Projects

Developing a predictive support system to understand which individuals are at risk of becoming long-term unemployed, in order to assist IEFP's Counsellors to determine how to personalize their professional development plans best. The tool allows Counsellors to understand which factors contribute to an individual's risk, giving them insight into the system's decision-making process, and granting the agency to override the tool in favor of an expert human judgment when appropriate. We are currently preparing a pilot study that will provide a critical evaluation of Counsellor’s opinions about the tool, to better understand the extent to which it facilitates their daily interactions with unemployed persons, and to support future research in unemployment prevention. This work was co-created with experts in labor policy and social work, including the Counsellors themselves in the design process.

Partner: IEFP

# Social Good  # Unemployment  # Decision-Making

Seasonal flu places a heavy burden on human populations and healthcare systems, thus, requires permanent surveillance. Current surveillance methods are robust yet slow. With the collaboration of national and international public health institutions, we are developing models that can timely predict flu levels by using a combination of offline and online data (such as search trends and social media shares).

# Data-Driven Policy  # Healthcare 

In the last few years, Portugal has been witnessing rapid growth in tourism which is ill-equipped to face hard to quantify challenges such as tourist congestions, loss of city identity, degradation of patrimony, etc. The project proposes a data-driven approach to the tourism management in the Portuguese territory through a set of tools to inform Portuguese policy-makers about the state of the tourism industry, going beyond the traditional survey data and research and providing complete analyses of this sector using Big Data sources. With the insights provided by the project, tourism decision-makers will have crucial information to design policies that foster sustainable and friendly cities, both for tourists and dwellers.

Partners: Turismo de Portugal and NOS

# Social Good  # Tourism Management  # Data Driven Policy

Antibiotics (Ab) are one of the most important class of medical drugs. But when exposed to Ab, bacterial populations can quickly become resistant to them, and antibiotic-resistant bacteria are a serious health problem.

The best way to prevent the evolution of new resistances is only to use Ab when they are necessary. We have initiated a collaboration with the Portuguese Ministry of Health and are using their large database of medical prescriptions to 1) characterize the distribution of antibiotic prescription by medical doctors and identify causes of over-prescription; 2) identify the gold standard for antibiotic prescription for the Portuguese population; and 3) propose interventions to reduce Ab prescription.

# Data-Driven Policy  # Healthcare

Data-driven management is increasingly on the agenda of many Municipalities. The amount of data that Municipalities generate themselves, plus the data available from local partners such as Police, Transportation Companies, Telecom, among many others, offer a huge range of opportunities to develop new knowledge that supports public policy. CCDE is the data hub for the region, aiming to provide meaningful insights for local challenges, to experiment new approaches and solutions within the region and to foster knowledge dissemination through the integration of youth and a series of events.  

Partner: Câmara Municipal de Cascais

# Social Good  # Data Driven Policy

Emergency Care Units (ECUs) are medical facilities that deal with unplanned patient turnout, for a very large range of conditions, often urgent or acute, and frequently life-threatening. Therefore, ECUs need to find a difficult balance between having enough resources (human and others) to deal with an unexpected surge in patients, while reducing wasteful practices of sustaining more resources than required.

We focus on top drivers of ECU seeking behavior and use a Data Science and Machine Learning (ML) approach to study variations in emergency peaks and possible factors that might predict them. Together with the Portuguese Ministry of Health, and FCT funding, we expect to offer a simple prediction, that can be used by decision-makers and reduce uncertainty in ECU patient inflow.

# Data-Driven Policy  # Decision-Making  # Healthcare

The social sector represents an important sector of the Portuguese economy. However, the few data sources available provide little and disconnected pieces of information, a low level of interaction and poor visualizations. The goal of the project is to create a new and integrated database for the social sector to be at the disposal of the Portuguese society, serving NGOs, foundations, impact-driven companies, researchers, investors, Government agencies, among other stakeholders.

Partner: La Caixa Foundation

# Social Good   # Portuguese Social Sector

Parliaments are an essential forum for political decision making; studying their processes and output, from voting patterns to speech debates, but also biographical data, conflicts of interest and composition, can help us understand how they function and how they can better represent the will of the citizens. We have collected all parliamentary debate transcripts, from 1976 to present, and are now analyzing the text to detect temporal trends, identify major topics and cross that information with other variables, such as votes and biographies of the members of Parliament.

# Data-Driven Policy  # Political Debate

The project’s goal was to create a machine learning model using data from incidents recorded, road characteristics, speed and flow traffic data and weather data in order to predict, within a given time window, the probability of an accident. This project allows for a better allocation of road inspectors to road sections to patrol and decrease their response time to incidents.

Partner: Rijkswaterstaat

# Data Science for Social Good 2018  # Transportation  # Decision-Making

The United Nations recognizes gender equality as one of the Sustainable Development Goals to be achieved by 2030. Yet, few women are present in leadership positions despite having the same, or even higher levels of education. Although many hypotheses have been proposed, the reasons behind this "glass ceiling" remain unclear.

Political discourse in parliament provides a unique case-study on gender differences both in the behavior of women as well as on the behavior towards women. We make use of natural language processing techniques as well as basic statistics to identify differences between male and female behavior and discourse in the Portuguese parliament. Our goal is to reveal subtle differences so that both the public and the politicians themselves are aware of them.

# Data-Driven Policy  # Gender Equality

As Tuscany is one of the most popular tourist destinations in the world, the region, its resources and inhabitants have been put under extreme pressure. The project aimed to use machine-learning algorithms to group individuals and, thus, help to better understand the region’s tourists and improve tourism management.

Partners: Toscana Promozione Turistica and Vodafone Italy

# Data Science for Social Good 2018  # Tourism Management  # Data-Driven Policy

Whether we talk about the environment or public debt, the topic of sustainability seems pervasive in public discussions. But exactly how pervasive is it? For how long do we care about the future impacts of our current decisions? We make use of the transcripts of the Portuguese parliament as well as online media records, Twitter and Facebook posts to observe the dynamics of the topic in recent years. Namely, we ask: In what contexts is sustainability discussed? Who talks about sustainability? What are its temporal dynamics? This project is supported by the Fundação Calouste Gulbenkian.

Partner: Fundação Calouste Gulbenkian

# Data-Driven Policy  # Sustainability

The purpose of the project is to use the data made available by the IEFP to build a modelled system whose objective is to empower the IEFP and its local offices to better identify individuals at high risk of long-term unemployment, and to provide data-driven insights which will allow for a more efficient allocation of IEFP’s resources to respond to the needs of unemployed individuals.

Partners: IEFP and EAPN

# Data Science for Social Good 2018  # Unemployment  # Data-Driven Policy

News media is a standard interface between the public and politics, and it is uncertain to what extent it has the ability to influence the political agenda and vice-versa. We are conducting a large-scale news media analysis in order to get some insights on the dynamics between media, political entities, and the decision-making process.

# Data-Driven Policy   # Decision-Making  # Media

The ultimate goal of the project was to increase the vaccination rate for measles, mumps, and rubella in Croatia. In order to achieve this, the team predicted the risk level of each child of not receiving the required two doses of the MMR vaccine and develop clusters of the above-mentioned children, according to similar features that would allow for customized vaccination-promotion policies.

Partners: Croatian Institute of Public Health (CIPH), Institute of Public Health of Split-Dalmatia County, Andrija Stampar School of Public Health and Croatian Society for School and University Medicine

# Data Science for Social Good 2018  # Healthcare  # Data-Driven Policy

In Portugal, Members of Parliament (MPs) are elected by regional circles, but voting intention polls only happen at the nation level, often leading to surprising national electoral results. We aim at developing an electoral model for the Portuguese parliamentary by using not only national but also regional voting patterns and non-traditional data sources to complement traditional polling.

# Data-Driven Policy  # Elections

The project aimed to support local authorities in understanding and measuring tourism beyond traditional surveys and statistics so that they can explore and design solutions for sustainable tourism in the city.

Partners: Toscana Promozione Turistica and Vodafone Italy

# Data Science for Social Good 2017  # Tourism Management  # Data Driven Policy

For several decades scientists from different fields have realized that many features of the natural and human world do not follow Gaussian distributions. On the contrary, quantities such as the magnitude of Earthquakes, the income of individuals, or the number of Facebook friends have "heavy tail" distributions. That means that while there are many instances of weak earthquakes, from time to time, there are a few extremely devastating ones. It is unclear how well classical methods (generalized linear models, etc.) are informative for these phenomena. We want to tackle this problem by understanding which human-based activities have heavy tails; assess the impact of these rare events, and modify existing empirical models to give us information about them.

# Human Behaviour

Illegal fishing and over-fishing are posing great threats to our oceans. It is estimated that 70% of global fisheries are over-exploited, and many are now on the brink of collapse. Populations of tuna, a critical apex predator in many marine ecosystems, have declined by over 90% in the past 40 years. Unless serious action is taken, we may be on the brink of large scale fishery collapses, which could devastate the environment and the livelihoods of millions around the world that depend on such fisheries.

The project aimed to create an open-source Risk Tool combining multiple satellite data sources to help overcome illegal, unreported and unregulated fishing, and creating a risk score.

Partners: Spire, World Economic Forum, Planet and DigitalGlobe

# Data Science for Social Good 2017  # Sustainability

Scientific knowledge has been accepted as the main driver of development, allowing for longer, healthier, and more comfortable lives. Still, public support to scientific research is wavering, with large numbers of people being uninterested or even hostile towards science. This is having serious social consequences, from the anti-vaccination community to the recent "post-truth" movement. We still lack an encompassing theory that can explain the public understanding of science, allowing for more targeted and informed approaches.

We are using large datasets, over many years, to try to better understand what influences people’s attitudes towards science.

# Human Behaviour

The goal of the project was to assist Cascais’ Municipality in understanding patterns of unemployment in the region and to develop a system to recommend the best type of interventions to bridge skills gaps and increase people’s likelihoods of employment.

Partners: Câmara Municipal de Cascais and IEFP

# Data Science for Social Good 2017  # Unemployment  # Data Driven Policy

Understanding how the public behaves during a health crisis is very valuable information for public health institutions. We found that during a health crisis setting, the 2009 flu pandemic, certain search trends proxied the population’s anxiety levels and that these were more associated with media reports. We are now expanding these techniques to better understand anxiety and fear spreading.

# Human Behaviour  # Healthcare Crisis

The project focused on optimizing matchmaking between patients and doctors by developing an automated mediation service. Its main objective was to increase the likelihood of a long-lasting relationships and the quality of follow-ups, as well as the practice of preventive medicine.

Partner: José de Mello Saúde

# Data Science for Social Good 2017  # Healthcare  # Decision-Making

The project aimed to help Rijkswaterstaat, a division of the Dutch Ministry of Infrastructure and Environment, by developing a policy for optimizing stationary and patrolling locations of inspectors on duty to minimize the time it takes them to reach an incident site. This way, the project contributed to optimize safety and traffic flow for road users.

Partner: Rijkswaterstaat

# Data Science for Social Good 2017  # Transportation  # Decision-Making

The project aimed to figure out how improved use of its rooftops could help address challenges with water storage, green spaces, and energy generation. In order to achieve this, the team used aerial and satellite images to identify the usage of rooftops in Rotterdam.

Partner: City of Rotterdam

# Data Science for Social Good 2017  # Data-Driven Policy