Gerasimos Razis

InfluenceTracker: Rating the Impact of a Twitter Account

This paper describes a methodology for rating the influence of a Twitter account in this famous microblogging service. Then it is evaluated over real accounts, under the belief that influence is not only a matter of quantity (amount of followers), but also a mixture of quality measures that reflect interaction, awareness, and visibility in the social sphere. The authors of this paper have created “InfluenceTracker”, a publicly available website where anyone can rate and compare the recent activity of any Twitter account.

Discovering similar Twitter accounts using semantics

On daily basis, millions of Twitter accounts post a vast number of tweets including numerous Twitter entities (mentions, replies, hashtags, photos, URLs). Many of these entities are used in common by many accounts. The more common entities are found in the messages of two different accounts, the more similar, in terms of content or interest, they tend to be. Towards this direction, we introduce a methodology for discovering and suggesting similar Twitter accounts, based entirely on their disseminated content in terms of Twitter entities used. The methodology is based exclusively on semantic representation protocols and related technologies. An ontological schema is also described towards the semantification of the Twitter accounts and their entities.

Semantifying Twitter: The Influence Tracker Ontology

In this paper, we propose an ontology schema towards semantification provision of Twitter social analytics. The ontology is deployed over a publicly available service that measures how influential a Twitter account is, by combining its social activity and interaction over Twitter sphere. Apart from influential quantity and quality measures, the service provides a SPARQL endpoint where users can perform advance semantic queries through the RDFized Twitter entities (mentions, replies, hash tags, photos, URLs) over the semantic graph.

Linked Open Economy: Take Full Advantage of Economic Data

For decades, information related to public finances was out of reach for most of the people. Gradually, public budgets and tenders are becoming openly available and global initiatives promote fiscal transparency and open product and price data. But, the poor quality of economic open data undermines their potential to answer interesting questions (e.g. efficiency of public funds and market processes). Linked Open Economy (LOE) has been developed as a top-level conceptualization that interlinks the publicly available economic open data by modelling the flows incorporated in public procurement together with the market process to address complex policy issues. LOE approach is extensively used to enrich open economic data ranging from budgets and spending to prices. Developers, professionals, public administrations and any other interested party use and customize LOE model to develop new systems, to enable information exchange between systems, to integrate data from heterogeneous sources and to publish open data related to economic activities.

Thematic labeling of Twitter accounts using DBpedia properties

In this paper, we propose an iterative algorithm towards the automatic labeling of Twitter accounts in respect to thematic categories derived from DBpedia properties. We describe the rationale behind the selection of these thematic categories, and discuss their evaluation assessment. Finally, we propose and analyze two generic and adaptable methodologies for discovering the necessary linked data resources for further enhancing the thematic description of Twitter accounts.

Semantic social analytics and linked open data cloud

In this paper, we propose an ontology schema towards linking semantified Twitter social analytics with the Linked Open Data cloud. The ontology is deployed over a publicly available service that measures how influential a Twitter account is by combining its social activity in Twitter. According to our knowledge this is the first work that combines social analytics with the Linked Open Data (LOD) cloud.

Query Expansion with a Little Help from Twitter

With the advent and rapid spread of microblogging services, web information management finds a new research topic. Although classical information retrieval methods and techniques help search engines and services to present an adequate precision in lower recall levels (top-k results), the constantly evolving information needs of microblogging users demand a different approach, which has to be adapted to the dynamic nature of On-line Social Networks (OSNs). In this work, we use Twitter as microblogging service, aiming to investigate the query expansion provision that can be extracted from large graphs, and compare it against classical query expansion methods that require mainly prior knowledge, such as browsing history records or access and management of search logs. We provide a direct comparison with mainstream media services, such as Google, Yahoo!, Bing, NBC and Reuters, while we also evaluate our approach by subjective comparisons in respect to the Google Hot Searches service.

The eLOD Ontology: Modeling Economic Open Data

For decades, valuable economic data was out of reach for most of the people. Gradually, public budgets and tenders are becoming openly available and global initiatives promote financial transparency and data innovation. But, yet the poor quality of open data undermines their potential to answer interesting questions (e.g. efficiency of public funds and market processes). The eLOD ontology has been initiated as a top-level conceptualization that interlinks the publicly available economic open data by modelling the flows incorporated in public procurement together with the market process to address complex policy issues. This paper presents the basic aspects of eLOD ontology in interlinking and querying diverse open data ranging from budget execution to prices. Already, eLOD ontology is used by two EU projects in order to to develop new systems, to enable information exchange between systems, to integrate data from heterogeneous sources and to publish open data related to economic activities.

Big Data for a Linked Open Economy

As the volume data grows exponentially, more and more big data handling approaches are also applied in the linked data cloud. Thus, semantic triplets which are nucleus of the Resource Description Framework (RDF) must be harmonized to the demanding needs of the 4 Vs. This paper presents the architecture and the main components of a big linked data repository named LinkedEconomy. The scope of the platform is to collect, process, interlink and publish unprecedented high-detailed economic data in machine-readable format, in order to (a) provide a new data corpus for enriching research efforts in Economic, Statistics and Business studies, and (b) contribute to Big data analytics for corporate decision making.