@article{ChatsiouJankin, author = {Chatsiou, Kakia and Jankin, Slava}, title = {Deep Learning for Political Science}, series = {The SAGE Handbook of Research Methods in Political Science and International Relations}, journal = {The SAGE Handbook of Research Methods in Political Science and International Relations}, abstract = {Political science, and social science in general, have traditionally been using computational methods to study areas such as voting behavior, policy making, international conflict, and international development. More recently, increasingly available quantities of data are being combined with improved algorithms and affordable computational resources to predict, learn, and discover new insights from data that is large in volume and variety. New developments in the areas of machine learning, deep learning, natural language processing (NLP), and, more generally, artificial intelligence (AI) are opening up new opportunities for testing theories and evaluating the impact of interventions and programs in a more dynamic and effective way. Applications using large volumes of structured and unstructured data are becoming common in government and industry, and increasingly also in social science research. This chapter offers an introduction to such methods drawing examples from political science. Focusing on the areas where the strengths of the methods coincide with challenges in these fields, the chapter first presents an introduction to AI and its core technology - machine learning, with its rapidly developing subfield of deep learning. The discussion of deep neural networks is illustrated with the NLP tasks that are relevant to political science. The latest advances in deep learning methods for NLP are also reviewed, together with their potential for improving information extraction and pattern recognition from political science texts.}, language = {en} } @article{CampionGascoJankinetal., author = {Campion, Averill and Gasco, Mila and Jankin, Slava and Esteve, Marc}, title = {Managing Artificial Intelligence Deployment in the Public Sector}, series = {Computer/IEEE, 2020}, volume = {53}, journal = {Computer/IEEE, 2020}, number = {10}, doi = {10.1109/MC.2020.2995644}, pages = {28 -- 37}, abstract = {The scarcity of empirical evidence surrounding the organizational challenges and successful approaches to artificial intelligence (AI) deployment has resulted in mostly theoretical conceptualizations. By analyzing policy labs and offices of data analytics across the US to understand organizational challenges of AI adoption and implementation in the public sector as well as to identify successful management strategies to address such challenges, our study moves from speculation to gathering evidence. Our findings show that most challenges are found during the implementation stage and include challenges related to skills, culture, and resistance to share the data driven by data challenges. Further, our results indicate that long term strategies and short term actions need to be put in place to address these challenges. Among the first ones, leadership and executive support and stakeholder management seem to play an important role. Data standardization, training, and data-sharing agreements also seem to be successful specific short-term actions.}, language = {en} } @article{DasandiGrahamLampardetal., author = {Dasandi, Niheer and Graham, Hilary and Lampard, Pete and Jankin, Slava}, title = {Engagement with health in national climate change commitments under the Paris Agreement: a global mixed-methods analysis of the nationally determined contributions}, series = {Lancet Planetary Health}, volume = {5}, journal = {Lancet Planetary Health}, number = {2}, doi = {10.1016/S2542-5196(20)30302-8}, pages = {93 -- 101}, abstract = {Background: Instituted under the Paris Agreement, nationally determined contributions (NDCs) outline countries' plans for mitigating and adapting to climate change. They are the primary policy instrument for protecting people's health in the face of rising global temperatures. However, evidence on engagement with health in the NDCs is scarce. In this study, we aimed to examine how public health is incorporated in the NDCs, and how different patterns of engagement might be related to broader inequalities and tensions in global climate politics. Methods: We analysed the NDCs in the UN Framework Convention on Climate Change registry submitted by 185 countries. Using content analysis and natural language processing (NLP) methods, we developed measures of health engagement. Multivariate regression analyses examined whether country-level factors (eg, population size, gross domestic product [GDP], and climate-related exposures) were associated with greater health engagement. Using NLP methods, we compared health engagement with other climate-related challenges (ie, economy, energy, and agriculture) and examined broader differences in the keyword terms used in countries with high and low health engagement in their NDCs. Findings: Countries that did not mention health in their NDCs were clustered