TAUR.bib

%% This BibTeX bibliography file was created using BibDesk.
%% https://bibdesk.sourceforge.io/

%% Saved with string encoding Unicode (UTF-8) 


@article{pangetal2002,
	author = {Pang, B. and Lee, L. and Vaithyanathan, S.},
	date-added = {2022-11-04 15:45:35 +1100},
	date-modified = {2022-11-04 15:45:53 +1100},
	journal = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
	pages = {79-86},
	title = {Thumbs up? Sentiment classification using machine learning techniques},
	year = {2002}}

@article{Most63,
	author = {F. Mosteller and D. L. Wallace},
	date-added = {2022-11-04 15:27:17 +1100},
	date-modified = {2022-11-04 15:27:17 +1100},
	journal = {Journal of the American Statistical Assocation},
	number = {302},
	pages = {275--309},
	title = {Inference in an Authorship Problem},
	volume = {58},
	year = {1963}}

@article{monroe2008,
	author = {Monroe, B.L. and Quinn, K.M. and Colaresi, M.P.},
	date-added = {2022-11-04 15:22:21 +1100},
	date-modified = {2022-11-04 15:22:58 +1100},
	journal = {Political Analysis},
	number = {4},
	pages = {372--403},
	title = {Fightin' Words: {L}exical Feature Selection and Evaluation for Identifying the Content of Political Conflict},
	volume = {16},
	year = {2008}}

@manual{spacyr,
	author = {Kenneth Benoit and Akitaka Matsuo},
	date-added = {2022-08-24 17:18:06 +1000},
	date-modified = {2022-08-24 17:18:06 +1000},
	note = {R package version 1.2.1},
	title = {spacyr: Wrapper to the 'spaCy' 'NLP' Library},
	url = {https://CRAN.R-project.org/package=spacyr},
	year = {2020},
	bdsk-url-1 = {https://CRAN.R-project.org/package=spacyr}}

@article{spaCy,
	author = {Honnibal, Matthew and Montani, Ines and Van Landeghem, Sophie and Boyd, Adriane},
	date-added = {2022-08-24 16:27:38 +1000},
	date-modified = {2022-08-24 16:27:38 +1000},
	doi = {10.5281/zenodo.1212303},
	title = {{spaCy}: Industrial-strength Natural Language Processing in Python},
	year = {2020},
	bdsk-url-1 = {https://doi.org/10.5281/zenodo.1212303}}

@book{becue2019textual,
	author = {B{\'e}cue-Bertaut, Monica},
	date-added = {2022-08-24 16:18:37 +1000},
	date-modified = {2022-08-24 16:18:37 +1000},
	publisher = {CRC Press},
	title = {Textual data Science with {R}},
	year = {2019}}

@book{turenne2016analyse,
	author = {Turenne, Nicolas},
	date-added = {2022-08-24 16:16:50 +1000},
	date-modified = {2022-08-24 16:16:50 +1000},
	publisher = {ISTE Group},
	title = {Analyse de donn{\'e}es textuelles sous R},
	year = {2016}}

@book{kwartler2017text,
	author = {Kwartler, Ted},
	date-added = {2022-08-24 15:58:45 +1000},
	date-modified = {2022-08-24 15:58:45 +1000},
	publisher = {John Wiley \& Sons},
	address = {Chichester},
	title = {Text Mining in Practice with {R}},
	year = {2017}}

@article{tidytextJOSS,
	author = {Julia Silge and David Robinson},
	date-added = {2022-08-24 15:56:19 +1000},
	date-modified = {2022-08-24 15:56:19 +1000},
	doi = {10.21105/joss.00037},
	journal = {Journal of Open Source Software},
	number = {3},
	title = {tidytext: Text Mining and Analysis Using Tidy Data Principles in R},
	url = {http://dx.doi.org/10.21105/joss.00037},
	volume = {1},
	year = {2016},
	bdsk-url-1 = {http://dx.doi.org/10.21105/joss.00037}}

