate, discrimination, and bullying, and even materialized into real-world threats and attacks against individuals or groups. In this paper, we study the Gamergate controversy. Started in August 2014 in the online gaming world, it quickly spread across various social networking platforms, ultimately leading to many incidents of cyberbullying and cyberaggression. We focus on Twitter, presenting a measurement study of a dataset of 340k unique users and 1.6M tweets to study the properties of these users, the content they post, and how they differ from random Twitter users. We find that users involved in this "Twitter war" tend to have more friends and followers, are generally more engaged and post tweets with negative sentiment, less joy, and more hate than random users. We also perform preliminary measurements on how the Twitter suspension mechanism deals with such abusive behaviors. While we focus on Gamergate, our methodology to collect and analyze tweets related to aggressive and bullying activities is of independent interest.
}, issn = {978-1-4503-4914-7}, doi = {10.1145/3041021.3053890}, url = {http://dl.acm.org/citation.cfm?id=3053890}, author = {Despoina Chatzakou and Nicolas Kourtellis and Jeremy Blackburn and Emiliano De Cristofaro and Gianluca Stringhini and Athena Vakali} } @article {1928, title = {Sentiment analysis leveraging emotions and word embeddings}, journal = {Expert Systems with Applications}, volume = {69}, year = {2017}, pages = {214 - 224}, abstract = {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} } @inproceedings {1929, title = {Exploriometer: Leveraging Personality Traits for Coverage and Diversity Aware Recommendations}, booktitle = {Proceedings of the 24th International Conference on World Wide Web Companion, WWW 2015, Florence, Italy, May 18-22, 2015 - Companion Volume}, year = {2015}, doi = {10.1145/2740908.2742140}, url = {http://doi.acm.org/10.1145/2740908.2742140}, author = {Evangelos Chatzicharalampous and Christos Zigkolis and Athena Vakali} } @article {7045420, title = {Harvesting Opinions and Emotions from Social Media Textual Resources}, journal = {Internet Computing, IEEE}, volume = {19}, number = {4}, year = {2015}, month = {July}, pages = {46-50}, keywords = {Adaptation models, Analytical models, Filtering, Internet/Web technologies, Media, Sentiment analysis, Text processing, textual resources, Web 2.0}, issn = {1089-7801}, doi = {10.1109/MIC.2015.28}, author = {Despoina Chatzakou and Athena Vakali} } @inbook {1161, title = {MultiSpot: Spotting Sentiments with Semantic Aware Multilevel Cascaded Analysis}, booktitle = {Big Data Analytics and Knowledge Discovery}, series = {Lecture Notes in Computer Science}, volume = {9263}, year = {2015}, pages = {337-350}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, keywords = {Multilevel features, Sentiment detection}, isbn = {978-3-319-22728-3}, doi = {10.1007/978-3-319-22729-0_26}, url = {http://dx.doi.org/10.1007/978-3-319-22729-0_26}, author = {Despoina Chatzakou and Passalis, Nikolaos and Athena Vakali}, editor = {Sanjay Kumar Madria and Hara, Takahiro} } @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} } @proceedings {1932, title = {Web Information Systems Engineering - WISE 2014 Workshops - 15th International Workshops IWCSN 2014, Org2 2014, PCS 2014, and QUAT 2014, Thessaloniki, Greece, October 12-14, 2014, Revised Selected Papers}, booktitle = {Lecture Notes in Computer Science}, series = { }, volume = {9051}, year = {2015}, publisher = {Springer}, isbn = {978-3-319-20369-0}, doi = {10.1007/978-3-319-20370-6}, url = {http://dx.doi.org/10.1007/978-3-319-20370-6}, editor = {Boualem Benatallah and Azer Bestavros and Barbara Catania and Armin Haller and Yannis Manolopoulos and Athena Vakali and Yanchun Zhang} } @inproceedings {conf/pkdd/ArvanitidisSVT14, title = {Branty: A Social Media Ranking Tool for Brands}, booktitle = {ECML/PKDD (3)}, series = {Lecture Notes in Computer Science}, volume = {8726}, year = {2014}, pages = {432-435}, publisher = {Springer}, organization = {Springer}, isbn = {978-3-662-44844-1}, author = {Arvanitidis, Alexandros and Serafi, Anna and Athena Vakali and Tsoumakas, Grigorios}, editor = {Calders, Toon and Esposito, Floriana and Hullermeier, Eyke and Meo, Rosa} } @inproceedings {conf/icete/KakarontzasACV14, title = {A Conceptual Enterprise Architecture Framework for Smart Cities - A Survey Based Approach}, booktitle = {ICE-B}, year = {2014}, pages = {47-54}, publisher = {SciTePress}, organization = {SciTePress}, isbn = {978-989-758-043-7}, author = {Kakarontzas, George and Anthopoulos, Leonidas G. and Despoina Chatzakou and Athena Vakali}, editor = {Obaidat, Mohammad S. and Holzinger, Andreas and van Sinderen, Marten and Dolog, Peter} } @inproceedings {conf/wims/PolymerouCV14, title = {EmoTube: A Sentiment Analysis Integrated Environment for Social Web Content}, booktitle = {WIMS}, year = {2014}, pages = {20}, publisher = {ACM}, organization = {ACM}, isbn = {978-1-4503-2538-7}, author = {Polymerou, Evangelia and Despoina Chatzakou and Athena Vakali}, editor = {Akerkar, Rajendra and Bassiliades, Nick and Davies, John and Ermolayev, Vadim} } @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} } @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} } @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/icdm/ZigkolisKV13, title = {Dissimilarity Features in Recommender Systems}, booktitle = {ICDM Workshops}, year = {2013}, pages = {825-832}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, isbn = {978-0-7695-5109-8}, author = {Christos Zigkolis and Karagiannidis, Savvas and Athena Vakali}, editor = {Wei Ding and Washio, Takashi and Xiong, Hui and Karypis, George and Thuraisingham, Bhavani M. and Cook, Diane J. and Wu, Xindong} } @inproceedings {6681459, title = {Micro-blogging Content Analysis via Emotionally-Driven Clustering}, booktitle = {Affective Computing and Intelligent Interaction (ACII), 2013 Humaine Association Conference on}, year = {2013}, month = {Sept}, pages = {375-380}, keywords = {affective analysis methodology, Clustering algorithms, content management, content sharing, Dictionaries, emotion intensity monitoring, emotionally-driven clustering, Equations, human emotion states, information sharing, lexicon-based technique, Mathematical model, microblogging content analysis, pattern clustering, people perception, Pragmatics, Semantics, Sentiment analysis, social networking (online), social pulse, social relations, text analysis, Twitter}, issn = {2156-8103}, doi = {10.1109/ACII.2013.68}, author = {Despoina Chatzakou and Vassiliki A. Koutsonikola and Athena Vakali and Konstantinos Kafetsios} } @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/data/VakaliCKA13, title = {Social Data Sentiment Analysis in Smart Environments - Extending Dual Polarities for Crowd Pulse Capturing}, booktitle = {DATA}, year = {2013}, pages = {175-182}, publisher = {SciTePress}, organization = {SciTePress}, isbn = {978-989-8565-67-9}, author = {Athena Vakali and Despoina Chatzakou and Vassiliki A. Koutsonikola and Andreadis, George}, editor = {Helfert, Markus and Francalanci, Chiara and Filipe, Joaquim} } @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 {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} } @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/ht/PaparrizosKAV10, title = {Automatic extraction of structure, content and usage data statistics of web sites}, booktitle = {HT}, year = {2010}, pages = {301-302}, publisher = {ACM}, organization = {ACM}, abstract = {In this paper we present a web mining tool which automaticallyextracts the structure, content and usage data statistics of websites. This work inspired by the fact that web mining consists ofthree axes: web structure mining, web content mining and webusage mining. Each one of those axes is using the structure,content and usage data respectively. The scope is to use thedeveloped multi-thread web crawler as a tool to automaticallyextract from web pages data that are associated with each one ofthose three axes in order afterwards to compute several usefuldescriptive statistics and apply advanced mathematical andstatistical methods. A description of our system is provided aswell as some experimentation results.
}, keywords = {classification, Crawling, Structure Content and Usage data, Web Mining Algorithm}, isbn = {978-1-4503-0041-4}, author = {Paparrizos, Ioannis K. and Vassiliki A. Koutsonikola and Angelis, Lefteris and Athena Vakali}, editor = {Chignell, Mark H. and Toms, Elaine G.} } @inproceedings {conf/mm/PapadopoulosZKKV10, title = {ClustTour: city exploration by use of hybrid photo clustering}, booktitle = {ACM Multimedia}, year = {2010}, pages = {1617-1620}, publisher = {ACM}, organization = {ACM}, abstract = {We present a technical demonstration of an online city explorationapplication that helps users identify interesting spotsin a city by use of photo clusters corresponding to landmarksand events. Our application, called ClustTour, is based onan efficient landmark and event detection scheme for taggedphoto collections. The proposed scheme relies on the combinationof a graph-based photo clustering algorithm, makinguse of both visual and tag information of photos, with acluster classification and merging module. ClustTour createsa map-based visualization of the identified photo clustersthat are classified in prominent categories and are filterableby time and tag. We believe that such an applicationcan greatly facilitate the task of knowing a city through itslandmarks and events. So far, the demo has been based on alarge photo dataset focused on Barcelona, and it is graduallyexpanding to contain photo clusters of several major cities ofEurope. Furthermore, an Android application is developedthat complements the web-based version of ClustTour.
