Talks and presentations

Tracking the Connections Between Public Health and Climate Change

January 27, 2020

Talk, Applied Machine Learning Days at Swiss Federal Institute of Technology Lausanne, Lausanne, Switzerland

Climate change is undermining the foundations of good health; threatening the food we eat, the air we breathe, and the hospitals and clinics we depend on. However, the response to climate change could be the greatest global health opportunity of the 21st century. The Lancet Countdown: Tracking Progress on Health and Climate Change brings together 35 leading academic institutions and UN agencies from every continent to monitor this transition from threat to opportunity. We track annual indicators of progress, empowering the health profession and supporting policymakers to accelerate their response. In the talk we discuss the application of machine learning and natural language processing to develop and track a set of Lancet Countdown indicators.

Complexity and Data Science: Cluster of Methods - pattern analysis, machine learning, causal inference

November 25, 2019

Talk, Helmholtz Incubator Information and Data Science Workshop, Berlin, Germany

The talk covers the application of data science methods and tools for complex systems as enabler of new science. The Cynefin Framework is introduced as a practical approach to complex systems. The enabling role of machine learning and natural language processing is discussed in the context of the social care system.

AI for SDG 16 on Peace, Justice, and Strong Institutions: Tracking Progress and Assessing Impact

August 11, 2019

Talk, Workshop on Artificial Intelligence and United Nations Sustainable Development Goals, IJCAI International Joint Conferences on Artificial Intelligence, Macao, China

The transition from the Millennium Development Goals (MDGs) to the Sustainable Development Goals (SDGs) brought with it significant changes in the process of creating the goals and with the actual content of the SDGs. One of the most important developments was the inclusion of SDG 16, which recognises the central role of effective, accountable and inclusive political institutions in promoting sustainable development. Yet, a significant shortcoming is the difficulty in measuring progress on this SDG 16. In addition to general issues linked with data availability across the various indicators, a key challenge is aggregating trends across these wide-ranging indicators to track overall progress on SDG 16. A second issue that follows, is that despite claims regarding the centrality of SDG 16 for achieving the other SDGs, little is known about the causal pathways from the different indicators in SDG 16 to the other SDGs and associated indicators. In other words, questions remain over how changes in SDG 16 indicators impact a country’s progress towards indicators linked to health, gender equality, water and sanitation, and climate change.

AI for Common Good

June 14, 2019

Talk, AI TRAPS: Automating Discrimination, Berlin, Germany

AI FOR THE PEOPLE: AI Bias, Ethics & The Common Good. What is the role of AI in improving public services? What is the role of academia in the process? How can we improve collaboration between academia and government to tackle challenges of public service delivery with data science and AI?

NLP Applications in Political Science

December 12, 2018

Talk, Language and Computation Seminar Series, School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK

Political science scholars working with large quantities of textual data are often interested in discovering latent semantic structures in their document collections. Examples include legislative debates, policies, media content, manifestos, and open-ended survey questions. Domain idiosyncrasies often do not allow direct application of standard NLP toolkit. This talk will introduce several recent applications in the areas of climate change politics, international relations, legislative politics, and armed conflict prediction.

Data Science and AI for Public Good: Lessons from cross-sectoral collaboration

November 27, 2018

Talk, Bringing Data To Life For Policy and Practice: The BLGDRC Conference 2018, London, UK

Around the world, cross-sectoral collaborations between universities and the public sector are the norm for leveraging data science and artificial intelligence based capabilities to deliver policy and shape efficiencies in highly uncertain environments. In line with this vision, the HEFCE funded Catalyst Project brought together Essex County Council, Suffolk County Council, and University of Essex to enable innovative and far reaching responses to pressing national and local issues. While such cross-sectoral collaboration is not new, there is a lack of a systematic review of the empirical evidence about which managerial strategies help overcome the serious challenges involved with interorganisational collaboration. This talk presents the first results from a programme of study to take stock of the lessons learnt in the project around collaboration between public authorities and the University and to place these in the context of global best practices in cross-sectoral collaboration.

Transfer Topic Labeling with Domain-Specific Knowledge Base: An Analysis of UK House of Commons Speeches 1935-2014

November 08, 2018

Talk, Center for Comparative & International Studies, University of Zurich, Zurich, Switzerland

Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching meaningful labels to estimated topics. This process of manual labeling is not scalable and suffers from human bias. We present a transfer learning approach to topic labeling that leverages existing knowledge-base in political science to automatically label topics. These labels can be used instead of human labeling or supplementing it by guiding the labeling process in a more replicable procedure by retaining humans in the loop. We demonstrate our approach with a large scale topic model analysis of the complete corpus of UK House of Commons speeches 1935-2014, using the coding instructions of the Comparative Agendas Project to label topics. We evaluate our results using human expert coding. We show that our approach works well for a majority of the topics we estimate; but we also find that institution-specific topics, in particular on subnational governance, require manual input.

Text Analysis and International Organizations

January 22, 2018

Tutorial, Empirical Research on International Organizations, Lorentz Workshop, Leiden University, Leiden, Netherlands

This tutorial covers how diplomats can use data and sophisticated analytical tools (namely Natural Language Processing and advanced statistical methods) to better understand and conduct multilateral diplomacy.

Data science for the public sector

October 31, 2017

Talk, The growing ubiquity of algorithms in society: implications, impacts and innovations. The Royal Society Scientific Meeting, London, UK

Public sector organisations are increasingly interested in using data science capabilities to deliver policy and generate efficiencies in high uncertainty environments. The long-term success of data science in the public sector relies on successfully embedding it into delivery solutions for policy implementation. This requires organisational innovation and change delivered through structural and cultural adaptation, together with capacity building. Another key factor for success is the contribution of academia and the private and third sector. This talk will discuss the opportunities that exist for using data science in delivering public services at the international and national levels.