Natural Language Processing for Achieving Sustainable Development: the Case of Neural Labelling to Enhance Community Profiling

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8427–8444, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8427 Natural Language Processing for Achieving Sustainable Development: the Case of Neural Labelling to Enhance Community Profiling Costanza Conforti1,2, Stephanie Hirmer1,3, David Morgan4, Marco Basaldella2, Yau Ben Or1 1Rural Senses Ltd. 2Language Technology Lab, University of Cambridge 3Energy and Power Group, University of Oxford 4Centre for Sustainable Development, University of Cambridge info@ruralsenses.com Abstract In recent years, there has been an increasing interest in the application of Artificial Intel- ligence – and especially Machine Learning – to the field of Sustainable Development (SD). However, until now, NLP has not been sys- tematically applied in this context. In this paper, we show the high potential of NLP to enhance project sustainability. In particu- lar, we focus on the case of community pro- filing in developing countries, where, in con- trast to the developed world, a notable data gap exists. Here, NLP could help to ad- dress the cost and time barrier of structuring qualitative data that prohibits its widespread use and associated benefits. We propose the new extreme multi-class multi-label Auto- matic User-Perceived Value classification task. We release Stories2Insights (S2I), an expert- annotated dataset of interviews carried out in Uganda, we provide a detailed corpus analysis, and we implement a number of strong neural baselines to address the task. Experimental re- sults show that the problem is challenging, and leaves considerable room for future research at the intersection of NLP and SD. 1 Introduction Sustainable Development (SD) is an interdisci- plinary field which studies the integration and bal- ancing of economic, environmental and social con- cerns to tackle the broad goal of achieving inclusive and sustainable growth (Brundtland, 1987; Keeble, 1988; Sachs, 2015). As a collective, trans-national effort toward sustainability, in 2015 the United Na- tions approved the 2030 Agenda (United Nations, 2015), which identifies 17 Sustainable Develop- ment Goals (SDGs) to be reached by 2030 (Lee et al., 2016). In recent years, there has been in- creasing recognition of the fundamental role played by data in achieving the objectives set out in the SDGs (Griggs et al., 2013; Nilsson et al., 2016; Vinuesa et al., 2020). In this paper, we focus on data-driven planning and delivery of projects1 which address one or more of the SDGs in a developing country con- text. When dealing with developing countries, a deep understanding of project beneficiaries’ needs and values (hereafter referred to as User-Perceived Values or UPVs, Hirmer and Guthrie (2016)) is of particular importance. This is because benefi- ciaries with limited financial means are especially good at assessing needs and values (Hirji, 2015). When a project fails to create value to a benefit- ing community, the community is less likely to care about its continued operation (Watkins et al., 2012; Chandler et al., 2013; Hirmer, 2018) and as a consequence, the chances of the project’s long- term success is jeopardised (Bishop et al., 2010). Therefore, comprehensive community profiling2 plays a key …

Content truncated to 500 words