}, keywords = {Clustering, event and landmark detection, tagging}, isbn = {978-1-60558-933-6}, author = {Symeon Papadopoulos and Christos Zigkolis and Kapiris, Stefanos and Yiannis Kompatsiaris and Athena Vakali}, editor = {Bimbo, Alberto Del and Chang, Shih-Fu and Smeulders, Arnold W. M.} } @inproceedings {conf/rcis/MoussiadesV09, title = {Benchmark graphs for the evaluation of Clustering Algorithms}, booktitle = {RCIS}, year = {2009}, pages = {197-206}, publisher = {IEEE}, organization = {IEEE}, abstract = {Artificial graphs are commonly used for theevaluation of community mining and clustering algorithms. Eachartificial graph is assigned a pre-specified clustering, which iscompared to clustering solutions obtained by the algorithmsunder evaluation. Hence, the pre-specified clustering shouldcomply with specifications that are assumed to delimit a goodclustering. However, existing construction processes for artificialgraphs do not set explicit specifications for the pre-specifiedclustering. We call these graphs, randomly clustered graphs.Here, we introduce a new class of benchmark graphs which areclustered according to explicit specifications. We call themoptimally clustered graphs. We present the basic properties ofoptimally clustered graphs and propose algorithms for theirconstruction. Experimentally, we compare two communitymining algorithms using both randomly and optimally clusteredgraphs. Results of this evaluation reveal interesting insights bothfor the algorithms and the artificial graphs.
}, keywords = {Artificial graph, Community structure, Graph clustering, Intra linkage ratio, Modularity}, isbn = {978-1-4244-2864-9}, author = {Moussiades, Lefteris and Athena Vakali}, editor = {Flory, Andre and Collard, Martine} } @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} } @article {journals/internet/VakaliCM05, title = {XML Data Stores: Emerging Practices}, journal = {IEEE Internet Computing}, volume = {9}, number = {2}, year = {2005}, pages = {62-69}, author = {Athena Vakali and Barbara Catania and Anna Maddalena} } @article {catania05xml, title = {XML document indexes: a classification}, journal = {Internet Computing, IEEE}, volume = {9}, number = {5}, year = {2005}, pages = {64{\textendash}71}, abstract = {XML{\textquoteright}s increasing diffusion makes efficient XML query processing and indexing all the more critical. Given the semistructured nature of XML documents, however, general query processing techniques won{\textquoteright}t work. Researchers have proposed several specialized indexing methods that offer query processors efficient access to XML documents, although none are yet fully implemented in commercial products. In this article the classification of XML indexing techniques identifies current practices and trends, offering insight into how developers can improve query processing and select the best solution for particular contexts.
}, keywords = {documents indexing, xml}, author = {Barbara Catania and Anna Maddalena and Athena Vakali} } @article {journals/internet/CataniaMV05, title = {XML Document Indexes: A Classification}, journal = {IEEE Internet Computing}, volume = {9}, number = {5}, year = {2005}, pages = {64-71}, author = {Barbara Catania and Anna Maddalena and Athena Vakali} } @inproceedings {conf/mmdb/HammicheBHV04, title = {Semantic retrieval of multimedia data}, booktitle = {MMDB}, year = {2004}, pages = {36-44}, publisher = {ACM}, organization = {ACM}, abstract = {This paper deals with the problem of finding multimediadata that fulfill the requirements of user queries. We assumeboth the user query and the multimedia data are expressedby MPEG-7 standard. The MPEG-7 formalism lacks thesemantics and reasoning support in many ways. For example,the search of the implicit data can not be achieved,due to its description based on XML schema. We propose aframework for querying multimedia data based on a tree embeddingapproximation algorithm, combining the MPEG-7standard and an ontology
}, keywords = {Approximation Ontologies, MPEG-7, Multimedia Data, Tree embedding}, isbn = {1-58113-975-6}, author = {Hammiche, Samira and Benbernou, Salima and Hacid, Mohand-Said and Athena Vakali}, editor = {Chen, Shu-Ching and Shyu, Mei-Ling} } @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.} }