Research

  • English
  • Italiano

Deep learning (DL) is a branch of machine learning that focuses on representation-learning methods composed of multiple levels of non-linear modules. Starting from a low level representation of an object (e.g., characters, pixels) each level outputs a representation at a higher, slightly more...

The availability of Big Data is deeply changing our approach to understanding and modeling economic and financial systems. Moreover it represents a huge business opportunity that can be exploited by having the right tools and concepts. In particular, the possibility of tracking the behavior of...

Modern data-storage systems, such as Hadoop and BigTable use compression to reduce the volume of data to be transferred to/from disks, which are slow, as well as to increase the data to be stuffed into the internal memory of computers, which are fast. We have state-of-the-art results in this...

The technologies of mobile communications pervade our society and wireless networks sense the movement of people, generating large volumes of mobility data, such as mobile phone call records and Global Positioning System (GPS) tracks. The striking analytical power of massive collections of...

Sentiment analysis is the discipline that studies natural language text in order to detect and recognize the presence of expressed opinions, emotions, sentiments, and other cognitive states of a subjective nature. In the last ten years sentiment analysis has grown from a small niche concern to...

In the era of Big Data the opportunities of discovering knowledge from social big data increase with the risk of privacy violation: during knowledge discovery, the risk is the uncontrolled intrusion into the personal data of the data subjects, namely, of the (possibly unaware) people whose data...

One of the most prolific sources of big data is represented by search engines' services. In particular, the astonishing number of queries received each day from search engines represent a rich repository of data that is waiting to be turned into knowledge. The knowledge mined from query logs can...

A key research area covered by the European Laboratory on Big Data and Social Mining Network Science, an interdisciplinary discipline focusing on the study of interconnected entities, including social, biological, communication and computer networks. The main objective of the field is to develop...

The growing popularity of online platforms based on user-generated content is gradually creating a digital world that mirrors the physical world. In the paradigm of crowdsensing, the crowd becomes a distributed network of social sensors that allows us to understand real life events at a quasi-...

Measuring well-being of the society requires a multidimensional and integrated approach aimed at describing the health of the society through a complex, multifaceted and compound methodology.
One of the aims of this research area is to unravel some important methodological aspects and...