in high-income countries, whereas greater health engagement was concentrated in low-income and middle-income countries. Having a low GDP per capita and being a small island developing state were associated with higher levels of health engagement. In addition, higher levels of population exposure to temperature change and ambient air pollution were associated with more health coverage included in a country's NDC. Variation in health engagement was greater than for other climate-related issues and reflected wider differences in countries' approaches to the NDCs. Interpretation: A focus on health in the NDCs follows broader patterns of global inequalities. Poorer and climate-vulnerable countries that contribute least to climate change are more likely to engage with health in their NDCs, while richer countries focus on non-health sectors in their NDCs, such as energy and the economy.}, language = {en} } @article{DasandiGrahamLampardetal., author = {Dasandi, Niheer and Graham, Hilary and Lampard, Pete and Jankin, Slava}, title = {Intergovernmental engagement on health impacts of climate change}, series = {Bulletin of the World Health Organization}, volume = {102}, journal = {Bulletin of the World Health Organization}, number = {111}, doi = {10.2471/BLT.20.270033}, abstract = {Objective: To examine country engagement with the health impacts of climate change in (1) annual statements in the UN General Debate (UNGD); and (2) the Nationally Determined Contributions (NDCs) of the Paris Agreement; and to identify what factors drive country engagement. Methods: First, we measure engagement by the total references to the health and climate change relationship in each text, using a keyword-in-context search with relevant search terms. Second, we use machine learning models, specifically random forest models, to identify the most important country-level predictors of engagement. Our predictors are political and economic factors, health outcomes, climate change-related variables, and membership of political negotiating groups in the UN. Findings: For both UNGD statements and NDCs, we find that that low- and middle-income countries discuss the health impacts of climate change much more than high-income countries. We find that the most important predictors of country engagement are related health outcomes (infant mortality rates, maternal death risk, life expectancy), countries' income levels (GDP per capita), and fossil fuel consumption. Membership of political negotiating groups (e.g. G77 and SIDS) is less important predictors. Conclusion: Our analysis indicates a North-South division in engagement, and hence there is little to suggest that a health framing of climate change overcomes existing geopolitical divisions in climate change negotiations. Countries who carry the heaviest health burdens but lack necessary resources to address the impacts of climate change are shouldering responsibility for reminding the global community of the implications of climate change for people's health.}, language = {en} } @article{WattsJankinMunzertetal., author = {Watts, Nick and Jankin, Slava and Munzert, Simon and Amann, Markus and Arnell, Nigel and Ayeb-Karlsson, Sonja and Beagley, Jessica and Belesova, Kristine and Boykoff, Maxwell and Byass, Peter and Cai, Wenjia and Campbell-Lendrum, Diarmid and Capstick, Stuart and Chambers, Jonathan and Coleman, Samantha and Dalin, Carole and Daly, Meaghan and Dasandi, Niheer}, title = {The 2020 report of The Lancet Countdown on health and climate change: responding to converging crises}, series = {The Lancet}, volume = {397}, journal = {The Lancet}, number = {10269}, doi = {10.1016/S0140-6736(20)32290-X}, pages = {129 -- 170}, abstract = {The world has already warmed by more than 1.2C compared with preindustrial levels, resulting in profound, immediate, and rapidly worsening health effects, and moving dangerously close to the agreed limit of maintaining temperatures "well below 2C". These health impacts are seen on every continent, with the ongoing spread of dengue virus across South America, the cardiovascular and respiratory effects of record heatwaves and wildfires in Australia, western North America, and western Europe, and the undernutrition and mental health effects of floods and droughts in China, Bangladesh, Ethiopia, and South Africa. In the long term, climate change threatens the very foundations of human health and wellbeing, with the Global Risks Report registering climate change as one of the five most damaging or probable global risks every year for the past decade.