The Power of Words from the 2024 United States Presidential Debates: A Natural Language Processing Approach (original) (raw)
Related papers
Exploring the United States Presidential Debates via Text Mining
This study explores the changes and developments of the United States presidential debates based on TV debate transcripts since the initiation of the presidential debates in 1960 until 2016. Via modern text mining techniques, the general and diachronic developments in the speeches of political candidates as well as differences considering language and rhetoric of the representatives of the two major parties-Democrats and Republicans are investigated. The results of the study confirm that syntactic and semantic complexity of debate speeches is getting lower over the years: the syntactical structure becomes simpler, sentences shorter, the vocabulary is getting more repetitive and common. Moreover, a tendency to more plain syntax and shorter grammatical units is indicated, that contributes to a better comprehension by a larger audience. Based on LIWC word categories and sentiment analysis results, this study indicates that until 2016 positive sentiments in candidate speeches are gradually decreasing. The 2016 debates are defined as the most negatively tuned ones with Donald Trump's negativity scores higher than any other presidential candidate over the 12 years of TV debates. Zusammenfassung In dieser Masterarbeit werden die Veränderungen und Entwicklungen der US-Präsidentschaftsdebatten basierend auf TV-Debattentranskripten in den Jahren 1960 bis 2016 untersucht. Mit Hilfe moderner Text-Mining-Techniken werden die allgemeinen und diachronen Entwicklungen in den Reden politischer Kandidaten sowie Unterschiede in Sprache und Rhetorik zwischen Demokraten und Republikaner analysiert. Die Ergebnisse der Studie zeigen, dass sich die syntaktische und semantische Komplexität der Debattenreden im Laufe der Jahre verringerte: die syntaktische Struktur wurde einfacher, Sätze wurden kürzer, der Wortschatz wurde repetitiver. Darüber hinaus wird eine Tendenz zu einer einfacheren Syntax und kürzeren grammatikalischen Einheiten aufgezeigt, die zu einem besseren Verständnis für ein größeres Publikum beitragen könnte. Basierend auf LIWC-Wortkategorien und Ergebnissen der Sentiment-Analyse wurde festgestellt, dass bis 2016 die positiven Sentiments in den Reden der Kandidaten graduell abnehmen. George W. Bush and even more during the Trump's election in 2016 (Lim, 2008). Simpler language in speeches may signal an attempt to address a broader, less educated audience and to satisfy the demands of "sound bite" journalism (Hallin, 1992), but may also be a way to address the demands of the spoken genre, where high complexity increases the risk of ambiguity (Vrana and Schneider, 2017). Most of current researches applying diverse modern text mining methods and focused either on the debates of one specific election cycle (María and Palacios,
Brno studies in English
Using corpus linguistics analysis techniques, this study compares salient lexical and phraseological features of the political discourse of Barrack Obama and Donald Trump to reveal the presidents' individual linguistic styles and preferred discursive themes. For this purpose, the WordSmith Tools software is used to extract frequency wordlists, keyword lists and clusters from two corpora of political speeches, and select the most frequent units for further identification of their patterns of use and function. The findings show that the speakers convey their intent to the listeners relying on their own idiolects. Differences are found in thematic concerns and in the use of those items that figure high in both corpora, building the image of Obama as a serious, objective and organized speaker, and that of Trump, as emotion-driven, subjective and fraternizing.
Journal of Computational Social Science, 2023
As part of the “text-as-data” movement, Natural Language Processing (NLP) provides a computational way to examine political polarization. We conducted a methodological scoping review of studies published since 2010 (n = 154) to clarify how NLP research has conceptualized and measured political polarization, and to characterize the degree of integration of the two different research paradigms that meet in this research area. We identified biases toward US context (59%), Twitter data (43%) and machine learning approach (33%). Research covers different layers of the political public sphere (politicians, experts, media, or the lay public), however, very few studies involved more than one layer. Results indicate that only a few studies made use of domain knowledge and a high proportion of the studies were not interdisciplinary. Those studies that made efforts to interpret the results demonstrated that the characteristics of political texts depend not only on the political position of the...
A Comparative Corpus-Based Study on the Political Discourse of the U.S. Presidents: Obama and Trump
SEEU Review
The aim of this research is to analyze the political discourse and the language they used in public addresses provided by two former presidents of the United States, specifically, President Barak Obama and President Donald Trump. This research reflects on the material that has been collected for several months which aimed to contribute on the analysis of the corpus, distinctions and similarities, as well as their attitudes towards the public opinion. The objectives of this study are mainly empirical and theoretical. Considering the empirical objectives, this study seeks to explore, identify and categorize the most used words in a political speech according to the categories, form, function and meaning, whereas, the theoretical objectives of this study are to provide a description of the language that is used in major events from well-known politicians when aiming to capture people’s attention. Their rhetorical habits were examined, in every delivery of Mr. Obama’s political speech; ...
