Measure Country-Level Socio-Economic Indicators with Streaming News: An Empirical Study

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 1249–1254, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 1249 Measure Country-Level Socio-Economic Indicators with Streaming News: An Empirical Study Bonan Min Raytheon BBN Technologies bonan.min@raytheon.com Xiaoxi Zhao Department of Economics, Boston University xiaoxiz@bu.edu Abstract Socio-economic conditions are difficult to measure. For example, the U.S. Bureau of Labor Statistics needs to conduct large-scale household surveys regularly to track the un- employment rate, an indicator widely used by economists and policy makers. We ar- gue that events reported in streaming news can be used as “micro-sensors” for measuring socio-economic conditions. Similar to collect- ing surveys and then counting answers, it is possible to measure a socio-economic indica- tor by counting related events. In this paper, we propose Event-Centric Indicator Measure (ECIM), a novel approach to measure socio- economic indicators with events. We empiri- cally demonstrate strong correlations between ECIM values to several representative indica- tors in socio-economic research. 1 Introduction Socio-economic indicators are powerful instru- ments for measuring economic conditions and the sociocultural environment that people live in. They are widely used to inform policy makers, and help them to measure outcome of policy interven- tions. They are often difficult, if not impossible, to measure. Take unemployment rate as an exam- ple, the U.S. Bureau of Labor Statistics conducts large-scale household surveys in order to track it. More abstract indicators (e.g. economic uncer- tainty), which involve vague or complex social in- teractions, are very difficult to measure accurately. We hypothesize that streaming news, reporting a vast amount of real-world events, can be used for measuring socio-economic indicators. We pro- pose Event-Centric Indicator Measure (ECIM), a novel approach to measure socio-economic in- dicators using events extracted from streaming news. We demonstrated that ECIM is effective; ECIM values are strongly correlated with repre- sentative socio-economic indicators. Figure 1: The ECIM workflow. Words in bold are event triggers. Text in parentheses shows normalized loca- tions (countries) and time. “Related” shows whether an event trigger is related to the target indicator (e.g., “unemployment rate”) based on keyword matching. We will first present an overview of the ECIM approach, and then describe how we extract events from text and aggregate them to calculate EC- IMs for each socio-economic indicator. We will then present large-scale experiments to demon- strate that ECIM is effective, using several widely used socio-economic indicators. 2 Event-Centric Indicator Measure The ECIM workflow is summarized in Figure 1. Given a large-scale streaming news collection, the system first extracts event mentions (event trigger words or phrases) along with their locations and time. For each socio-economic indicator, the sys- tem will then aggregate relevant events per each time step to produce ECIM, a time series measur- ing the corresponding socio-economic condition. 2.1 Extract Events from Text We extract event frames from predicate-argument structures that are automatically generated from 1250 text. Then we extract an event trigger, a location and a …

Content truncated to 500 words