A BERT's Eye View: A Big Data Framework for Assessing Language Convergence and Accommodation

Abstract

The current paper details a novel quantitative framework leveraging recent advances in AI and Natural Language Processing to quantitatively assess language convergence and accommodation. This new framework is computationally cheap and straightforward to implement. The framework is then applied to a case study of immigration rhetoric in the lead up to the 2016 general election in the USA. Major results from the case study show that (1) Democrats and Republicans exhibited significant language convergence with members of their own parties, (2) President Barack Obama and Hillary Clinton converged with Senate Democrats’ immigration rhetoric, (3) Democrats accommodated the immigration rhetoric of both President Barack Obama and (candidate) Hillary Clinton, (4) contrary to initial hypotheses, Donald Trump's vitriolic immigration rhetoric did not show signs of language convergence with Republicans in the Senate, and (5) equally surprising, Senate Republicans showed significant non-accommodation to Donald Trump despite potential political costs for having done so.

Keywords

convergence accommodation social media computational modeling big data intergroup communication immigration rhetoric.

Get full access to this article

View all access options for this article.

References

Abell

(2002). Mad cows and British politicians: The role of scientific and national identities in managing blame for the BSE crisis. Text & Talk, 22(2), 173–198. https://doi.org/10.1515/text.2002.007

Adams

Miles

Dunbar

N. E.

Giles

(2018). Communication accommodation in text messages: Exploring liking, power, and sex as predictors of textisms. The Journal of Social Psychology, 158(4), 474–490. https://doi.org/10.1080/00224545.2017.1421895

Aragones

Neeman

(2000). Strategic ambiguity in electoral competition. Journal of Theoretical Politics, 12(2), 183–204. https://doi.org/10.1177/0951692800012002003

Aurnhammer

Frank

S. L.

(2019). Evaluating information-theoretic measures of word prediction in naturalistic sentence reading. Neuropsychologia, 134(107198). https://doi.org/10.1016/j.neuropsychologia.2019.107198

Zhao

W. G. W.

(2021). Symbolic convergence or divergence? Making sense of (the rhetorical) senses of a university-wide organizational change. Frontiers in Psychology, 12(690757). https://doi.org/10.3389/fpsyg.2021.690757

Baldassarri

Gelman

(2008). Partisans without constraint: Political polarization and trends in American public opinion. American Journal of Sociology, 114(2), 408–446. https://doi.org/10.1086/590649

Barbera

Jost

J. T.

Nagler

Tucker

J. A.

Bonneau

. (2015). Tweeting from left to right: Is online political communication more than an echo chamber? Psychological Science, 26(10), 1531–1542. https://doi.org/10.1177/0956797615594620.

Bash

. (2016). Lindsey Graham won’t vote for Trump or Clinton in 2016. Retrieved from: https://www.cnn.com/2016/05/06/politics/lindsey-graham-donald-trump-hillary-clinton-not-vote/index.html.

Boyd

R. L.

Schwartz

H. A.

(2021). Natural language analysis and the psychology of verbal behavior: the past, present, and future states of the field. Journal of Language & Social Psychology, 40(1), 21–40. https://doi.org/10.1177/0261927X20967028

10.

Bradac

J. J.

Mulac

House

(1988). Lexical diversity and magnitude of convergent versus divergent style shifting: Perceptual and evaluative consequences. Language & Communication, 8(3), 213–228. https://doi.org/10.1016/0271-5309(88)90019-5

11.

Broderick

M. P.

Anderson

A. J.

Di Liberto

G. M.

Crosse

M. J.

Lalor

E. C.

(2018). Electrophysiological correlates of semantic dissimilarity reflect the comprehension of natural, narrative speech. Current Biology, 28(5), 803–809. https://doi.org/10.1016/j.cub.2018.01.080

12.

Campbell

J. E.

(1985). Explaining presidential losses in midterm congressional elections. The Journal of Politics, 47(4), 1140–1157. https://doi.org/10.2307/2130810

13.

Center

P. R

. (2016). Top voting issues in 2016 election. Retrieved from: https://www.pewresearch.org/politics/2016/07/07/4-topvoting-issues-in-2016-election/.

14.

Cirugeda

I. L.

Ruiz

R. S.

(2013). Persuasive rhetoric in Barack Obama’s immigration speech: Pre- and post-electoral strategies. Camino Real, 5(8), 81–99. https://ebuah.uah.es/xmlui/bitstream/handle/10017/19993/persuasive_Cirugeda_CR_2013_N8.pdf?sequence = 1&isAllowed = y

15.

