ACM Celebration of Women in Computing: womENcourage 2019

The Data Science for Society event is a workshop organized by the Knowledge Discovery and Data Mining Laboratory (KDD Lab) within the 6th ACM Celebration of Women in Computing: womENcourage 2019. The workshop brings together women in careers in computing science to exchange knowledge and experience.

More information about the 6th ACM Celebration of Women in Computing: womENcourage 2019 can be found at ACM Celebration of Women in Computing: womENcourage 2019

about the workshop

The big data arising from the digital breadcrumbs of human activities promise to let us scrutinize the ground truth of individual and collective behaviour at an unprecedented detail and scale. Big data, combined with social data mining, i.e., adequate means for accessing big data and extracting useful knowledge from them provide a chance to understand the complexity of our contemporary, globally-interconnected society: e.g., disentangling urban sustainability and resilience, societal well-being and its multiple facets, the unequal distribution of resources and opportunities, the "ecological" problems of our information system, such as polarization and misinformation, the dynamics and economic drivers behind human migration. This workshop will focus on examples of social mining and big data research answering challenging questions in different domains that have been developed within the project SoBigData.

On line debates: i) is there any consequence in opinion formation and diffusion due to the algorithm bias present in social media platforms? [1]; ii) using Twitter as a proxy of our society, to monitor opinions about politicians, looking at abuse broken down by parties and gender [2].

Migration: discussions about the refugee crisis and the United Kingdom European Union membership referendum. These complex and contended topics can be analyzed monitoring online social networks like Twitter [3]. Discussion about the possibility to infer immigrants' rate by using Twitter data and by exploiting Sentiment Analysis techniques [4,5].

City of Citizens: how to invest in car sharing [6], autonomous drive and electric mobility, as starting point for enabling smart city solutions.

On top of this, a fundamental point that often is forgotten regards ethics and its implication. In particular, we want to describe some of challenging methodologies and solutions to privacy analysis [7] and explainability of algorithms [8].

[1] A. Sîrbu, D. Pedreschi, F. Giannotti, J. Kertész, Algorithmic bias amplifies opinion fragmentation and polarization: A bounded confidence model, PLOS one, Published: March 5, 2019
[2] G. Gorrell, M. Greenwood, I. Roberts, D. Maynard, K. Bontcheva, Online abuse of uk mps in 2015 and 2017: Perpetrators, targets, and topics, arXiv preprint arXiv:1804.01498
[3] M. Coletto, A. Esuli, C. Lucchese, C. Muntean, F. Nardini, R. Perego, C. Renso, Perception of social phenomena through the multidimensional analysis of online social networks, Online Social Networks and Media 1:2017
[4] L. Pollacci, A. Sîrbu, F. Giannotti, D. Pedreschi, C. Lucchese, C.I. Muntean. Sentiment spreading: an epidemic model for lexicon-based sentiment analysis on twitter. In Conference of the Italian Association for Artificial Intelligence, 2017, November, 114-127. Springer, Cham.
[5] L. Pollacci, A. Sîrbu, F. Giannotti, D. Pedreschi. Measuring the Salad Bowl: Superdiversity on Twitter. Submitted
[6] C. Boldrini, R. Bruno, M. Laarabi. Weak signals in the mobility landscape: car sharing in ten European cities, EPJ Data Science 8 (1), 7
[7] F. Pratesi, A. Monreale, R. Trasarti, F. Giannotti, D. Pedreschi, T. Yanagihara. PRUDEnce: a system for assessing privacy risk vs utility in data sharing ecosystems, Transaction on Data Privacy. Journal. 11 (2018)
[8] R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, D. Pedreschi. A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51 (5), 93, 2018

