AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频

生成解读视频

AI 溯源

AI解析本论文相关学术脉络

生成溯源树

AI 精读

AI抽取本论文的概要总结

微博一下：

Politeness markers are intimately related to the power dynamics of social interactions and are often a decisive factor in whether those interactions go well or poorly

A Computational Approach to Politeness with Application to Social Factors.

meeting of the association for computational linguistics, (2013): 250-259

引用：377|浏览158

下载 PDF 全文

其它链接

dblp.uni-trier.de academic.microsoft.com arxiv.org

引用

微博一下

关键词

wikipediaAWATIFsocial factorAmazon Mechanical Turkcomputational framework更多(13+)

摘要

We propose a computational framework for identifying linguistic aspects of politeness. Our starting point is a new corpus of requests annotated for politeness, which we use to evaluate aspects of politeness theory and to uncover new interactions between politeness markers and context. These findings guide our construction of a classifie...更多

代码：

数据：

精读

下载 PDF 全文

PPT (上传PPT)

相似论文

引用论文

被引论文

简介

Politeness is a central force in communication, arguably as basic as the pressure to be truthful, informative, relevant, and clear (Grice, 1975; Leech, 1983; Brown and Levinson, 1978).
The authors focus on requests because they involve the speaker imposing on the addressee, making them ideal for exploring the social value of politeness strategies (Clark and Schunk, 1980; Francik and Clark, 1985).
Requests stimulate extensive use of what Brown and Levinson (1987) call negative politeness: speaker strategies for minimizing the imposition on the addressee, for example, by being indirect (Would you mind) or apologizing for the imposition (the author terribly is sorry, but) (Lakoff, 1973; Lakoff, 1977; Brown and Levinson, 1978)

重点内容

Politeness is a central force in communication, arguably as basic as the pressure to be truthful, informative, relevant, and clear (Grice, 1975; Leech, 1983; Brown and Levinson, 1978)
Politeness markers are intimately related to the power dynamics of social interactions and are often a decisive factor in whether those interactions go well or poorly (Gyasi Obeng, 1997; Chilton, 1990; Andersson and Pearson, 1999; Rogers and LeeWong, 2003; Holmes and Stubbe, 2005)
The present paper develops a computational framework for identifying and characterizing politeness marking in requests
We show that polite Wikipedia editors are more likely to achieve high status through elections; once elected, they become less polite
We characterized politeness markings as currency used to pay respect. Such language is costly in a social sense, and, relatedly, tends to incur costs in terms of communicative efficiency (Van Rooy, 2003). Are these costs worth paying? We address this question by studying politeness in the context of the electoral system of the Wikipedia community of editors

结果

As shown in Figure 2, the labels are coherent and significantly different from the randomized procedure (p < 0.0001 according to a Wilcoxon signed rank test).5.

结论

The authors construct and release a large collection of politeness-annotated requests and use it to evaluate key aspects of politeness theory.
The authors build a politeness classifier that achieves near-human performance and use it to explore the relation between politeness and social factors such as power, status, gender, and community membership.
The authors hope the publicly available collection of annotated requests enables further study of politeness and its relation to social factors, as this paper has only begun to explore this area

表格

Table1: Summary of the request data and its politeness annotations
Table2: The percentage of requests for which all five annotators agree on binary politeness. The 4th quartile contains the requests with the top 25% politeness scores in the data. (For reference, randomized scoring yields agreement percentages of <20% for all quartiles.)
Table3: Positive (1-5) and negative (6–20) politeness strategies and their relation to human perception of politeness. For each strategy we show the average (human annotated) politeness scores for the requests exhibiting that strategy (compare with 0 for a random sample of requests; a positive number indicates the strategy is perceived as being polite), as well as the percentage of requests exhibiting the respective strategy that fall in the top quartile of politeness scores (compare with 25% for a random sample of requests). Throughout the paper: for politeness scores, statistical significance is calculated by comparing the set of requests exhibiting the strategy with the rest using a Mann-Whitney-Wilcoxon U test; for top quartile membership a binomial test is used
Table4: Accuracies of our two classifiers for Wikipedia (Wiki) and Stack Exchange (SE), for in-domain and cross-domain settings. Human performance is included as a reference point. The random baseline performance is 50%
Table5: Politeness and status. Editors who will eventually become admins are more polite than non-admins (p<0.001 according to a MannWhitney-Wilcoxon U test) and than editors who will eventually fail to become admins (p<0.001). Out of their requests, 30% are rated in the top politeness quartile (significantly more than the 25% of a random sample; p<0.001 according to a binomial test). This analysis was conducted on 31k requests (1.4k for Admins, 28.9k for Non-admins, 652 for Failed)
Table6: Politeness and dependence. Requests made in comments posted by the question-asker are significantly more polite than the other requests. Analysis conducted on 181k requests (106k for question-askers, 75k for answer-givers)
Table7: Politeness and Stack Exchange reputation (texts by question-askers only). High-reputation users are less polite. Analysis conducted on 25k requests (4.5k low, 12.5k middle, 8.4k high)
Table8: Politeness of requests from different language communities on Stack Exchange

Download tables as Excel

相关工作

Politeness has been a central concern of modern pragmatic theory since its inception (Grice, 1975; Lakoff, 1973; Lakoff, 1977; Leech, 1983; Brown and Levinson, 1978), because it is a source of pragmatic enrichment, social meaning, and cultural variation (Harada, 1976; Matsumoto, 1988; 12However, due to the limited size of the human-labeled data, we could not control for the role of the user in the Stack Exchange reputation experiment.