Conway

L. G.

Zubrod

(2022). Are U.S. Presidents becoming less rhetorically complex? Evaluating the integrative complexity of Joe Biden and Donald Trump in historical context. Journal of Language and Social Psychology. Advance online: https://doi.org/10.1177/0261927X221081126.

16.

Democratic Party Platform. (2016). Retrieved from: https://democrats.org/wp-content/uploads/2018/10/2016_DNC_Platform.pdf.

17.

Devlin

Chang

M.-W.

Lee

Toutanova

. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Retrieved from: arXiv:1810.04805 [cs]. http://arxiv.org/abs/1810.04805.

18.

de Vries

van Cranenburgh

Nissim

(2020). What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models. Findings of the Association for Computational Linguistics: EMNLP, 2020, 4339–4350. https://doi.org/10.18653/v1/2020.findings-emnlp.389

19.

Dougherty

D. S.

Mobley

S. K.

Smith

S. E.

(2010). Language convergence and meaning divergence: A theory of intercultural communication. Journal of International and Intercultural Communication, 3(2), 164–186. https://doi.org/10.1080/17513051003611628

20.

Dragojevic

Giles

(2014). Language and interpersonal communication: their intergroup dynamics. In Berger

C. R.

(Ed.), Handbook of interpersonal communication (pp. 29–51). De Gruyter Mouton. https://doi.org/10.1515/9783110276794.29.

21.

Dumais

Furnas

Landauer

Deerwester

Harshman

(1996). Using latent semantic analysis to improve access to textual information. CHI Proceedings, 88, https://doi.org/10.1145/57167.57214

22.

Eisenberg

E. M.

(1984). Ambiguity as strategy in organizational communication. Communication Monographs, 51(3), 227–242. https://doi.org/10.1080/03637758409390197

23.

Enli

G. S.

Skogerbø

(2013). Personalized campaigns in party-centered politics. Information, Communication & Society, 16(5), 757–774. https://doi.org/10.1080/1369118X.2013.782330

24.

Fangen

Vaage

(2018). “The immigration problem” and Norwegian right-wing politicians. New Political Science, 40(3), 459–476. https://doi.org/10.1080/07393148.2018.1487145

25.

Gallois

Gasiorek

Giles

Soliz

(2016). Communication accommodation theory: Integrations and new framework developments. In Giles

(Ed.), Communication accommodation theory: negotiating personal relationships and social identities across contexts (pp. 192–210). Cambridge University Press.

26.

Gallois

Ogay

Giles

(2005). Communication accommodation theory: A look back and a look ahead. In Gudykunst

W. B.

(Ed.), Theorizing about intercultural communication (pp. 121–148). Sage.

27.

Giger

Lefkofridi

(2014). Salience-based congruence between parties & their voters: The Swiss case. Swiss Political Science Review, 20(2), 287–304. https://doi.org/10.1111/spsr.12069

28.

Giles

Soliz

(2015). Communication accommodation theory a situated framework for relational, family, and intergroup dynamics. In Braithwaite

D. O.

Schrodt

(Eds.), Engaging theories in interpersonal communication: multiple perspectives (2^nd. ed., pp. 234–252). Sage.

29.

Graesser

Cho

Kiela

. (2020). Emergent linguistic phenomena in multi-agent communication games. Retrieved from: arXiv:1901.08706 [cs]. http://arxiv.org/abs/1901.08706.

30.

Hammer

Kafura

(2019). Republicans and democrats in different worlds on immigration (tech. Rep.). Chicago Council on Global Affairs. Retrieved from: https://www.jstor.org/stable/resrep21289.

31.

Hayward

(2011). Convergence/divergence: Party political discourse in northern Ireland’s transition from conflict. Dynamics of Asymmetric Conflict, 4(3), 196–213. https://doi.org/10.1080/17467586.2011.632779

32.

Hooghe

Dassonneville

(2018). Explaining the trump vote: The effect of racist resentment and anti-immigrant sentiments. PS: Political Science & Politics, 51(3), 528–534. https://doi.org/10.1017/S1049096518000367

33.

Johnson

(2018). Trump, the democrats, and the politics of immigration. Political Insight, 9(3), 15–19. https://doi.org/10.1177/2041905818796572

34.

Jones

J. M

. (2015). One in five voters say immigration stance critical to vote (quantitative analysis). Retrieved from: https://news.gallup.com/poll/185381/onefive-voters-say-immigration-stance-critical-vote.aspx.

35.

Keblusek

Giles

Maass

(2017). Communication and group life: How language and symbols shape intergroup relations. Group Processes & Intergroup Relations, 20(5), 632–643. https://doi.org/10.1177/1368430217708864

36.

