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} } @article {journals/tweb/KoutsonikolaV11, title = {A Clustering-Driven LDAP Framework}, journal = {TWEB}, volume = {5}, number = {3}, year = {2011}, pages = {12}, abstract = {LDAP directories have proliferated as the appropriate storage framework for various and heterogeneousdata sources, operating under a wide range of applications and services. Due to the increased amount andheterogeneity of the LDAP data, there is a requirement for appropriate data organization schemes. TheLPAIR \& LMERGE (LP-LM) algorithm, presented in this article, is a hierarchical agglomerative structurebasedclustering algorithm which can be used for the LDAP directory information tree definition. A thoroughstudy of the algorithm{\^a}{\texteuro}{\texttrademark}s performance is provided, which designates its efficiency. Moreover, the RelativeLink as an alternative merging criterion is proposed, since as indicated by the experimentation, it canresult in more balanced clusters. Finally, the LP and LM Query Engine is presented, which considering theclustering-based LDAP data organization, results in the enhancement of the LDAP server{\^a}{\texteuro}{\texttrademark}s performance.
}, keywords = {Clustering, DIT organization, LDAP services, merging criteria, query and retrieval engine}, author = {Vassiliki A. Koutsonikola and Athena Vakali} } @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} } @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/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 {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} } @article {journals/ijkwi/KoutsonikolaV09, title = {A fuzzy bi-clustering approach to correlate web users and pages}, journal = {I. J. Knowledge and Web Intelligence}, volume = {1}, number = {1/2}, year = {2009}, pages = {3-23}, abstract = {With the rapid development of information technology, thesignificance of clustering in the process of delivering information to users isbecoming more eminent. Especially in the web information space, clusteringanalysis can prove particularly beneficial for a variety of applications such asweb personalisation and profiling, caching and prefetching and content deliverynetworks. In this paper, we propose a bi-clustering approach, which identifiesgroups of related web users and pages. The proposed approach is a three-stepprocess that relies on the principles of spectral clustering analysis and providesa fuzzy relation scheme for the revealed users{\^a}{\texteuro}{\texttrademark} and pages{\^a}{\texteuro}{\texttrademark} clusters. Experimentshave been conducted on both synthetic and real datasets to prove the proposedmethod{\^a}{\texteuro}{\texttrademark}s efficiency and reveal hidden knowledge.
}, keywords = {fuzzy bi-clustering, spectral analysis, web pages, web users}, author = {Vassiliki A. Koutsonikola and Athena Vakali} } @article {journals/ijwis/KoutsonikolaPVP09, title = {A new approach to web users clustering and validation: a divergence-based scheme}, journal = {IJWIS}, volume = {5}, number = {3}, year = {2009}, pages = {348-371}, abstract = {Purpose {\^a}{\texteuro}{\textquotedblleft} Web users{\^a}{\texteuro}{\texttrademark} clustering is an important mining task since it contributes in identifying usagepatterns, a beneficial task for a wide range of applications that rely on the web. The purpose of thispaper is to examine the usage of Kullback-Leibler (KL) divergence, an information theoretic distance,as an alternative option for measuring distances in web users clustering.Design/methodology/approach {\^a}{\texteuro}{\textquotedblleft} KL-divergence is compared with other well-known distancemeasures and clustering results are evaluated using a criterion function, validity indices, andgraphical representations. Furthermore, the impact of noise (i.e. occasional or mistaken page visits) isevaluated, since it is imperative to assess whether a clustering process exhibits tolerance in noisyenvironments such as the web.Findings {\^a}{\texteuro}{\textquotedblleft} The proposed KL clustering approach is of similar performance when compared withother distance measures under both synthetic and real data workloads. Moreover, imposing extranoise on real data, the approach shows minimum deterioration among most of the other conventionaldistance measures.Practical implications {\^a}{\texteuro}{\textquotedblleft} The experimental results show that a probabilistic measure such asKL-divergence has proven to be quite efficient in noisy environments and thus constitute a goodalternative, the web users clustering problem.Originality/value {\^a}{\texteuro}{\textquotedblleft} This work is inspired by the usage of divergence in clustering of biological dataand it is introduced by the authors in the area of web clustering. According to the experimental resultspresented in this paper, KL-divergence can be considered as a good alternative for measuringdistances in noisy environments such as the web.
