Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals
This work addresses the problem of scalable and reliable text analysis for researchers in fields like political science and social media studies, offering an incremental improvement over existing dictionary-based methods.
The paper tackles the challenge of quantifying message features like moral content in text by introducing vec-tionaries, which enhance validated dictionaries with word embeddings through nonlinear optimization, resulting in measurements better aligned with human assessments and enabling prediction of outcomes such as message retransmission.
While researchers often study message features like moral content in text, such as party manifestos and social media, their quantification remains a challenge. Conventional human coding struggles with scalability and intercoder reliability. While dictionary-based methods are cost-effective and computationally efficient, they often lack contextual sensitivity and are limited by the vocabularies developed for the original applications. In this paper, we present an approach to construct vec-tionary measurement tools that boost validated dictionaries with word embeddings through nonlinear optimization. By harnessing semantic relationships encoded by embeddings, vec-tionaries improve the measurement of message features from text, especially those in short format, by expanding the applicability of original vocabularies to other contexts. Importantly, a vec-tionary can produce additional metrics to capture the valence and ambivalence of a message feature beyond its strength in texts. Using moral content in tweets as a case study, we illustrate the steps to construct the moral foundations vec-tionary, showcasing its ability to process texts missed by conventional dictionaries and word embedding methods and to produce measurements better aligned with crowdsourced human assessments. Furthermore, additional metrics from the vec-tionary unveiled unique insights that facilitated predicting outcomes such as message retransmission.