Levy

(2008). Expectation-based syntactic comprehension. Cognition, 106(3), 1126–1177. https://doi.org/10.1016/j.cognition.2007.05.006

37.

Martinez-Mira

(2014). The immigration debate in the 2012 US presidential election and the role of rhetoric. Anglistik, 25(2), 107–124. https://angl.winter-verlag.de/article/ANGL/2014/2/7

38.

Nganga

S. W.

(2020). Winning through (dis)alignment: The language of the Kenyan female politicians. In Kioko

Kagumire

Matandela

(Eds.), Challenging patriarchy: the role of patriarchy in the roll-back of democracy (pp. 150–162). Heinrich-Boll-Stiftung.

39.

Pennington

Socher

Manning

(2014). Glove: global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532–1543. https://doi.org/10.3115/v1/D14-1162

40.

Quinonez

E. S.

(2018). (Un)welcome to America: A critical discourse analysis of anti-immigrant rhetoric in trump’s speeches and conservative mainstream media (master’s thesis). California State University. https://scholarworks.lib.csusb.edu/etd/635/.

41.

Republican Party Platform. (2016). Retrieved from: https://prod-cdn-static.gop.com/media/documents/DRAFT_12_FINAL%5B1%5D-ben_1468872234.pdf.

42.

Roeder

. (2017). The worst tweeter in politics isn’t Trump. Retrieved from: https://fivethirtyeight. com/features/the-worst-tweeter-in-politics-isnt-trump/.

43.

Sanchez

G. R.

Gomez-Aguinaga

(2017). Latino rejection of the trump campaign: How trump’s racialized rhetoric mobilized the latino electorate as never before. Aztlán: A Journal of Chicano Studies, 42(2), 165–181. http://mattbarreto.com/mbarreto/courses/sanchez_gomez_aztlan.pdf.

44.

Siddiqui

(2016). Rubio: trump is an “embarrassment” and republicans will pay big in November. The Guardian. Retrieved from: https://www.theguardian.com/us-news/2016/mar/15/marco-rubiotrump-already-embarrassment-for-republican-party.

45.

Sides

Tesler

Vavreck

(2018). Hunting where the ducks are: activating support for donald trump in the 2016 republican primary. Journal of Elections, Public Opinion and Parties, 28(2), 135–156. https://doi.org/10.1080/17457289.2018.1441849

46.

Sloan

Morgan

Housley

Edwards

(2013). Knowing the tweeters: Deriving socially relevant demographics from twitter. Sociological Research Online, 18, 3. https://orca.cardiff.ac.uk/49152/1/SocResOnline%20Knowing%20the%20Tweeters.pdf. https://doi.org/10.5153/sro.3001

47.

Smaldino

P. E.

Flamson

T. J.

McElreath

(2018). The evolution of covert signaling. Scientific Reports, 8, 4905. https://doi.org/10.1038/s41598-018-22926-1

48.

Song

Wang

Liang

Liu

Jiang

(2020). Utilizing BERT intermediate layers for aspect based sentiment analysis and natural language inference. Retrieved from: arXiv:2002.04815 [cs]. http://arxiv.org/abs/2002.04815.

49.

Trueswell

Tanenhaus

(1994). Semantic influences on parsing: Use of thematic role information in syntactic ambiguity resolution. Journal of Memory and Language, 33(3), 285–318. https://doi.org/10.1006/jmla.1994.1014

50.

van Aken

Winter

Loser

Gers

F. A.

(2019). How does BERT answer questions? A layer-wise analysis of transformer representations. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 1823–1832. https://doi.org/10.1145/3357384.3358028

51.

Van Swol

L. M.

Kane

A. A.

(2019). Language and group processes: An integrative, interdisciplinary review. Small Group Research, 50(1), 3–38. https://doi.org/10.1177/1046496418785019

52.

Walgrave

Lefevere

(2013). Ideology, salience, and complexity: Determinants of policy issue incongruence between voters and parties. Journal of Elections, Public Opinion and Parties, 23(4), 456–483. https://doi.org/10.1080/17457289.2013.810630

53.

Winders

(2016). Immigration and the 2016 election. Southeastern Geographer, 56(3), 291–296. https://www.jstor.org/stable/26233803. https://doi.org/10.1353/sgo.2016.0034

54.

Wolf

Debut

Sanh

Chaumond

Delangue

Moi

Cistac

Rault

Louf

Funtowicz

Davison

Shleifer

von Platen

Jernite

Plu

Scao

T. L.

Gugger

, … Rush

A. M

. (2020). HuggingFace’s transformers: state-of-the-art natural language processing. Retrieved from: ArXiv:1910.03771 [cs]. http://arxiv.org/abs/1910.03771.