}, language = {en} } @article{UshakovaJankin, author = {Ushakova, Anastasia and Jankin, Slava}, title = {Big data to the rescue? Challenges in analysing granular household electricity consumption in the United Kingdom}, series = {Energy Research \& Social Science}, volume = {64}, journal = {Energy Research \& Social Science}, issn = {2214-6296}, doi = {10.1016/j.erss.2020.101428}, abstract = {Rapid growth in smart meter installations has given rise to vast collections of data at a high time-resolution and down to an individual level. However, to enable efficient policy interventions, we need to be able to appropriately segment the population of users. The aim of this paper is to consider challenges and opportunities associated with large highly-granular temporal datasets that describe residential electricity consumption. In particular, the focus is on experiments relating to aggregation of smart meter time-series data in the context of clustering and prediction tasks that are often used for customer targeting and to gain insight on energy-use about sub populations. To cluster energy use profiles, we propose a novel framework based on a set of Gaussian based models which we use to encode individuals' energy consumption over time. The dataset consists of half hourly electricity consumption records from smart meters of households in the UK (2014-2015). The contribution of this paper comes from its investigation of how consumers or groups may be clustered according to model parameters in scenarios where additional data on consumers is not available to the researcher, or where anonymity preservation of the smart meter user is prioritised. A secondary aim is to invite greater awareness when data reduction is required to reduce the size of a large dataset for computational purposes. This may have implications for policy interventions acting at the individual or small group level, for instance, when designing incentives to encourage energy efficient behaviour or when identifying fuel poor customers.}, language = {en} } @article{JankinRomanellovanDaalenetal., author = {Jankin, Slava and Romanello, Marina and van Daalen, Kim and Anto, Joesp M. and Dasandi, Niheer and Drummond, Paul and Hamilton, Ian G. and Kendrovski, Vladimir and Lowe, Rachel and Rockl{\"o}v, Joacim and Schmoll, Oliver and Semenza, Jan C. and Tonne, Cathryn and Nilsson, Maria}, title = {Tracking progress on health and climate change in Europe}, series = {The Lancet Public Health}, journal = {The Lancet Public Health}, doi = {10.1016/S2468-2667(21)00207-3}, abstract = {Left unabated, climate change will have catastrophic effects on the health of present and future generations. Such effects are already seen in Europe, through more frequent and severe extreme weather events, alterations to water and food systems, and changes in the environmental suitability for infectious diseases. As one of the largest current and historical contributors to greenhouse gases and the largest provider of financing for climate change mitigation and adaptation, Europe's response is crucial, for both human health and the planet. To ensure that health and wellbeing are protected in this response it is essential to build the capacity to understand, monitor, and quantify health impacts of climate change and the health co-benefits of accelerated action. Responding to this need, the Lancet Countdown in Europe is established as a transdisciplinary research collaboration for monitoring progress on health and climate change in Europe. With the wealth of data and academic expertise available in Europe, the collaboration will develop region-specific indicators to address the main challenges and opportunities of Europe's response to climate change for health. The indicators produced by the collaboration will provide information to health and climate policy decision making, and will also contribute to the European Observatory on Climate and Health.}, language = {en} } @article{RomanelloDiNapoliDrummondetal., author = {Romanello, Marina and Di Napoli, Claudia and Drummond, Paul and Green, Carole and Kennard, Harry and Lampard, Pete and Scamman, Daniel and Arnell, Nigel and Ayeb-Karlsson, Sonja and Berrang Ford, Lea and Belesova, Kristine and Bowen, Kathryn and Cai, Wenjia and Callaghan, Max and Campbell-Lendrum, Diarmid and Chambers, Jonathan and Daalen, Kim R van and Dalin, Carole and Dasandi, Niheer and Dasgupta, Shouro and Davies, Michael and Dominguez-Salas, Paula and Dubrow, Robert and Ebi, Kristie L and Eckelman, Matthew and Ekins, Paul and Escobar, Luis E and Georgeson, Lucien and Graham, Hilary and Gunther, Samuel H and Hamilton, Ian and Hang, Yun and H{\"a}nninen, Risto and Hartinger, Stella and He, Kehan and Hess, Jeremy J and Hsu, Shih-Che and Jankin, Slava and Jamart, Louis and Jay, Ollie and Kelman, Ilan and Kiesewetter, Gregor and Kinney, Patrick and Kjellstrom, Tord and Kniveton, Dominic and Lee, Jason K W and Lemke, Bruno and Liu, Zhao and Lott, Melissa and Lotto Batista, Martin and Lowe, Rachel and MacGuire, Frances and Sewe, Maquins Odhiambo and Martinez-Urtaza, Jaime and Maslin, Mark and McAllister, Lucy and McGushin, Alice and McMichael, Celia and Mi, Zhifu and Milner, James and Minor, Kelton and Minx, Jan C and Mohajeri, Nahid and Moradi-Lakeh, Maziar and Morrissey, Karyn and Munzert, Simon and Murray, Kris A and Neville, Tara and Nilsson, Maria and Obradovich, Nick and O'Hare, Megan B and Oreszczyn, Tadj and Otto, Matthias and Owfi, Fereidoon and Pearman, Olivia and Rabbaniha, Mahnaz and Robinson, Elizabeth J Z and Rockl{\"o}v, Joacim and Salas, Renee N and Semenza, Jan C and Sherman, Jodi D