Text clustering: An application with the <i>State of the Union</i> addresses

Savoy, Jacques

doi:10.1002/asi.23283

Cited by 30 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current study, the target application pursues a larger scale than a few authors in describing the lexical specificities associated with each U.S. president. Moreover, a recent study shows that when applying a clustering algorithm on this corpus, all speeches appearing under the same presidency tend to regroup themselves under the same cluster (Savoy, 2015).…”

Section: Term Specificity Measurementioning

confidence: 93%

“…From a lexical point of view, the presidencies of Eisenhower, Kennedy, or Ford present only a few overused terms reused by the following presidents. When analyzing the style of the U.S. presidents (Savoy, 2015), we can see that these three presidents are strongly related to only one other president and relatively distant from the others. In other words, and from a lexical point of view, they are isolated.…”

Section: Lexical Leadersmentioning

confidence: 98%

See 1 more Smart Citation

Text representation strategies: An example with the State of the union addresses

Savoy

2015

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

This paper describes a clustering and authorship attribution study over the State of the Union addresses from 1790 to 2014 (224 speeches delivered by 41 presidents).To define the style of each presidency, we have applied a principal component analysis (PCA) based on the partof-speech (POS) frequencies. From Roosevelt (1934), each president tends to own a distinctive style whereas previous presidents tend usually to share some stylistic aspects with others. Applying an automatic classification based on the frequencies of all content-bearing word-types we show that chronology tends to play a central role in forming clusters, a factor that is more important than political affiliation. Using the 300 most frequent word-types, we generate another clustering representation based on the style of each president. This second view shares similarities with the first one, but usually with more numerous and smaller clusters. Finally, an authorship attribution approach for each speech can reach a success rate of around 95.7% under some constraints. When an incorrect assignment is detected, the proposed author often belongs to the same party and has lived during roughly the same time period as the presumed author. A deeper analysis of some incorrect assignments reveals interesting reasons justifying difficult attributions.

show abstract

Section: Term Specificity Measurementioning

confidence: 93%

Section: Lexical Leadersmentioning

confidence: 98%

Text representation strategies: An example with the State of the union addresses

Savoy

2015

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…Following Lei and Wen (2020), the present study employed the State of the Union Addresses delivered by 43 presidents of the United States of America as the dataset. The dataset was used for its features such as availability, long timespan, and comparability in genre (Savoy, 2015). First, all the texts of the addresses are freely available from the American Presidency Project homepage (http://presidency.proxied.lsit.ucsb.…”

Section: Methodsmentioning

confidence: 99%

Dependency distance minimization: a diachronic exploration of the effects of sentence length and dependency types

Liu

Zhu

Lei

2022

Humanit Soc Sci Commun

View full text Add to dashboard Cite

Dependency distance is regarded as an index of memory load and a measure of syntactic difficulty. Previous research has found that dependency distance tends to minimize both synchronically and diachronically due to the limited resource of working memory. However, little is known concerning the effects of different dependency types on the dependency distance minimization. In addition, previous studies showed inconsistent results on the anti-minimization of dependency distance in shorter sentences. Hence, a more fine-grained investigation is needed on the diachronic change of dependency distance with shorter sentences such as those of three or four words. To address these issues, this study intends to explore the diachronic change of dependency distance in terms of two variables, i.e., dependency types and sentence length. Results show that anti-minimization does exist in short sentences diachronically, and sentence length has an effect on diachronic dependency distance minimization of dependency types. More importantly, not all dependency types present a decreasing trend, while only nine types of dependency relations are responsible for the dependency distance minimization. Possible explanations for the findings are offered.

show abstract

“…The methodological approach employed in this study is textual analysis. Textual analysis has often been used to qualitatively analyse communication data (Osei Fordjour, 2022;Savoy, 2015;Sikanku, 2020;Smith, 2017;Sowińska, 2013). Textual analysis is a methodology that helps researchers gather data and make sense of written or spoken language (Chung & Park, 2010;McKee, 2003).…”

Section: Methodology: Textual Analysismentioning

confidence: 99%

Presidential discourse, the public and recurring themes: A political communication analysis of the 2019 State of the Nation Address in Ghana

Sikanku

2022

Communication and the Public

View full text Add to dashboard Cite

The State of the Nation Address is one of the most important public speeches of a president because it sets the tone, framework and plans of the administration in any given year. This research contributes to contemporary scholarly studies by systematically studying presidential discourse within a growing African democracy – from a communication perspective – rather than the routine generic policy analysis. Since communication is a vital aspect of governance, the present study helps to unearth the policy priorities and framework that characterized a major administration under Ghana’s democracy. From a broader perspective, the textual analysis of this speech offers a modest attempt to examine some elements of political communication within Africa’s democratization process. The major objectives of the study were twofold: (a) first, to analyse the major topics or subject areas embedded in the speech and (b) to ascertain the recurring essential thematic elements of the State of the Nation Address as postulated by Shogan. The results indicate that the social agenda (including sanitation, housing and social amenities) was the central focus of the President’s address, followed by politics, while economic affairs featured as the third predominant issue in the address. Three thematic elements – bipartisanship, past and future, and optimism – are discursively analysed. This study contributes to the study of political communication and Presidential agendas in one of Africa’s fledgling democracies.

show abstract

Text clustering: An application with the State of the Union addresses

Cited by 30 publications

References 20 publications

Text representation strategies: An example with the State of the union addresses

Text representation strategies: An example with the State of the union addresses

Dependency distance minimization: a diachronic exploration of the effects of sentence length and dependency types

Presidential discourse, the public and recurring themes: A political communication analysis of the 2019 State of the Nation Address in Ghana

Contact Info

Product

Resources

About