@book{silge2017text,
	author = {Silge, Julia and Robinson, David},
	date-added = {2022-08-24 15:49:42 +1000},
	date-modified = {2022-08-24 15:49:42 +1000},
	publisher = {O'Reilly Media, Inc.},
	title = {Text Mining with R: A Tidy Approach},
	year = {2017}}

@book{xie2015,
	address = {Boca Raton, Florida},
	author = {Yihui Xie},
	edition = {2nd},
	note = {ISBN 978-1498716963},
	publisher = {Chapman and Hall/CRC},
	title = {Dynamic Documents with {R} and knitr},
	url = {http://yihui.name/knitr/},
	year = {2015},
	bdsk-url-1 = {http://yihui.name/knitr/}}

@article{quantedaJOSS,
	author = {Kenneth Benoit and Kohei Watanabe and Haiyan Wang and Paul Nulty and Adam Obeng and Stefan M{\"u}ller and Akitaka Matsuo},
	doi = {10.21105/joss.00774},
	journal = {Journal of Open Source Software},
	number = {30},
	pages = {774},
	title = {quanteda: An {R} Package for the Quantitative Analysis of Textual Data},
	url = {https://quanteda.io},
	volume = {3},
	year = {2018},
	bdsk-url-1 = {https://quanteda.io},
	bdsk-url-2 = {https://doi.org/10.21105/joss.00774}}

@article{young2012,
	author = {Young, Lori and Soroka, Stuart N.},
	date-modified = {2019-10-13 20:17:38 +0200},
	journal = {Political Communication},
	number = {2},
	pages = {205-231},
	title = {Affective News: The Automated Coding of Sentiment in Political Texts},
	volume = {29},
	year = {2012}}

@incollection{benoit2020text,
	address = {Thousand Oaks},
	author = {Benoit, Kenneth},
	booktitle = {Handbook of Research Methods in Political Science and International Relations},
	date-added = {2020-09-30 08:13:11 +0100},
	date-modified = {2020-09-30 08:21:58 +0100},
	editor = {Curini, Luigi and Franzese, Robert},
	pages = {461-497},
	publisher = {Sage},
	rating = {5},
	subtitle = {An Overview},
	title = {Text as Data},
	year = {2020}}

@manual{rvest,
	author = {Hadley Wickham},
	note = {R package version 1.0.2},
	title = {rvest: Easily Harvest (Scrape) Web Pages},
	url = {https://CRAN.R-project.org/package=rvest},
	year = {2021},
	bdsk-url-1 = {https://CRAN.R-project.org/package=rvest}}

@article{JSSv025i05,
	abstract = {During the last decade text mining has become a widely used discipline utilizing statistical and machine learning methods. We present the <strong>tm</strong> package which provides a framework for text mining applications within R. We give a survey on text mining facilities in R and explain how typical application tasks can be carried out using our framework. We present techniques for count-based analysis methods, text clustering, text classification and string kernels.},
	author = {Feinerer, Ingo and Hornik, Kurt and Meyer, David},
	doi = {10.18637/jss.v025.i05},
	journal = {Journal of Statistical Software},
	number = {5},
	pages = {1--54},
	title = {Text Mining Infrastructure in {R}},
	url = {https://www.jstatsoft.org/index.php/jss/article/view/v025i05},
	volume = {25},
	year = {2008},
	bdsk-url-1 = {https://www.jstatsoft.org/index.php/jss/article/view/v025i05},
	bdsk-url-2 = {https://doi.org/10.18637/jss.v025.i05}}

@article{tmpackage,
	author = {Ingo Feinerer and Kurt Hornik and David Meyer},
	journal = {Journal of Statistical Software},
	month = {March},
	number = {5},
	pages = {1--54},
	title = {Text Mining Infrastructure in {R}},
	url = {https://www.jstatsoft.org/v25/i05/},
	volume = {25},
	year = {2008},
	bdsk-url-1 = {https://www.jstatsoft.org/v25/i05/}}