and Shi, Liuhua and Shumake-Guillemot, Joy and Silbert, Grant and Sofiev, Mikhail and Springmann, Marco and Stowell, Jennifer and Tabatabaei, Meisam and Taylor, Jonathon and Tri{\~n}anes, Joaquin and Wagner, Fabian and Wilkinson, Paul and Winning, Matthew and Yglesias-Gonz{\´a}lez, Marisol and Zhang, Shihui and Gong, Peng and Montgomery, Hugh and Costello, Anthony}, title = {The 2022 report of the Lancet Countdown on health and climate change: health at the mercy of fossil fuels}, series = {The Lancet}, volume = {400}, journal = {The Lancet}, number = {10363}, doi = {10.1016/S0140-6736(22)01540-9}, pages = {1619 -- 1654}, language = {en} } @article{RomanelloWalawenderHsuetal., author = {Romanello, Marina and Walawender, Maria and Hsu, Shih-Che and Moskeland, Annalyse and Palmeiro-Silva, Yasna and Scamman, Daniel and Ali, Zakari and Ameli, Nadia and Angelova, Denitsa and Ayeb-Karlsson, Sonja and Basart, Sara and Beagley, Jessica and Beggs, Paul J and Blanco-Villafuerte, Luciana and Cai, Wenjia and Callaghan, Max and Campbell-Lendrum, Diarmid and Chambers, Jonathan D and Chicmana-Zapata, Victoria and Chu, Lingzhi and Cross, Troy J and van Daalen, Kim R and Dalin, Carole and Dasandi, Niheer and Dasgupta, Shouro and Davies, Michael and Dubrow, Robert and Eckelman, Matthew J and Ford, James D and Freyberg, Chris and Gasparyan, Olga and Gordon-Strachan, Georgiana and Grubb, Michael and Gunther, Samuel H and Hamilton, Ian and Hang, Yun and H{\"a}nninen, Risto and Hartinger, Stella and He, Kehan and Heidecke, Julian and Hess, Jeremy J and Jamart, Louis and Jankin, Slava and Jatkar, Harshavardhan and Jay, Ollie and Kelman, Ilan and Kennard, Harry and Kiesewetter, Gregor and Kinney, Patrick and Kniveton, Dominic and Kouznetsov, Rostislav and Lampard, Pete and Lee, Jason K W and Lemke, Bruno and Li, Bo and Liu, Yang and Liu, Zhao and Llabr{\´e}s-Brustenga, Alba and Lott, Melissa and Lowe, Rachel and Martinez-Urtaza, Jaime and Maslin, Mark and McAllister, Lucy and McMichael, Celia and Mi, Zhifu and Milner, James and Minor, Kelton and Minx, Jan and Mohajeri, Nahid and Momen, Natalie C and Moradi-Lakeh, Maziar and Morrisey, Karyn and Munzert, Simon and Murray, Kris A and Obradovich, Nick and O'Hare, Megan B and Oliveira, Camile and Oreszczyn, Tadj and Otto, Matthias and Owfi, Fereidoon and Pearman, Olivia L and Pega, Frank and Perishing, Andrew J and Pinho-Gomes, Ana-Catarina and Ponmattam, Jamie and Rabbaniha, Mahnaz and Rickman, Jamie and Robinson, Elizabeth and Rockl{\"o}v, Joacim and Rojas-Rueda, David and Salas, Renee N and Semenza, Jan C and Sherman, Jodi D and Shumake-Guillemot, Joy and Singh, Pratik and Sj{\"o}din, Henrik and Slater, Jessica and Sofiev, Mikhail and Sorensen, Cecilia and Springmann, Marco and Stalhandske, Z{\´e}lie and Stowell, Jennifer D and Tabatabaei, Meisam and Taylor, Jonathon and Tong, Daniel and Tonne, Cathryn and Treskova, Marina and Trinanes, Joaquin A and Uppstu, Andreas and Wagner, Fabian and Warnecke, Laura and Whitcombe, Hannah and Xian, Peng and Zavaleta-Cortijo, Carol and Zhang, Chi and Zhang, Ran and Zhang, Shihui and Zhang, Ying and Zhu, Qiao and Gong, Peng and Montgomery, Hugh and Costello, Anthony}, title = {The 2024 report of the Lancet Countdown on health and climate change: facing record-breaking threats from delayed action}, series = {The Lancet}, volume = {404}, journal = {The Lancet}, number = {10465}, publisher = {Elsevier BV}, issn = {0140-6736}, doi = {10.1016/S0140-6736(24)01822-1}, pages = {1847 -- 1896}, language = {en} } @article{ChelottiDasandiJankinMikhaylov, author = {Chelotti, Nicola and Dasandi, Niheer and Jankin Mikhaylov, Slava}, title = {Do Intergovernmental Organizations Have a Socialization Effect on Member State Preferences? Evidence from the UN General Debate}, series = {International Studies Quarterly}, volume = {66}, journal = {International Studies Quarterly}, number = {1}, publisher = {Oxford University Press (OUP)}, issn = {0020-8833}, doi = {10.1093/isq/sqab069}, abstract = {The question of whether intergovernmental organizations (IGOs) have a socialization effect on member state preferences is central to international relations. However, empirical studies have struggled to separate the socializing effects of IGOs on preferences from the coercion and incentives associated with IGOs that may lead to foreign policy alignment without altering preferences. This article addresses this issue. We adopt a novel approach to measuring state preferences by applying text analytic methods to country statements in the annual United Nations General Debate (UNGD). The absence of interstate coordination with UNGD statements makes them particularly well suited for testing socialization effects on state preferences. We focus on the European Union (EU), enabling us to incorporate the pre-accession period—when states have the strongest incentives for foreign policy alignment—into our analysis. The results of our analysis show that EU membership has a socialization effect that produces preference convergence, controlling for coercion and incentive effects.}, language = {en} }