Konstantinos N. Vavliakis

Event identification in web social media through named entity recognition and topic modeling

The problem of identifying important online or real life events from large textual document streams that are freely available on the World Wide Web is increasingly gaining popularity, given the flourishing of the social web. An event triggers discussion and comments on the WWW, especially in the blogosphere and in microblogging services. Consequently, one should be able to identify the involved entities, topics, time, and location of events through the analysis of information publicly available on the web, create semantically rich representations of events, and then use this information to provide interesting results, or summarize news to users. In this paper, we define the concept of important event and propose an efficient methodology for performing event detection from large time-stamped web document streams. The methodology successfully integrates named entity recognition, dynamic topic map discovery, topic clustering, and peak detection techniques. In addition, we propose an efficient algorithm for detecting all important events from a document stream. We perform extensive evaluation of the proposed methodology and algorithm on a dataset of 7million blogposts, as well as through an international social event detection challenge. The results provide evidence that our approach: a) accurately detects important events, b) creates semantically rich representations of the detected events, c) can be adequately parameterized to correspond to different social perceptions of the event concept, and d) is suitable for online event detection on very large datasets. The expected complexity of the online facet of the proposed algorithm is linear with respect to the number of documents in the data stream.

RDOTE - Publishing Relational Databases into the Semantic Web

A necessary step for the evolution of the traditional Web into a Semantic Web is the transformation of the vast quantities of data, currently residing in Relational Databases into semantically aware data. In addition, in cases where new ontology schemata are developed, considerable experimentation with real data for testing the consistency of classes, properties and entailment rules is required. During the last decade, there has been intense research and development in creating methodologies and tools able to map Relational Databases with the Resource Description Framework (RDF). Although some systems have gained wider acceptance in the Semantic Web community, they either require users to learn a declarative language for encoding mappings or, in case they support friendly user interfaces, they provide limited expressivity. Thereupon, we present RDOTE, a framework for easily transporting data residing in Relational Databases into the Semantic Web. RDOTE is available under GNU/GPL license and it provides friendly graphical user interfaces, as well as enough expressivity for creating automatic and custom RDF dumps of relational data. RDOTE is also compatible with D2RQ and R2RML mapping definitions.

Multilingual Sentiment Analysis Using Emoticons and Keywords

Nowadays the World Wide Web has evolved into a leading communication channel and information exchange medium. Especially after the introduction of the so-called web 2.0 and the explosion that followed regarding user generated content, the amount of data available over the internet has attracted the interest of both the scientific and business community. Their efforts focus on identifying the inner structures of data and the knowledge that can be derived by analyzing them. Web 2.0 is the subject of study and research in a number of areas. One of these areas is sentiment analysis, where the main goal is to study and draw conclusions about subjectivity, polarity and the feeling that is expressed in user generated content, which mainly consist of free text documents. The goal of this paper is to apply sentiment analysis on multilingual data, focusing on documents written in Greek. We developed an integrated framework that accepts user generated documents and then identifies the polarity of the text (neutral, negative or positive) and the sentiment expressed through it (joy, love, anger or sadness). We followed a semi-supervised approach which led to the development of two techniques for the automatic collection of training data without any human intervention. Our approach involves the detection and use of self-defining features that are available within the data. We take into account two emotionally rich features: a) emoticons and b) lists of emotionally intense keywords. These features are evaluated on data coming from a popular forum, using various classifiers and feature vectors. Our experimental results point to various conclusions about the effectiveness, advantages and limitations of applying such methods on Greek data. Using keywords we achieved 90% mean accuracy on identifying the subjectivity level and 93% on correctly identifying the polarity level, whereas using emoticons the mean accuracy for each of these levels was 74% and 77% respectively.

Redefining the Market Power of Small-Scale Electricity Consumers through Consumer Social Networks

Energy markets have undergone important changes at the conceptual level over the last years. Decentralized supply, small-scale production and smart grid optimization and control are the new building blocks. These changes offer substantial opportunities for all energy market stakeholders, some of which however, remain largely unexploited. Small-scale consumers, as a whole, account for significant amount of energy in current markets (up to 40%), as individuals though their consumption is trivial, and their market power practically non-existent. Thus, it is necessary to assist small-scale energy market stakeholders combine their market power. Within the context of this work we propose Consumer Social Networks (CSNs) as a means for achieve the objective. We present a simulation environment for the creation of CSNs and provide a proof of concept on how CSNs can be formulated based on various criteria. Each cluster in a CSN may be treated as a nontrivial stakeholder with specific characteristics that can actively affect energy market pricing policies. We also show provide an indication on how demand response programs designed based on targeted incentives may lead to energy peak reductions.

