Saved in:
Bibliographic Details
Main Authors: Duan, Zening, Shao, Anqi, Hu, Yicheng, Lee, Heysung, Liao, Xining, Suh, Yoo Ji, Kim, Jisoo, Yang, Kai-Cheng, Chen, Kaiping, Yang, Sijia
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.05990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916773237882880
author Duan, Zening
Shao, Anqi
Hu, Yicheng
Lee, Heysung
Liao, Xining
Suh, Yoo Ji
Kim, Jisoo
Yang, Kai-Cheng
Chen, Kaiping
Yang, Sijia
author_facet Duan, Zening
Shao, Anqi
Hu, Yicheng
Lee, Heysung
Liao, Xining
Suh, Yoo Ji
Kim, Jisoo
Yang, Kai-Cheng
Chen, Kaiping
Yang, Sijia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05990
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals
Duan, Zening
Shao, Anqi
Hu, Yicheng
Lee, Heysung
Liao, Xining
Suh, Yoo Ji
Kim, Jisoo
Yang, Kai-Cheng
Chen, Kaiping
Yang, Sijia
Computation and Language
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.
title Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals
topic Computation and Language
url https://arxiv.org/abs/2312.05990