The politeness Package: Detecting Politeness in Natural Language

Yeomans, Michael; Kantor, Alejandro; Tingley, Dustin

doi:10.32614/rj-2018-079

Cited by 39 publications

(33 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this we select the 4,000 most similar pairs for a total of 8,000 complaints. For our treatment (politeness), we use a state-ofthe-art politeness detection package geared towards social scientists (Yeomans et al, 2018). This package reports a score from a trained classifier using expert features of politeness and a hand-labeled dataset.…”

Section: Application: Complaints To the Financial Protection Bureaumentioning

confidence: 99%

Causal Effects of Linguistic Properties

Pryzant¹,

Card²,

Jurafsky³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster response time? How much will a positive product review increase sales? This paper addresses two technical challenges related to the problem before developing a practical method. First, we formalize the causal quantity of interest as the effect of a writer's intent, and establish the assumptions necessary to identify this from observational data. Second, in practice, we only have access to noisy proxies for the linguistic properties of interest-e.g., predictions from classifiers and lexicons. We propose an estimator for this setting and prove that its bias is bounded when we perform an adjustment for the text. Based on these results, we introduce TEXTCAUSE, an algorithm for estimating causal effects of linguistic properties. The method leverages (1) distant supervision to improve the quality of noisy proxies, and(2) a pre-trained language model (BERT) to adjust for the text. We show that the proposed method outperforms related approaches when estimating the effect of Amazon review sentiment on semi-simulated sales figures. Finally, we present an applied case study investigating the effects of complaint politeness on bureaucratic response times.

show abstract

Section: Application: Complaints To the Financial Protection Bureaumentioning

confidence: 99%

Causal Effects of Linguistic Properties

Pryzant¹,

Card²,

Jurafsky³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…Step 2: Natural Language Processing to extract politeness features (Yeomans et al, 2019) -Tweets identified and coded in Step 1.…”

Section: Opportunity Structuresmentioning

confidence: 99%

“…Step 2: Natural Language Processing to Measure Variations in Confrontational and Persuasive Stances Across Themes. To identify alternative uses of persuasive and confrontational stances by SG participants, we relied on the computational linguistics R package "Politeness" (Yeomans et al, 2019). This package provides tools to measure 36 linguistic features that have been previously identified as relating to display of politeness (Brown & Levinson, 1987;Danescu-Niculescu-Mizil et al, 2013).…”

Section: Framing Tasksmentioning

confidence: 99%

Beyond Clicktivism: What Makes Digitally Native Activism Effective? An Exploration of the Sleeping Giants Movement

Bernard

Luczak‐Roesch

2021

Social Media + Society

View full text Add to dashboard Cite

This article explores how successful digitally native activism generates social change. Digitally native movements are initiated, organized, and coordinated online without any physical presence or pre-existing offline campaign. To do so, we explore the revelatory case of Sleeping Giants (SG)—an online movement that led more than 4,000 organizations to withdraw their programmatic advertising spend from Breitbart, a far-right publisher. Analyzing 3.5 million tweets related to the movement along with qualitative secondary data, we used a mixed method approach to investigate the conditions that favored SG emergence, the organizing and coordinating practices of the movement, and the strategic framing practices involved in the tuning of the movement’s language and rhetoric toward its targets. Overall, we contribute to research on online movements and shed light on the pivotal role of peer production work and of language in leading an impactful online movement that aimed to counter online disinformation and hate speech.

show abstract

“…Individuals exposed to more polite partners may change their prior beliefs about the other side more than those exposed to less polite partners. We use the R package politeness to identify linguistic features of politeness with sentence parsing and dictionary methods (Yeomans et al, 2018). This package extends the work of Danescu-Niculescu-Mizil et al (2013) and Voigt et al (2017) by combing the indicators of politeness in both works.…”

Section: Preliminary Analysis Of Text Datamentioning

confidence: 99%

Sensitivity Analysis for Causal Mediation through Text: an Application to Political Polarization

Tierney¹,

Volfovsky²

2021

Proceedings of the First Workshop on Causal Inference and NLP

View full text Add to dashboard Cite

We introduce a procedure to examine a textas-mediator problem from a novel randomized experiment that studied the effect of conversations on political polarization. In this randomized experiment, Americans from the Democratic and Republican parties were either randomly paired with one-another to have an anonymous conversation about politics or alternatively not assigned to a conversationchange in political polarization over time was measured for all participants. This paper analyzes the text of the conversations to identify potential mediators of depolarization and is faced with a unique challenge, necessitated by the primary research hypothesis, that individuals in the control condition do not have conversations and so lack observed text data. We highlight the importance of using domain knowledge to perform dimension reduction on the text data, and describe a procedure to characterize indirect effects via text when the text is only observed in one arm of the experiment.

show abstract

The politeness Package: Detecting Politeness in Natural Language

Cited by 39 publications

References 10 publications

Causal Effects of Linguistic Properties

Causal Effects of Linguistic Properties

Beyond Clicktivism: What Makes Digitally Native Activism Effective? An Exploration of the Sleeping Giants Movement

Sensitivity Analysis for Causal Mediation through Text: an Application to Political Polarization

Contact Info

Product

Resources

About