Ide, 1989; Blum-Kulka and Kasper, 1990; BlumKulka, 2003; Watts, 2003; Byon, 2006). The starting point for most research is the theory of Brown and Levinson (1987). Aspects of this theory have been explored from game-theoretic perspectives (Van Rooy, 2003) and implemented in language generation systems for interactive narratives (Walker et al, 1997), cooking instructions, (Gupta et al, 2007), translation (Faruqui and Pado, 2012), spoken dialog (Wang et al, 2012), and subjectivity analysis (Abdul-Mageed and Diab, 2012), among others.

In recent years, politeness has been studied in online settings. Researchers have identified variation in politeness marking across different contexts and media types (Herring, 1994; Brennan and Ohaeri, 1999; Duthler, 2006) and between different social groups (Burke and Kraut, 2008a). The present paper pursues similar goals using orders of magnitude more data, which facilitates a fuller survey of different politeness strategies.

基金

This work was supported in part by NSF IIS-1016909, CNS-1010921, IIS-1149837, IIS-1159679, ARO MURI, DARPA SMISC, Okawa Foundation, Docomo, Boeing, Allyes, Volkswagen, Intel, Alfred P

研究对象与分析

documents: 13

A summary of all our request data is shown in Table 1. Inter-annotator agreement To evaluate the reliability of the annotations we measure the interannotator agreement by computing, for each batch of 13 documents that were annotated by the same set of 5 users, the mean pairwise correlation of the respective scores. For reference, we compute the same quantities after randomizing the scores by sampling from the observed distribution of politeness scores

