Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals

arXiv:2312.05990v2 Announce Type: replace
Abstract: 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 …

abstract arxiv case case study challenge coding cost cs.cl dictionary extract features human media quantification reliability researchers scalability social social media study text type