Fabio Benedetti

 

Università degli Studi di Modena e Reggio Emilia
Address: Dipartimento di Ingegneria Enzo Ferrari, Via Pietro Vivarelli 10 - int. 1 - 41125 Modena Italy
Email: fabio.benedetti at unimore.it
Google Schoolarlinkedin-icon Web-Twitter-alt-2-Metro-icon images github

Summary

CV

I am Fabio Benedetti, a PhD in ICT with the passion for data managing, analysis and visualization. I really love working with data and face the new challenges it involves. I think that a Data Scientist have to own strong statistical knowledge for extracting value from raw data, but he also have to be able to provide effective and synthetic visualizations of results. I try, as possible, to stay updated, following online courses about statistic, Big Data, Data Visualization.

Now, I'm working in the IT new business solution department of Unipol Sai. My job comprehends design and development of data centric prototypes for improving the business processes inside our group. These prototypes involve scalable infrastructures, given the high volume of data, machine learning techniques, and the use of innovative ways of visualisation.

My research topic during the PhD touched various topics. I developed a tool called LODeX able to index automatically Linked Open Data sources, visualize a browsable summary of their schema (by using D3.js) and enable the composition of visual SPARQL query. I spent 7 month in the US at Knoesis research center where I worked with SPARK in internal projects and I developed a scalable technique, called CSA, for estimating inter document similarity between text documents.

Before starting the PhD school I did an internship at Datariver where I re engineered a framework for clinical data management. Then, I collaborated with Doxee in a Business Intelligence and Data Integration project. During this period I explored the use of the Pentaho Open Source platform to integrate data coming from different Databases and produce BI reports.

 

Projects

 

LODeX

The Linked Open Data (LOD) Cloud has more than tripled its sources in just three years (from 295 sources in 2011 to 1014 in 2014). While the LOD data are being produced at a increasing rate, LOD tools lack in producing an high level representation of datasets and in supporting users in the exploration and querying of a source. To overcome the above problems and significantly increase the number of consumers of LOD data, we devised a new method and a tool, called LODeX, that promotes the understanding, navigation and querying of LOD sources both for experts and for beginners. It also provides a standardized and homogeneous summary of LOD sources and supports user in the creation of visual queries on previously unknown datasets.

 

Activities

 

Tutorial on Sentiment Analysis

A simple project with some script that implement techniques of Sentiment Analysis for the course of Big Data Analysis of the department of engeneering of Modena e Reggio Emilia.

Slides & GitHub

 

Web Science Summer School - Southampton University (20-26 July 2014)

 The School has been characterized by mixture of invited talks and tutorials on several aspects of data science, including data analytics, data publishing and interlinking, social media management, open data, and crowdsourcing.

Web page

 

RDA Research Data Alliance - Member of the Big Data Analytic Interest Group

 I won a grant as Early Career Scientist and I have been assigned the Big Data Analytic Interest group. I participated to the RDA Fourth Plenary Meeting 22 - 24 September 2014 in Amsterdam, where I also presented a poster containing my research on Linked Open Data.

Web page

 

Certifications

 

 

Publications