invited speakers

Chiara Boldrini
Since 2012, I’m a permanent researcher in the Ubiquitous Internet group of IIT-CNR in Italy. My research interests are opportunistic/DTN networking, smart transportation and urban computing, social network analysis. I have investigated both the algorithmic aspects of opportunistic networks (contributing the HiBOp and ContentPlace protocols) and their analytical modelling. I have also worked on the modelization of human mobility (you may have heard of the HCMM protocol). Recently, I have spent most of my time studying issues related to smart transportation, with a special focus on car sharing systems. In particular, I have designed optimized supply models for innovative car sharing systems and I have investigated the potential of mining car sharing datasets (hint: lots of very interesting info can be discovered). I am now focusing more on online social network analysis, specifically studying the ego-network structure in Twitter and other online social networks.
Fosca Giannotti
Fosca Giannotti is a director of research of computer science at the Information Science and Technology Institute "A. Faedo" of the National Research Council, Pisa, Italy. Fosca Giannotti is a pioneering scientist in mobility data mining, social network analysis and privacy-preserving data mining. Fosca leads the Pisa KDD Lab - Knowledge Discovery and Data Mining Laboratory, a joint research initiative of the University of Pisa and ISTI-CNR, founded in 1994 as one of the earliest research lab centered on data mining. Fosca's research focus is on social mining from big data: smart cities, human dynamics, social and economic networks, ethics and trust, diffusion of innovations. She has coordinated tens of European projects and industrial collaborations. Fosca is now the coordinator of SoBigData, the European research infrastructure on Big Data Analytics and Social Mining, an ecosystem of ten cutting edge European research centres providing an open platform for interdisciplinary data science and data-driven innovation.
Diana Maynard
Diana Maynard is a Research Fellow at the University of Sheffield, UK. She has a PhD in Natural Language Processing and mostly spends her time developing tools for text analysis, in particular for social media, as well as teaching and consultancy work. She has over 60 academic publications and lots of experience organising conferences, giving talks and managing projects.
Cristina Ioana Muntean
Cristina Ioana Muntean is a permanent researcher at High Performance Computing lab, at ISTI-CNR. She received her PhD in 2013 from Babes-Bolyai University in Romania. She joined the HPC lab after finishing her dissertation and has worked with the group members on topics related to Information Retrieval. Her main research interests are IR and Machine Learning with applications to web search, news and social media. She is particularly interested in sequential neural models and their application to text summarization and web / news retrieval. Another research interest is trajectories and mobility analysis and applications. She has published papers in top-tier conferences and journals in the field and she has also gained experience in working on European and regional projects.
Alina Sirbu
Alina is Assistant Professor of Computer Science at University of Pisa, and member of the Knowledge Discovery and Data Mining laboratory. Her research interests are Complex Systems Modelling, Data Science and Machine Learning, applied to a variety of systems ranging from technical (HPC systems, data centres), social (opinion dynamics, social choice theory, behaviour change) to biological (gene regulatory networks). Her work has appeared in BMC Bioinformatics, PLOS One, Journal of Statistical Physics, Nature Methods, Cluster Computing, Quality and Quantity, Advances in Complex Systems and other international journals and conferences. She was previously Research Assistant at Bologna University, Italy, and Postdoctoral Researcher at the Institute for Scientific Interchange in Turin. In 2014 se was Visiting Assistant Professor at New York University, Shanghai. She holds a PhD in Computational Biology from Dublin City University, Ireland and a BSc in Computer Science from AI Cuza. University in Iasi, Romania. She was recipient of the Irish Research Council for Science Engineering and Technology EMBARK scholarship award in 2008.


11:00 - 11:10

Welcome and Overview of the Workshop

Introduction to the workshop: SoBigData, an ecosystem for Social Mining Research

11:10 - 11:35

Invited talk on "Migration" (Cristina I. Muntean)

Presentation of studies on perception about immigrants and Brexit.

11:35 - 12:05

Invited talk on "On line debates" (Diana Maynard)

Description of the use of Twitter to monitor opinions of politicians, showing an increment over the time of abuse directed at women and those not in the currently governing party.

12:05 - 12:30

Invited talk on "On line debates" (Alina Sirbu)

Description of the role of social networks and online media in shaping public debate and the problems related to algorithmic bias that is believed to enhance fragmentation and polarization of the societal debate.

12:30 - 13:30

Lunch break

13:30 - 13:55

Invited talk on "Migration" (Alina Sirbu)

Description of the joint usage of Twitter and Sentiment Analysis to now-cast immigrants' rates in Italy and United Kingdom.

13:55 - 14:20

Invited talk on "City of Citizens" (Chiara Boldrini)

Introducing car sharing possibilities but also major obstacles in the demand. We discuss which sociodemographic and urban activity indicators are associated with variations in car sharing request.

14:20 - 15:00

Invited talk on "Data Science & Ethics" (Fosca Giannotti)

Discussion on the urgent open challenge of how to construct meaningful explanations of black box and opaque AI/ML systems.


letizia milli

University of Pisa & CNR Pisa ISTI KDDLab, Italy

michela natilli

University of Pisa & CNR Pisa ISTI KDDLab, Italy

laura pollacci

University of Pisa & CNR Pisa ISTI KDDLab, Italy

francesca pratesi

University of Pisa & CNR Pisa ISTI KDDLab, Italy


Graziella Lonardi Buontempo room - MAXXI (National Museum of XXI Century Arts), Rome, Italy