Multi-Dimensional Analysis of Political Language
Lecture Notes in Electrical Engineering, 2012
This paper presents a method for the valuation of discourses from different linguistic perspectives: lexical, syntactic and semantic. We describe a platform (Discourse Analysis Tool -DAT) which integrates a range of language processing tools with the intent to build complex characterisations of the political discourse. The idea behind this construction is that the vocabulary and the clause structure of the sentence betray the speaker's level of culture, while the semantic classes mentioned in a speech characterises the speaker's orientation. When the object of study is the political discourse, an investigation on these dimensions could put in evidence features influencing the electing public. The method is intended to help both political speakers to improve their discourse abilities, by comparing their speeches with those of personalities of the public life in the past, and the public at large by evidencing hidden aspects of the linguistic and intellectual abilities of their candidates.
Identification of Common Trends in Political Speech in Social Media using Sentiment Analysis
Euromed (International Conference on Digital Heritage), 2022
Social Media have been extensively used for commercial and politi-cal communication, besides their initial scope of providing an easy-to-use outlet to produce and consume user-generated content. Besides being a popular medi-um, Social Media have definitely changed the way we express ourselves or where we look for emerging news and commentary, especially during troubled times. In this paper, we examine a corpus assembled from the Twitter accounts of politicians in the United States and annotated with respect to their audience and the sentiment they convey with each post. Our purpose is to examine whether there are stylistic differences among representatives of different politi-cal ideologies, directed to different audiences or with dissimilar agendas. Our findings verify existing knowledge from conventional written communication and can be used to evaluate the quality and depth of political expression and di-alogue, especially during the period leading to an election.
The Linguistic Aspects on the 2019 Presidential Candidate Debate
2020
The presidential candidate debate was held five times by the General Election Commision (KPU) from January 17 to April 13, 2019. This is regulated in Law No. 7 of 2017, known as the Election Law. In the debate, there were discussion and exchange of opinions on a matter that must be defended. This study described the linguistic aspects used by the presidential candidates on the 2019 presidential candidate debate. This study employed a qualitative descriptive method with heuristic analysis. The data was collected by examining the notes taking technique. The results point out that during the 2019 presidential candidates’ debate, both presidential candidates use language style, satire, allusion, tautology, and rhetoric. The presidential candidates use a variety of official languages, sociolect, various literary languages, a variety of journalistic languages and a variety of familiar languages. They use dictions, such as foreign word choices, absorption, special, general, popular, and co...
Pakistan journal of humanities and social sciences, 2023
The present era is the era of digitalization which has profoundly impacted the different segments of the society. Hence, the present research was conducted to explore the linguistic shifts in the political discourse in the digital mass communication era. This study gathered data from reputable news sites, social media platforms, government archives, and academic libraries. Employing a stratified random sample technique ensured a diverse dataset, encompassing texts from varied political affiliations, historical periods, speeches, tweets, and articles. Rigorous preparation methods, such as data cleaning, standardization, and tokenization, were applied to enhance the study's consistency and reliability. The linguistic analysis investigated numerous linguistic elements, including vocabulary richness, sentence structure, sentiment, and the use of rhetorical techniques in political discourse. The findings highlight the diverse implications of linguistic shifts in the digital age, spanning emotional tone, information credibility, misinformation proliferation, and nuances of political polarization. As the digital age continues to shape political speech, the conclusions e the critical need for political communicators to strike a delicate balance between linguistic simplicity and discursive richness.
ArXiv, 2019
A key question in the analysis of collective social behaviour is related to know if and how mass media can influence public opinion. In this paper, we explore quantitatively the relation between a specific manifestation of public opinion and the intention to vote a given candidate, with the information related to the candidates in the Mass Media. We analyse the political news articles related to the US presidential campaign during the year 2016, using techniques of natural language processing. We applied recursive deep models for semantic composition over sentiment treebank to be able to detect the sentiment 1 ar X iv :1 90 9. 08 09 5v 1 [ cs .S I] 6 S ep 2 01 9 of sentences, and topic detection methods in order to characterise how media outlets get involved in the election coverage. The results of the analysis were compared to the outcomes of political polls in order to know which of these two aspects of the information have more influence and if there exists any causal relationshi...
Natural Language Processing in Political Campaigns
2017
This paper overviews the Majoritas ecosystem, providing a complete overview of political campaigns assessment aimed to assist politicians and their staff in delivering consistent and personalized message within social media.