D Iezzi

Centrality Measures for Text Clustering

Text clustering is an unsupervised process of classifying texts and words into different groups. In literature, many algorithms use a bag of words model to represent texts and classify contents. The bag of words model assumes that word order has no signicance. The aim of this article is to propose a new method of text clustering, considering links between terms and documents. We use centrality measures to assess word/text importance in a corpus and to sequentially classify documents.

Intimate Femicide in Italy: A Model to Classify How Killings Happened

Women’s homicide (femicide) is the most serious form of violence against women. The aim of this paper is to propose a method to classify the underlying mechanism of killing. We analysed 1,125 cases of femicides in Italy from 2000 to 2005, 764 of these occurring in a domestic setting. The most important information about the mechanism of femicide is textual data, referring to newspaper articles. We propose a method to describe the killer profile on the basis of the analysis of crime scenes, possible suspect information and killer’s modus operandi.

Fuzzy c-Means for Web Mining: The Italian Tourist Forum Case

e-tourism is in stable growth and becoming one of the leading sectors in the e-commerce world. Social media and mobile technologies are holding an increasingly important role in the procurement processes of tourism, by both providing access to real-time information and promoting the exchange of experiences. Web mining allows the collection of new unstructured data and the building of users’ profiles based on electronic web mouth. We apply a soft approach to solve lexical ambiguity and build a vocabulary for the tourism sector. Indeed, we propose a new version of the fuzzy c-means algorithm to detect the best centroid clusters, and we choose the final partition according to the validation of three indices (the partition coefficient, the classification entropy, and the Xie-Beni index). We use this method to classify 525 posts published by the Italian tourism forum from January 2010 to April 2012.

A New Fuzzy Method to Classify Professional Profiles from Job Announcements

In the last years, Universities have created an office of placement to facilitate the employability of graduates. University placement offices select for companies, which offer a job and/or training position, a large number of graduates only based on degree and grades.

Competences Offered to Statisticians by the Italian Universities and Required by the Job Market

The development of the European higher education system, within the frame of the Bologna process, requires that higher education be more and more integrated with the wider economic strategies (Lisbon objectives) and that employability be taken into account by the study programmes. Higher education institutions are invited not only to answer to the needs of the national labour markets but also to incorporate into their perspectives the European one. The Italian university reform provides for a first triennial cycle with educational and training purposes that give graduates an immediate access to the labour market. The labour market requires, on the other hand, graduates to have not only a theoretical education, but also professional competences. This paper aims to build cognitive maps of the study programmes in Statistics and rank the competences required by the job market to graduates in Statistics. We apply for that various methods of multivariate and textual analysis.

La qualità della vita percepita nelle metropoli europee

La qualita della vita percepita nelle metropoli europee (di Domenica Fioredistella Iezzi) - ABSTRACT: The quality of life perception in European cities Objectives The quality of life (Qol) is a complex expression that includes different meanings. In this paper, Qol was assumed as a mix of qualitative and quantitative aspects. The qualitative approach provides an in-depth study of the motivations, feelings and reactions to a given subject or concept among selected social groups. Qol perception was analysed in thirty-one European cities (EU 15) and the results were compared with the objective data. The aim of this paper is to propose a non linear method based on the Qol to rank the European cities.

An Application of Text Mining Technique for the Census of Nonprofit Institutions

The National Institutes of Statistics are increasing in the use of administrative data, which are routinely collected by organizations as part of their business or operational activities. As a matter of fact, this huge amount of data is relevant whether by transforming in statistics for building information systems or by using them as additional information during the whole statistical survey. With regard to Italian nonprofit institutionTM Census, text data from the Italian Revenue Agency are being used to create the list. The paper explores the opportunity of using the text mining technique on the available data to build a classification of nonprofit organizations, which may also help to distinguish them from firms and public institutions. We apply text classification and text clustering methods to select the best partition of the dataset, and we underline the advantages and disadvantages of different processes.

Using Rasch Measurement to Assess the Role of the Traditional Family in Italy

In the last two decades, Italian family has undergone profound changes. The role of traditional family has become weaker and new living arrangements have gained importance. The ISTAT multipurpose survey on “Households and social aspects” collected the Italianopinion about traditional role of the family. The aim of this study is to assess “Italian” “opinion” about traditional family pattern. Construct and content validity are supported using classical test theory and Rasch modeling in order to test an eight-item Likert scale.

Forecasting a Classification

This paper focuses on the problem of forecasting a classification given a panel data set formed by a (multiple) time series of partitions of a same set of units. As far as we know, in classification and time series analysis this is a completely new problem. A methodology based on a vector autoregressive model is here proposed to directly forecast a partition given a (multiple) time series of partitions with the same fixed number of classes for each time. Two real panel data have been analysed with this new procedure. Open problems are discussed in a final section.