This is a two-stage predictive model for the mobility of scientists. First, data mining is used to predict which researcher will move in the next year on the basis of their...

Online interactions between users via the wall feature in the New Orleans regional network.

This experiment compares the performance of some GNN-based approaches for predicting the therapy recommended to type-2 diabetes patients

The dataset contains a knowledge base built with data coming from Flickr and Wikipedia. It covers three Italian cities which are important from a sightseeing point of view and...

Proper risk stratification of patients with differentiated thyroid cancer (DTC) is essential to avoid both unnecessary diagnostic procedures in low-risk patients and clinical...

This dataset contains tweets related to the devastating earthquake occurred on 22 February 2011, at around 12 p.m. local time in Christchurch, New Zealand...

The dataset contains mobile phone records collected in Rome between November 2015 and August 2016. It contains Call Data Records (CDRs) of phone users, and the corresponding...

This method nowcasts migration stocks and flows by using Twitter data. Under development.

This dataset is related to a power outage (i.e., a blackout) that occurred in the city of Milan, in northern Italy, in the night between 14 and 15 May 2013. Despite not...

Census data recording the migration of people between metropolitan areas in the US

A dataset of soccer-logs for all the main soccer leagues in the world, from season 2014/2015 to the current one.

The adult dataset includes $48,842$ instances with demographic information like age, workclass, marital-status, race, capital-loss, capital-gain etc. The income attribute...

This dataset comprises 1,100 Italian tweets shared in the aftermath of the 2009 L’Aquila earthquake (https://en.wikipedia.org/wiki/2009_L%27Aquila_earthquake). The earthquake...

The ClueWeb09 dataset consists of about 1 billion web pages in ten languages that were collected in January and February 2009. It was created to support research on...

We propose a new framework that can exploit topological and biological information to predict protein-protein interactions. The algorithm relies on the underlying hypothesis...

In the german credit dataset each one of the 1,000 persons is classified as a good or bad creditor according to attributes like age, sex, checking_account, credit_amount,...

This dataset contains anonymized proximity information sent by 154 mobile phones (both Android and iPhone) via phone apps. These information are sent by bluetooth beacons every...

The dataset comprises pickup and drop-off times and locations of vehicles in 10 European cities for one of the major free-floating car sharing operator. For nine of these...

Spambots are automated accounts (i.e., accounts driven by a bot) that repeatedly advertise unsolicited and often harmful content (e.g., malware, URLs to phishing Web sites,...