quanteda: An R package for the quantitative analysis of textual data

Benoit, Kenneth; Watanabe, Kohei; Wang, Haiyan; Nulty, Paul; Obeng, Adam; Müller, Stefan; Matsuo, Akitaka

doi:10.21105/joss.00774

Cited by 933 publications

(653 citation statements)

References 11 publications

Supporting

Mentioning

624

Contrasting

Unclassified

Order By: Relevance

“…Shock includes words and phrases associated with the crisis itself (financial crisis, crisis lessons, sovereign debt, and subprime). Core includes those that capture the key elements of the original monetary policy paradigm 4 We use software by Benoit et al (2018) to remove stop words, numbers, and punctions; and to remove inflections from words in order to reduce them to their roots. We use software by Roberts et al (2018) to estimate a Correlated Topic Model (Blei and Lafferty 2007).…”

Section: Methodsmentioning

confidence: 99%

Adding rooms onto a house we love: Central banking after the global financial crisis

Johnson

Arel‐Bundock

Portniaguine

2018

Public Administration

View full text Add to dashboard Cite

This article examines the extent to which central bankers have been willing and able to rethink their beliefs about monetary policy in the wake of the global financial crisis. We show that despite the upheaval, the core pre‐crisis monetary policy paradigm remains relatively intact: central bankers believe that they should primarily pursue price stability through targeting a low inflation rate in a transparent manner, and that they need operational independence in order to achieve this goal. In a bid to address post‐crisis conditions and maintain their credibility, however, central bankers have also layered new elements onto this paradigmatic core. We document both the resilience of pre‐crisis beliefs and the process of layering using computer‐assisted text analysis and qualitative analysis of 13,586 speeches given between 1997 and 2017 by central bankers from around the world.

show abstract

Section: Methodsmentioning

confidence: 99%

Adding rooms onto a house we love: Central banking after the global financial crisis

Johnson

Arel‐Bundock

Portniaguine

2018

Public Administration

View full text Add to dashboard Cite

show abstract

“…The full list of removed tokens/features is available upon request. All preprocessing steps along with subsequent analyses were performed in R/R Studio with the quanteda package (Benoit et al, 2018).…”

Section: Appendix A: Methods Used For Data Collection and Analysismentioning

confidence: 99%

Manual or Machine? A Review of the Crisis and Disaster Literature

Kuipers¹,

Kantorowicz²,

Mostert³

2019

Risk Hazard & Crisis Pub Pol

View full text Add to dashboard Cite

This review aims to map the literature on crisis and disasters by means of a machine‐read assessment of the scholarly debate in these domains. The software analyzed abstracts of over 1,000 articles of four related crisis and disaster journals—to find out how the software categorizes their content in a set of topics, what the dominant topics of discussion are, how the topics are distributed over the journals, and what profiles the journals de facto have. The review reflects on the advantages and the limits of machine‐read classification and analysis vis‐à‐vis the manual approach. The conclusion offers an agenda for further research and debate.

show abstract

“… Note : Sources: General textual network analysis tools: http://www.eladsegev.com/tools, Count Words: http://www.countwordsfree.com, DMI: https://wiki.digitalmethods.net/Dmi/ToolDatabase, Mozdeh: http://mozdeh.wlv.ac.uk, (Thelwall, ) TAGS: https://tags.hawksey.info, Visone: https://visone.info, Gephi: https://gephi.org, NodeXL: https://nodexl.com, quanteda: https://quanteda.io/reference/textplot_network.html, (Benoit et al, ) textnets: https://github.com/cbail/textnets, Text‐Network Analysis: https://github.com/michal‐pikusa/text‐network‐analysis …”

Section: Guidelines For Conducting Textual Network Analysismentioning

confidence: 99%

Textual network analysis: Detecting prevailing themes and biases in international news and social media

Segev

2020

Sociology Compass

View full text Add to dashboard Cite

The growing volumes of information available today provide opportunities but also challenges for social scientists. This paper presents textual network analysis—a network analysis procedure that transforms any given text into a visual map of words co‐occurring together. It aims at scholars and students who are not familiar with network analysis, showing step‐by‐step how to use this approach and highlighting its advantages and applications. It demonstrates how to identify the main themes appearing in the text as well as to detect its biases and frames. Researchers can use this procedure as a grounded content analysis to formulate theories or as a basis to test existing hypotheses. The second part of the paper presents two studies that applied textual network analysis: (a) to identify the main themes raised by elite newspapers on the “fake news” discourse and (b) to map the topics related to China on Twitter. Both examples show how textual network analysis can be relevant for communication, international relations, and political science scholars as well as for practitioners, wishing to understand the prevailing discourses and tailor their messages more effectively.

show abstract

quanteda: An R package for the quantitative analysis of textual data

Cited by 933 publications

References 11 publications

Adding rooms onto a house we love: Central banking after the global financial crisis

Adding rooms onto a house we love: Central banking after the global financial crisis

Manual or Machine? A Review of the Crisis and Disaster Literature

Textual network analysis: Detecting prevailing themes and biases in international news and social media

Contact Info

Product

Resources

About