引用论文

Muhammad Abdul-Mageed and Mona Diab. 2012. AWATIF: A multi-genre corpus for Modern Standard Arabic subjectivity and sentiment analysis. In Proceedings of LREC, pages 3907–3914.
Ashton Anderson, Daniel Huttenlocher, Jon Kleinberg, and Jure Leskovec. 201Effects of user similarity in social media. In Proceedings of WSDM, pages 703–712.
Lynne M. Andersson and Christine M. Pearson. 1999. Tit for tat? the spiraling effect of incivility in the workplace. The Academy of Management Review, 24(3):452–471.
Shoshana Blum-Kulka and Gabriele Kasper. 1990. Special issue on politeness. Journal of Pragmatics, 144(2).
Shoshana Blum-Kulka. 2003. Indirectness and politeness in requests: Same or different? Journal of Pragmatics, 11(2):131–146.
Philip Bramsen, Martha Escobar-Molana, Ami Patel, and Rafael Alonso. Extracting social power relationships from natural language. In Proceedings of ACL, pages 773–782.
Susan E Brennan and Justina O Ohaeri. 1999. Why do electronic conversations seem less polite? the costs and benefits of hedging. SIGSOFT Softw. Eng. Notes, 24(2):227–235.
Penelope Brown and Stephen C. Levinson. 197Universals in language use: Politeness phenomena. In Esther N. Goody, editor, Questions and Politeness: Strategies in Social Interaction, pages 56–311, Cambridge. Cambridge University Press.
Penelope Brown and Stephen C Levinson. 1987. Politeness: some universals in language usage. Cambridge University Press.
Moira Burke and Robert Kraut. 2008a. Mind your Ps and Qs: the impact of politeness and rudeness in online communities. In Proceedings of CSCW, pages 281–284.
Moira Burke and Robert Kraut. 2008b. Taking up the mop: identifying future wikipedia administrators. In CHI ’08 extended abstracts on Human factors in computing systems, pages 3441–3446.
Andrew Sangpil Byon. 2006. The role of linguistic indirectness and honorifics in achieving linguistic politeness in Korean requests. Journal of Politeness Research, 2(2):247–276.
Paul Chilton. 1990.
Politeness, politics, and diplomacy. Discourse and Society, 1(2):201–224.
Herbert H. Clark and Dale H. Schunk. 1980. Polite responses to polite requests. Cognition, 8(1):111– 143.
Cristian Danescu-Niculescu-Mizil, Lillian Lee, Bo Pang, and Jon Kleinberg. 2012. Echoes of power: Language effects and power differences in social interaction. In Proceedings of WWW, pages 699–708.
Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of LREC, pages 449–454.
Christopher P. Diehl, Galileo Namata, and Lise Getoor. 2007. Relationship identification for social network discovery. In Proceedings of the AAAI Workshop on Enhanced Messaging, pages 546–552.
Kirk W Duthler. 2006. The Politeness of Requests Made Via Email and Voicemail: Support for the Hyperpersonal Model. Journal of Computer-Mediated Communication, 11(2):500–521.
Manaal Faruqui and Sebastian Pado. 2012. Towards a model of formal and informal address in english. In Proceedings of EACL, pages 623–633.
Elen P. Francik and Herbert H. Clark. 1985. How to make requests that overcome obstacles to compliance. Journal of Memory and Language, 24:560– 568.
Eric Gilbert. 2012. Phrases that signal workplace hierarchy. In Proceedings of CSCW, pages 1037–1046.
H. Paul Grice. 1975. Logic and conversation. In Peter Cole and Jerry Morgan, editors, Syntax and Semantics, volume 3: Speech Acts, pages 43–58. Academic Press, New York.
S Gupta, M Walker, and D Romano. 2007. How rude are you?: Evaluating politeness and affect in interaction. Affective Computing and Intelligent Interaction, pages 203–217.
Samuel Gyasi Obeng. 1997. Language and politics: Indirectness in political discourse. Discourse and Society, 8(1):49–83.
S. I. Harada. 1976. Honorifics. In Masayoshi Shibatani, editor, Syntax and Semantics, volume 5: Japanese Generative Grammar, pages 499–561. Academic Press, New York.
Susan Herring. 1994. Politeness in computer culture: Why women thank and men flame. In Cultural performances: Proceedings of the third Berkeley women and language conference, volume 278, page 94.
Janet Holmes and Maria Stubbe. 2005. Power and Politeness in the Workplace: A Sociolinguistic Analysis of Talk at Work. Longman, London.
Ken Hyland. 2005. Metadiscourse: Exploring Interaction in Writing. Continuum, London and New York.
Sachiko Ide. 1989. Formal forms and discernment: Two neglected aspects of universals of linguistic politeness. Multilingua, 8(2–3):223–248.
David Kaplan. 1999. What is meaning? Explorations in the theory of Meaning as Use. Brief version — draft 1. Ms., UCLA.
Robin Lakoff. 1973. The logic of politeness; or, miding your P’s and Q’s. In Proceedings of the 9th Meeting of the Chicago Linguistic Society, pages 292–305.
Robin Lakoff. 1977. What you can do with words: Politeness, pragmatics and performatives. In Proceedings of the Texas Conference on Performatives, Presuppositions and Implicatures, pages 79–106.
Geoffrey N. Leech. 1983. Principles of Pragmatics. Longman, London and New York.
Jure Leskovec, Daniel Huttenlocher, and Jon Kleinberg. 2010. Governance in Social Media: A case study of the Wikipedia promotion process. In Proceedings of ICWSM, pages 98–105.
Bing Liu, Minqing Hu, and Junsheng Cheng. 2005. Opinion Observer: analyzing and comparing opinions on the Web. In Proceedings of WWW, pages 342–351.
Yoshiko Matsumoto. 1988. Reexamination of the universality of face: Politeness phenomena in Japanese. Journal of Pragmatics, 12(4):403–426.
Andrew McCallum, Xuerui Wang, and Andr’es Corrada-Emmanuel. 2007. Topic and role discovery in social networks with experiments on Enron and academic email. Journal of Artificial Intelligence Research, 30(1):249–272.
Robert Munro, Steven Bethard, Victor Kuperman, Vicky Tzuyin Lai, Robin Melnick, Christopher Potts, Tyler Schnoebelen, and Harry Tily. 2010. Crowdsourcing and language studies: the new generation of linguistic data. In Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk, pages 122–130.
Kelly Peterson, Matt Hohensee, and Fei Xia. 2011. Email formality in the workplace: A case study on the enron corpus. In Proceedings of the ACL Workshop on Language in Social Media, pages 86–95.
Vinodkumar Prabhakaran, Owen Rambow, and Mona Diab. 2012. Predicting Overt Display of Power in Written Dialogs. In Proceedings of NAACL-HLT, pages 518–522.
Priscilla S. Rogers and Song Mei Lee-Wong. 2003. Reconceptualizing politeness to accommodate dynamic tensions in subordinate-to-superior reporting. Journal of Business and Technical Communication, 17(4):379–412.
Andrew J. Scholand, Yla R. Tausczik, and James W. Pennebaker. 2010. Social language network analysis. In Proceedings of CSCW, pages 23–26.
Robert Van Rooy. 2003. Being polite is a handicap: Towards a game theoretical analysis of polite linguistic behavior. In Proceedings of TARK, pages 45–58.
Marilyn A Walker, Janet E Cahn, and Stephen J Whittaker. 1997. Improvising linguistic style: social and affective bases for agent personality. In Proceedings of AGENTS, pages 96–105.
William Yang Wang, Samantha Finkelstein, Amy Ogan, Alan W. Black, and Justine Cassell. 2012. ”love ya, jerkface”: Using sparse log-linear models to build positive and impolite relationships with teens. In Proceedings of SIGDIAL, pages 20–29.
Richard J. Watts. 2003. Politeness. Cambridge University Press, Cambridge.
Ian H Witten and Eibe Frank. 2005. Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann.