The 5th IEEE International
Conference on Data Science
and Advanced Analytics

1–4 October 2018
Turin — Italy

Data Science for Social Good

10:30 - 15:55, room “Piemonte”
  • 10:30Opening remarks
  • 10:35Keynote presentation: Marcel Salathé, EPFL, Lausanne, Switzerland
  • 11:15“Weak nodes detection in urban transport systems: Planning for resilience in Singapore”
    Michele Ferretti, Gianni Barlacchi, Lorenzo Lucchini, Luca Pappalardo and Bruno Lepri
  • 11:40“Data fusion to describe and quantify search and rescue operations in the Mediterranean Sea”
    Katherine Hoffmann Pham, Jeremy Boy and Miguel Luengo-Oroz
  • 12:05“Global income inequality and savings: A data science perspective”
    Kiran Sharma, Subhradeep Das and Anirban Chakraborti
  • 12:30Conference lunch
  • 14:00Oral contribution: Sarah McGough, Harvard University, Boston, USA
  • 14:30“Fine-grained Analysis of Cyberbullying using Weakly-Supervised Topic Models”
    Yue Zhang and Arti Ramesh
  • 15:05“Matchmaking between Patients and Doctors in Primary Care: Toward a Trusting Relationship”
    Qiwei Han, Mengxin Ji, Inigo Martınez De Rituerto Troya, Manas Gaur and Leid Zejnilovic
  • 15:30“Coolabilities API”
    David Nordfors, Sudipto Shankar Dasgupta, Ganapathy Subramanian, Ferose V R, Chally Grundwag and Behrang Zandi

Keynote Speakers

Marcel Salathé

“Crowdsourcing and Benchmarking: Making AI more accessible and adoptable”

AI development and adoption currently face two critical roadblocks. On the one hand, *despite* the open nature of the technology communities, AI development is still rather inaccessible to large parts of industry and academia. On the other hand, *because* of the open nature of the technology communities, AI can in principle be developed by anyone. This leads to an interesting paradox where we do not see enough people working on relevant problems, and at the same time, we see a confusing offer of AI models presented in a mix of outlets, from preprints to websites to apps on the various app stores. In this presentation, I will talk about efforts involving crowdsourcing, and community efforts like the Focus Group "AI for health”, to make AI both more accessible and adoptable.

Sarah McGough
Boston Children's Hospital,
Harvard University, Boston, USA

“Digital Disease Detection: Predictive analytics to improve disease surveillance in low-resource settings”

Disease surveillance is undermined by extended delays between symptom onset and official case reports, often due to complex and multi-tiered disease reporting and communication systems interacting at national, state, and city levels. Timeliness of reporting is exacerbated in low-resource settings that are strained by understaffing and underequipped surveillance units. Digital data streams that are available in real- or near-real-time have the potential to complement or enhance infectious disease surveillance by quickly and continuously capturing signals of population health activity that may be meaningful for disease tracking and forecasting. Focusing on a collection of inputs including Google search trends, Twitter, news reports, and satellite weather data, I will discuss the recent applications of novel data streams in disease detection, and the opportunities and challenges in leveraging these data to build real-time decision support tools for public health decision-makers.

Aims and Scope

Nowadays, we are witnessing an ever increasing interest in the exciting opportunities provided by data science when applied to the fields of social innovation, philanthropy, international development and humanitarian aid. From the analysis of satellite imagery to mapping poverty, to using Facebook data to track the global digital gender gap, the field of “Data Science for Social Good” is growing fast. Data from industrial actors (e.g. mobile phones data, remote sensing, satellite imagery) as well as data from digital traces generated by the pervasiveness of the Web in combination with state-of-the-art knowledge generated by data science can be synergically exploited to solve issues around many social problems and support global agencies and policymakers in implementing better and more impactful policies and interventions.

The goal of this session is to gather researchers from the fields of data science, machine learning and artificial intelligence together with experts in the social and political sciences to present and discuss applications of data science with a high social impact. The session will consist of: i) one or two invited presentations from the leading practitioners in the field, and ii) a series of contributed presentations on applied research that fits the theme of data science for social good in a broad sense.

In particular, in this special session we want to cover examples of Data Collaboratives, a new form of collaboration, beyond the public-private partnership model, in which participants from different sectors — especially companies — exchange their data to create public value. Also, the session will particularly welcome those contributions which aim at closing the gap between developing models and algorithms, and their practical applications in the workflow of non-profit organizations. Other topics of interest will be: models interpretability in support of better decision making; data science applied to impact measurement of social good programs; algorithmic privacy and fairness in the context of social good.

Topics of Interest

  • International development
  • Humanitarian aid
  • Gender data gaps
  • Health in developing countries
  • Migrations
  • Education
  • Unemployment
  • Inequality and poverty reduction
  • Environment and sustainability


Daniela Paolotti
ISI Foundation,
Turin, Italy

Michele Tizzoni
ISI Foundation,
Turin, Italy

Contact Persons

Daniela Paolotti –
Michele Tizzoni –

This site uses third parties' cookies.
If you want to know more or deny your consent to all or some of the cookies click here.
If you access any element below this banner you consent to the use of cookies.