Beyond the Headlines: Understanding Sentiments and Morals Impacting Female Employment in Spain

TL;DR

This study analyzes how Spanish news media depict female unemployment from 2000 to 2022 by applying a fine-grained FiGAS sentiment framework augmented with MoralStrength and LibertyMFD moral lexicons. By leveraging a large national and regional news corpus and Sense2Vec-derived terms, the authors extract aspect-based sentiment and moral polarity tied to the topic of female labor market outcomes, with geographic attribution to NUTS regions and a $90$-day smoothing to reveal temporal dynamics. The results show consistent negative sentiment and weaker liberty and fairness moral signals for female unemployment during economic downturns, with stronger regional variations and amplified effects during crises such as the 2008 recession and the COVID-19 pandemic. The approach is data-driven, generalizable to other topics, and offers a potential tool for policymakers to monitor gendered narratives in near real time, complementing official statistics. Limitations include lexicon coverage and translation noise, motivating future multilingual enhancements and lexicon development for broader applicability.

Abstract

After decades of improvements in the employment conditions of females in Spain, this process came to a sudden stop with the Great Spanish Recession of 2008. In this contribution, we analyse a large longitudinal corpus of national and regional news outlets employing advanced Natural Language Processing techniques to capture the valence of mentions of gender inequality expressed in the Spanish press. The automatic analysis of the news articles does indeed capture the known hardships faced by females in the Spanish labour market. Our approach can be straightforwardly generalised to other topics of interest. Assessing the sentiment and moral values expressed in the articles, we notice that females are, in the majority of cases, concerned more than males when there is a deterioration in the overall labour market conditions, based on newspaper articles. This behaviour has been present in the entire period of study (2000--2022) and looked particularly pronounced during the economic crisis of 2008 and the recent COVID-19 pandemic. Most of the time, this phenomenon looks to be more pronounced at the regional level, perhaps caused by a significant focus on local labour markets rather than on aggregate statistics or because, in local contexts, females might suffer more from an isolation or discrimination condition. Our findings contribute to a deeper understanding of the gender inequalities in Spain using alternative data, informing policymakers and stakeholders.

Figures (7)

• Figure 1: Articles' sentiment for the daily news about the (un)employment and labour market topics in Spain using a 90 days smoothing window. The average number of observations is normalised by the number of articles released over the same period. Red dotted lines indicate the beginnings of important periods of economic and social distress (Great Spanish Recession, EU Sovereign Debt Crisis, and COVID-19 pandemic).
• Figure 2: Sentiment polarity distributions per year (see Table \ref{['tab:perce-difference-year-sentiment']}) The dashed line corresponds to the first decile.
• Figure 3: Regional (NUTS2) percentage quantile differences in sentiment polarity (see Table \ref{['tab:perce-difference-nuts2-sentiment']})
• Figure 4: Geographic distribution of the percentage difference in sentiment polarity (10% quantile) for each Spanish region (NUTS2) between the (un)employment and labour market topics for "Female" and "Non-Female". A brighter red shade indicates an higher percentage difference and hence a more negative sentiment on the way the "Female" population is discussed about in the labour market related press.
• Figure 5: Percentage difference (10% quantile) in polarity per year for the liberty and fairness moral values between "Female" and "Non-Female" for the (un)employment and labour market topics.