@article{benoit19sophistication,
	author = {Benoit, Kenneth and Munger, Kevin and Spirling, Arthur},
	doi = {10.1111/ajps.12423},
	journal = {American Journal of Political Science},
	keywords = {seconary, phd, readability},
	number = {2},
	pages = {491-508},
	title = {Measuring and Explaining Political Sophistication Through Textual Complexity},
	volume = {63},
	year = {2019},
	bdsk-url-1 = {https://doi.org/10.1111/ajps.12423}}

@article{boussalis21reactions,
	author = {Boussalis, Constantine and Coan, Travis G. and Holman, Mirya R. and M{\"u}ller, Stefan},
	doi = {10.1017/S0003055421000666},
	journal = {American Political Science Review},
	number = {4},
	pages = {1242-1257},
	title = {Gender, Candidate Emotional Expression, and Voter Reactions During Televised Debates},
	volume = {115},
	year = {2021},
	bdsk-url-1 = {https://doi.org/10.1017/S0003055421000666}}

@article{herzog15cuts,
	author = {Herzog, Alexander and Benoit, Kenneth},
	doi = {10.1086/682670},
	journal = {The Journal of Politics},
	number = {4},
	pages = {1157-1175},
	title = {The Most Unkindest Cuts: Speaker Selection and Expressed Goverment Dissent During Economic Crisis},
	volume = {77},
	year = {2015},
	bdsk-url-1 = {https://doi.org/10.1086/682670}}

@article{castanhosilva22eu,
	author = {Castanho Silva, Bruno and Proksch, Sven-Oliver},
	doi = {10.1017/psrm.2021.36},
	journal = {Political Science Research and Methods},
	keywords = {secondary, Twitter},
	number = {doi: 10.1017/psrm.2021.36},
	title = {Politicians Unleashed? Political Communication on Twitter and in Parliament in Western Europe},
	volume = {published ahead of print},
	year = {2021},
	bdsk-url-1 = {https://doi.org/10.1017/psrm.2021.36}}

@article{mueller22temporal,
	author = {M{\"u}ller, Stefan},
	doi = {10.1086/715165},
	journal = {The Journal of Politics},
	number = {1},
	pages = {585-590},
	title = {The Temporal Focus of Campaign Communication},
	volume = {84},
	year = {2022},
	bdsk-url-1 = {https://doi.org/10.1086/715165}}

@article{card22immig,
	author = {Card, Dallas and Change, Serina and Becker, Chris and Mendelsohn, Julia and Voigt, Rob and Boustan, Leah and Abramitzky, Ran and Jurafsky, Daniel},
	doi = {10.1073/pnas.2120510119},
	journal = {Proceedings of the National Academy of Sciences of the United States of America (PNAS)},
	number = {31},
	pages = {e2120510119},
	title = {Computational Analysis of 140 years of US Political Speeches Reveals More Positive but Increasingly Polarized Framing of Immigration},
	volume = {119},
	year = {2022},
	bdsk-url-1 = {https://doi.org/10.1073/pnas.2120510119}}

@book{grimmer22textasdata,
	address = {Princeton},
	author = {Grimmer, Justin and Roberts, Margaret E. and Stewart, Brandon M.},
	date-modified = {2022-08-24 15:49:02 +1000},
	publisher = {Princeton University Press},
	subtitle = {A New Framework for Machine Learning and the Social Sciences},
	title = {Text as Data: The promise and pitfalls of automatic content analysis methods for political texts},
	year = {2022}}

@book{wickham23r4ds,
	address = {Sebastopol},
	author = {Wickham, Hadley and Çetinkaya-Rundel, Mine and Grolemund, Garrett},
	publisher = {O'Reilly},
	subtitle = {Import, Tidy, Transform, Visualize, and Model Data},
	title = {R for Data Science},
	url = {https://r4ds.hadley.nz},
	edition = {2},
	year = {2023}}
	