}, keywords = {Cluster analysis, Internet Data mining, User studies}, author = {Vassiliki A. Koutsonikola and Petridou, Sophia G. and Athena Vakali and Papadimitriou, Georgios I.} } @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/wise/KoutsonikolaPVHB08, title = {Correlating Time-Related Data Sources with Co-clustering}, booktitle = {WISE}, series = {Lecture Notes in Computer Science}, volume = {5175}, year = {2008}, pages = {264-279}, publisher = {Springer}, organization = {Springer}, abstract = {A huge amount of data is circulated and collected every dayon a regular time basis. Given a pair of such datasets, it might be possibleto reveal hidden dependencies between them since the presence of the onedataset elements may influence the elements of the other dataset and viceversa. Furthermore, the impact of these relations may last during a periodinstead of the time point of their co-occurrence. Mining such relationsunder those assumptions is a challenging problem. In this paper, we studytwo time-related datasets whose elements are bilaterally affected overtime. We employ a co-clustering approach to identify groups of similarelements on the basis of two distinct criteria: the direction and durationof their impact. The proposed approach is evaluated using time-relatednews and stock{\^a}{\texteuro}{\texttrademark}s market real datasets.
}, isbn = {978-3-540-85480-7}, author = {Vassiliki A. Koutsonikola and Petridou, Sophia G. and Athena Vakali and Hacid, Hakim and Benatallah, Boualem}, editor = {Bailey, James and Maier, David and Schewe, Klaus-Dieter and Thalheim, Bernhard and Wang, Xiaoyang Sean} } @inproceedings {conf/ismis/KoutsonikolaVMV08, title = {A Structure-Based Clustering on LDAP Directory Information}, booktitle = {ISMIS}, series = {Lecture Notes in Computer Science}, volume = {4994}, year = {2008}, pages = {121-130}, publisher = {Springer}, organization = {Springer}, abstract = {LDAP directories have rapidly emerged as the essentialframework for storing a wide range of heterogeneous information undervarious applications and services. Increasing amounts of informationare being stored in LDAP directories imposing the need for efficientdata organization and retrieval. In this paper, we propose the LPAIR\& LMERGE (LP-LM) hierarchical agglomerative clustering algorithmfor improving LDAP data organization. LP-LM merges a pair of clustersat each step, considering the LD-vectors, which represent the entries{\^a}{\texteuro}{\texttrademark}structure. The clustering-based LDAP data organization enhances LDAPserver{\^a}{\texteuro}{\texttrademark}s response times, under a specific query framework.
}, isbn = {978-3-540-68122-9}, author = {Vassiliki A. Koutsonikola and Athena Vakali and Mpalasas, Antonios and Valavanis, Michael}, editor = {An, Aijun and Matwin, Stan and Ras, Zbigniew W. and Slezak, Dominik} } @article {journals/tkde/PetridouKVP08, title = {Time-Aware Web Users{\textquoteright} Clustering}, journal = {IEEE Trans. Knowl. Data Eng.}, volume = {20}, number = {5}, year = {2008}, pages = {653-667}, author = {Petridou, Sophia G. and Vassiliki A. Koutsonikola and Athena Vakali and Papadimitriou, Georgios I.} } @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/KoutsonikolaV04, title = {LDAP: Framework, Practices, and Trends}, journal = {IEEE Internet Computing}, volume = {8}, number = {5}, year = {2004}, pages = {66-72}, author = {Vassiliki A. Koutsonikola and Athena Vakali} }