Towards Understanding How Personality, Motivation, and Events Trigger Web User Activity

Web 2.0 provided internet users with a dynamic medium, where information is updated continuously and anyone can participate. Though preliminary analysis exists, there is still little understanding on what exactly stimulates users to actively participate, create and share content in online communities. In this paper we present a methodology that aspires to identify and analyze those events that trigger web user activity, content creation and sharing in Web 2.0. Our approach is based on user personality and motivation, and on the occurrence of events with a personal or global impact. The proposed methodology was applied on data collected from Flickr and analysis was performed through the use of statistics and data mining techniques.

Eikonomia-An Integrated Semantically Aware Tool for Description and Retrieval of Byzantine Art Information

Semantic annotation and querying is currently applied on a number of versatile disciplines, providing the added-value of such an approach and, consequently the need for more elaborate - either case-specific or generic - tools. In this context, we have developed Eikonomia: an integrated semantically-aware tool for the description and retrieval of Byzantine artwork Information. Following the needs of the ORMYLIA Art Diagnosis Center for adding semantics to their legacy data, an ontology describing Byzantine artwork based on CIDOC-CRM, along with the interfaces for synchronization to and from the existing RDBMS have been implemented. This ontology has been linked to a reasoning tool, while a dynamic interface for the automated creation of semantic queries in SPARQL was developed. Finally, all the appropriate interfaces were instantiated, in order to allow easy ontology manipulation, query results projection and restrictions creation.

A correlation analysis of web social media

In this paper we analyze and compare three popular content creation and sharing websites, namely Panoramio, YouTube and Epinions. This analysis aims in advancing our understanding of Web Social Media and their impact, and may be useful in creating feedback mechanisms for increasing user participation and sharing. For each of the three websites, we select five fundamental factors appearing in all content centered Web Social Media and we use regression analysis to calculate their correlation. We present findings of statistically important correlations among these key factors and we rank the discovered correlations according to the degree of their influence. Furthermore, we perform analysis of variance in distinct subgroups of the collected data and we discuss differences found in the characteristics of these subgroups and how these differences may affect correlation results. Although we acknowledge that correlation does not imply causality, the discovered correlations may be a first step towards discovering causality laws behind content contribution, commenting and the formulation of friendship relations. These causality laws are useful for boosting the user participation in social media.

A Semantic Tag Recommendation Framework for Collaborative Tagging Systems

In this work we focus on folksonomies. Our goal is to develop techniques that coordinate information processing, by taking advantage of user preferences, in order to automatically produce semantic tag recommendations. To this end, we propose a generalized tag recommendation framework that conveys the semantics of resources according to different user profiles. We present the integration of various models that take into account content, historic values, user preferences and tagging behavior to produce accurate personalized tag recommendations. Based on this information we build several Bayesian models, we evaluate their performance, and we discuss differences in accuracy with respect to semantic matching criteria, and other approaches.

Recommendation Systems in a Conversational Web

In this paper we redefine the concept of Conversation Web in the context of hyper-personalization. We argue that hyper-personalization in the WWW is only possible within a conversational web where websites and users continuously“discuss” (interact in any way). We present a modular system architecture for the conversational WWW, given that adapting to various user profiles and multivariate websites in terms of size and user traffic is necessary, especially in e-commerce. Obviously there cannot be a unique fit-to-all algorithm, but numerous complementary personalization algorithms and techniques are needed. In this context, we propose PRCW, a novel hybrid approach combining offline and online recommendations using RFMG, an extension of RFM modeling. We evaluate our approach against the results of a deep neural network in two datasets coming from different online retailers. Our evaluation indicates that a) the proposed approach outperforms current state-of-art methods in small-medium datasets and can improve performance in large datasets when combined with other methods, b) results can greatly vary in different datasets, depending on size and characteristics, thus locating the proper method for each dataset can be a rather complex task, and c) offline algorithms should be combined with online methods in order to get optimal results since offline algorithms tend to offer better performance but online algorithms are necessary for exploiting new users and trends that turn up.

CASSANDRA: a simulation-based, decision-support tool for energy market stakeholders

Energy gives personal comfort to people, and is essential for the generation of commercial and societal wealth. Nevertheless, energy production and consumption place considerable pressures on the environment, such as the emission of green-house gases and air pollutants. They contribute to climate change, damage natural ecosystems and the man-made environment, and cause adverse effects to human health. Lately, novel market schemes emerge, such as the formation and operation of customer coalitions aiming to improve their market power through the pursuit of common benefits. In this paper we present CASSANDRA, an open source1, expandable software platform for modelling the demand side of power systems, focusing on small scale consumers. The structural elements of the platform are a) the electrical installations (i.e. households, commercial stores, small industries etc.), b) the respective appliances installed, and c) the electrical consumption-related activities of the people residing in the installations. CASSANDRA serves as a tool for simulation of real demand-side environments providing decision support for energy market stakeholders. The ultimate goal of the CASSANDRA simulation functionality is the identification of good practices that lead to energy efficiency, clustering electric energy consumers according to their consumption patterns, and the studying consumer change behaviour when presented with various demand response programs.