A computational approach toward understanding the political language of ideologically opposing groups - from historical newspapers to social media

Park, Jaihyun

Permalink

https://hdl.handle.net/2142/125699 Copy

Description

Title

A computational approach toward understanding the political language of ideologically opposing groups - from historical newspapers to social media

Author(s)

Park, Jaihyun

Issue Date

2024-07-10

Director of Research (if dissertation) or Advisor (if thesis)

Cordell, Ryan

Doctoral Committee Chair(s)

Cordell, Ryan

Committee Member(s)

• Underwood, Ted
• Yang, JungHwan
• Seo, JooYoung

Department of Study

Information Sciences

Discipline

Information Sciences

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Digital Humanities
• Computational Social Science

Abstract

Living in a democratic society grants us the freedom to hold and express our beliefs and thoughts, protected under the commonly referred to principle of ``freedom of conscience.'' As such, individuals act and speak in accordance with their belief systems and values, engaging in conversations to share perspectives, spread information aligned with their beliefs, or even persuade others to support causes they deem just. However, this freedom contributed to creating a polarized society where people find it difficult to unanimously agree with one another. Digital archives with a collection of text from historical newspapers to social media provide an opportunity to study how people of opposing viewpoints engaged in political battles and how they generated discourse around the topic they support. Taking this advantage, the thesis applies a computational approach to examine the political language of ideologically opposing groups using historical newspapers in Chronicling America and contemporary social media such as Twitter and Parler. For the historical context, the first two sections cover issue of slavery and racism in the 19th and 20th centuries. (1) The first section examines the discourse around slaves and servants during the period covering the Civil War and studies how newspapers from the South and North used different words to create distinct discourse communities. Methodologically, embedding-based text mining technologies and the method of incorporating possible OCR errors are used. In addition, the log-odds-ratio with informative Dirichlet prior is used to examine how prevalent the discourse words are in the newspapers from the South and North. This section concludes that the slave discourse accompanied socio-economic, legal, and administrative words regardless of the stance toward slavery while the servant discourse showed distinctive words in the Southern and Northern newspapers. The servant discourse words accompanied in the Southern newspapers included words related to the domestic work, which could potentially evoke a sense of nostalgia, while the Northern newspapers included words about religion. Further, this project found that the slave discourse words associated with Southern newspapers prevailed in the Northern newspapers due to socio-economic words that were shared between the two regions while servant discourse words were confined to the Southern and Northern newspapers (2) The second section focuses on the derogatory word referring to Asian workers and examines how this word is used. Asian immigrant workers were derogatorily referred to as ``coolies.'' Methodologically, embedding-based text mining technologies, the log-odds-ratio with informative Dirichlet prior, and network analysis to examine the most circulated story are used. This project finds that the derogatory word referring to Asian workers had a unique semantic space in the newspapers published in each State. Especially, the derogatory word referring to Asian workers was used in the context of African Americans in slave States, which could be explained by the historical context of abolition and its impact on the changes in the labor market. Lastly, this section addresses the most circulated story in the newspapers which frames the Asian workers as an inferior race compared to the White immigrants. For the contemporary context, (3) the third section introduces varied uses of toxic language on different social media platforms during the period of the 2020 U.S. Presidential election. A state-of-the-art method for determining the degree of toxicity in the text, a statistical approach to distinguish over-represented words in each platform, and network analysis are used. This section finds that the cross-platform users, who used both Twitter and Parler, showed varying degrees of homophily depending on the degree centrality. In addition, the cross-platform users showed a higher degree of toxicity in their language when they are engaged in out-group communication on Twitter. This finding supplements the existing literature on in-group and out-group communication that in-group communication takes place in peace while out-group communication exhibits hostility and argues that cross-platform users used different words on Twitter and Parler, creating a distinct discourse community in each platform. By leveraging digital archives and applying computational text analysis, this thesis aims to bridge the gap between the research on historical and contemporary political language thus far divided into two separate fields, Digital Humanities and Computational Social Science.

Graduation Semester

2024-08

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/125699

Copyright and License Information

Copyright 2024 Jaihyun Park

Owning Collections