	
  @Manual{stopwords,
    title = {stopwords: Multilingual Stopword Lists},
    author = {Kenneth Benoit and David Muhr and Kohei Watanabe},
    year = {2021},
    note = {R package version 2.3},
    url = {https://CRAN.R-project.org/package=stopwords},
  }
  
@article{denny18preprocess,
	author = {Denny, Matthew W. and Spirling, Arthur},
	doi = {10.1017/pan.2017.44},
	journal = {Political Analysis},
	number = {2},
	pages = {168-189},
	title = {Text Preprocessing For Unsupervised Learning: Why It Matters, When It Misleads, And What To Do About It},
	volume = {26},
	year = {2018}}
	
	

@article{monroe08intro,
	author = {Monroe, Burt L. and Schrodt, Philip A.},
	doi = {10.1093/pan/mpn017},
	journal = {Political Analysis},
	number = {4},
	pages = {351-355},
	subtitle = {The Statistical Analysis of Political Text},
	title = {Introduction to the Special Issue},
	volume = {16},
	year = {2008}}
	

@article{wilbur92stopwords,
	author = {Wilbur, W. John and Sirotkin, Karl},
	doi = {10.1177/01655515920180010},
	journal = {Journal of Information Science},
	number = {1},
	pages = {45-55},
	title = {The Automatic Identification of Stop Words},
	volume = {18},
	year = {1992}}
	
	
@article{sarica21stopwords,
	author = {Sarica, Serhad and Luo, Jianxi},
	doi = {10.1371/journal.pone.0254937},
	journal = {PLoS One},
	number = {8},
	pages = {e0254937},
	title = {Stopwords in Technical Language Processing},
	volume = {16},
	year = {2021}}


@inproceedings{porter01snowball,
  title={Snowball: A Language for Stemming Algorithms},
  author={Martin F. Porter},
  year={2001}
}


@article{tokenizers,
  title = {Fast, Consistent Tokenization of Natural Language Text},
  author = {Lincoln A. Mullen and Kenneth Benoit and Os Keyes and Dmitry Selivanov and Jeffrey Arnold},
  journal = {Journal of Open Source Software},
  year = {2018},
  volume = {3},
  issue = {23},
  pages = {655},
  doi = {10.21105/joss.00655}
}


@book{hvitfeldt21ml,
	address = {Boca Raton},
	author = {Hvitfeldt, Emil and Silge, Julia},
	publisher = {CRC Press},
	title = {Supervised Machine Learning For Text Analysis in R},
	url = {https://smltar.com},
	year = {2021}
}


@article{schofield16stem,
	author = {Schofield, Alexandra and Mimno, David},
	doi = {10.1162/tacl_a_00099},
	journal = {Transactions of the Association for Computational Linguistics},
	pages = {287-300},
	subtitle = {The Effects of Stemmers on Topic Models},
	title = {Comparing Apples to Apple},
	volume = {4},
	year = {2016}
}


@article{lupia20nsf,
	author = {Lupia, Arthur and Soroka, Stuart N. and Beatty, Alison},
	doi = {10.1126/sciadv.aaz6300},
	journal = {Science Advances},
	number = {33},
	pages = {eaaz6300},
	title = {What Does Congress Want from the National Science Foundation? A Content Analysis of Remarks from 1995 to 2018},
	volume = {6},
	year = {2020},
	bdsk-url-1 = {https://doi.org/10.1126/sciadv.aaz6300}}


@article{gessler22immig,
	author = {Gessler, Theresa and Hunger, Sophia},
	doi = {10.1017/psrm.2021.64},
	journal = {Political Science Research and Methods},
	number = {3},
	pages = {524 - 544},
	title = {How the Refugee Crisis and Radical Right Parties Shape Party Competition on Immigration},
	volume = {10},
	year = {2022}
}


@article{rauh20eu,
	author = {Rauh, Christopher and Bes, Bart Joachim and Schoonvelde, Martijn},
	doi = {10.1111/1475-6765.12350},
	journal = {European Journal of Political Research},
	number = {2},
	pages = {397-423},
	title = {Undermining, Defusing or Defending European Integration? Assessing Public Communication of European Executives in Times of EU Politicisation},
	volume = {59},
	year = {2020}}


@Manual{lda,
    title = {lda: Collapsed Gibbs Sampling Methods for Topic Models},
    author = {Jonathan Chang},
    year = {2015},
    note = {R package version 1.4.2},
    url = {https://CRAN.R-project.org/package=lda},
  }
  
  
@Article{stm,
    title = {{stm}: An {R} Package for Structural Topic Models},
    author = {Margaret E. Roberts and Brandon M. Stewart and Dustin Tingley},
    journal = {Journal of Statistical Software},
    year = {2019},
    volume = {91},
    number = {2},
    pages = {1--40},
    doi = {10.18637/jss.v091.i02},
  }
  

@Article{topicmodels,
    title = {{topicmodels}: An {R} Package for Fitting Topic Models},
    author = {Bettina Gr\"un and Kurt Hornik},
    journal = {Journal of Statistical Software},
    year = {2011},
    volume = {40},
    number = {13},
    pages = {1--30},
    doi = {10.18637/jss.v040.i13},
  }


@article{keyatm,
	author = {Eshima, Shusei and Imai, Kosuke and Sakasi, Tomoya},
	date-added = {2023-08-29 11:36:57 +0100},
	date-modified = {2023-08-29 11:38:25 +0100},
	doi = {10.1111/ajps.12779},
	journal = {American Journal of Political Science},
	keywords = {secondary, keyATM},
	title = {Keyword Assisted Topic Models},
	volume = {online first},
	year = {2023}}


@Manual{lsx,
    title = {LSX: Semi-Supervised Algorithm for Document Scaling},
    author = {Kohei Watanabe},
    year = {2023},
    note = {R package version 1.3.1},
    url = {https://CRAN.R-project.org/package=LSX},
  }
  
  @Manual{context,
    title = {conText: 'a la Carte' on Text (ConText) Embedding Regression},
    author = {Pedro L. Rodriguez and Arthur Spirling and Brandon Stewart},
    year = {2023},
    note = {R package version 1.4.3},
    url = {https://CRAN.R-project.org/package=conText},
  }



@book{manning08iir,
	address = {New York},
	author = {Manning, Christopher D. and Raghavan, Prabhakar and Sch{\"u}tze, Hinrich},
	date-added = {2017-08-09 10:24:52 +0000},
	date-modified = {2018-12-05 17:35:47 +0000},
	gender = {pm},
	keywords = {secondary, data mining, text analysis},
	publisher = {Cambridge University Press},
	title = {An Introduction to Information Retrieval},
	url = {https://nlp.stanford.edu/IR-book/},
	year = {2008}}


@article{slapin08wordfish,
	author = {Slapin, Jonathan B. and Proksch, Sven-Oliver},
	doi = {10.1111/j.1540-5907.2008.00338.x},
	journal = {American Journal of Political Science},
	number = {3},
	pages = {705-722},
	title = {A Scaling Model for Estimating Time-Series Party Positions from Texts},
	volume = {52},
	year = {2008}}
	
	

@article{crisp21voteseeking,
	author = {Crisp, Brian F. and Schneider, Benjamin and Catalinac, Amy and Muraoka, Taishi},
	doi = {10.1016/j.electstud.2021.102369},
	journal = {Electoral Studies},
	pages = {102369},
	title = {Capturing Vote-seeking Incentives and the Cultivation of a Personal and Party Vote},
	volume = {72},
	year = {2021}}