Priyanshu Priya
Skip Abstract Section
Abstract
Computational approach to politeness is the task of automatically predicting and/or generating politeness in text. This is a pivotal task for conversational analysis, given the ubiquity and challenges of politeness in interactions. The computational approach to politeness has witnessed great interest from the conversational analysis community. This article is a compilation of past works in computational politeness in natural language processing. We view four milestones in the research so far, viz. supervised and weakly supervised feature extraction to identify and induce politeness in a given text, incorporation of context beyond the target text, study of politeness across different social factors, and study the relationship between politeness and various socio-linguistic cues. In this article, we describe the datasets, approaches, trends, and issues in computational politeness research. We also discuss representative performance values and provide pointers to future works, as given in the prior works. In terms of resources to understand the state of the art, this survey presents several valuable illustrations—most prominently, a table summarizing the past papers along different dimensions, such as the types of features, annotation techniques, and datasets used.
- [1] . 2007. Constructing empirical models for automatic dialog parameterization. In International Conference on Text, Speech and Dialogue. Springer, 455–463.Google Scholar
Cross Ref
- [2] . 2008. Regression model for politeness estimation trained on examples. In Proceedings of the NooJ’07 Conference. 206–13.Google Scholar
- [3] . 2020. Contextualized Embeddings for Enriching Linguistic Analyses on Politeness. In Proceedings of the 28th International Conference on Computational Linguistics. 2181–2190.Google ScholarCross Ref
- [4] . 2016. Interpreting neural networks to improve politeness comprehension. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2035–2041.Google ScholarCross Ref
- [5] . 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations (ICLR’15).Google Scholar
- [6] . 2021. Conversations gone alright: Quantifying and predicting prosocial outcomes in online conversations. In Proceedings of the Web Conference. 1134–1145.Google ScholarDigital Library
- [7] . 2003. Strategies for learning in class imbalance problems. Pattern Recogn. 36, 3 (2003), 849–851.Google ScholarCross Ref
- [8] Elizabeth Bates and Louise Silvern. 1977. Social adjustment and politeness in preschoolers. Journal of Communication 27, 2 (1977), 104–111.Google Scholar
- [9] . 2023. PolitePEER: Does peer review hurt? A dataset to gauge politeness intensity in the peer reviews. Lang. Resourc. Eval. (2023), 1–23.Google Scholar
- [10] . 1991. Variation across Speech and Writing. Cambridge University Press.Google Scholar
- [11] . 1997. Fast planning through planning graph analysis. Artif. Intell. 90, 1-2 (1997), 281–300.Google ScholarDigital Library
- [12] . 2022. Conversational analysis of daily dialog data using polite emotional dialogue acts. In Proceedings of the 13th Language Resources and Evaluation Conference. 2395–2400.Google Scholar
- [13] . 2008. Impoliteness in Interaction. John Benjamins, Amsterdam, 1–295.Google Scholar
- [14] . 1991. The self and social conduct: Linking self-representations to prosocial behavior. J. Pers. Soc. Psychol. 60, 3 (1991), 368.Google ScholarCross Ref
- [15] . 1979. Speech as a marker of situation. In Social Markers in Speech. Cambridge University Press, 33–62.Google Scholar
- [16] . 1978. Universals in language usage: Politeness phenomena. In Questions and Politeness: Strategies in Social Interaction. Cambridge University Press, 56–311.Google Scholar
- [17] . 1987. Politeness: Some Universals in Language Usage. Vol. 4. Cambridge University Press.Google ScholarCross Ref
- [18] . 1992. An estimate of an upper bound for the entropy of English. Comput. Ling. 18, 1 (1992), 31–40.Google ScholarDigital Library
- [19] . 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, Vol. 33, 1877–1901.Google Scholar
- [20] . 2018. Modeling empathy and distress in reaction to news stories. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 4758–4765.Google ScholarCross Ref
- [21] . 2019. Taskmaster-1: Toward a realistic and diverse dialog dataset. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 4516–4525.Google ScholarCross Ref
- [22] . 2011. Emotional experience improves with age: Evidence based on over 10 years of experience sampling. Psychol. Aging 26, 1 (2011), 21.Google ScholarCross Ref
- [23] . 2020. Joint aspect extraction and sentiment analysis with directional graph convolutional networks. In Proceedings of the 28th International Conference on Computational Linguistics. 272–279.Google ScholarCross Ref
- [24] . 2018. Frustrated, polite, or formal: Quantifying feelings and tone in email. In Proceedings of the 2nd Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media. 76–86.Google ScholarCross Ref
- [25] Christie. 2007. Relevance theory and politeness. Journal of Politeness Research 3, 2 (2007), 269–294. Google ScholarCross Ref
- [26] Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei. 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research 25, 70 (2024), 1–53. Retrieved from http://jmlr.org/papers/v25/23-0870.htmlGoogle Scholar
- [27] . 2019. CONAN-COunter NArratives through Nichesourcing: A multilingual dataset of responses to fight online hate speech. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2819–2829.Google ScholarCross Ref
- [28] . 2011. Politeness and impoliteness. In Pragmatics of Society. de Gruyter Mouton, 393.Google ScholarCross Ref
- [29] . 2011. Impoliteness: Using Language to Cause Offence, Vol. 28. Cambridge University Press.Google ScholarCross Ref
- [30] . 2016. Impoliteness strategies. In Interdisciplinary Studies in Pragmatics, Culture and Society, 421–445.Google ScholarCross Ref
- [31] . 2017. The Palgrave Handbook of Linguistic (im) Politeness. Springer.Google ScholarCross Ref
- [32] . 1994. Maintenance strategies and physical affection as predictors of love, liking, and satisfaction in marriage. Commun. Rep. 7, 2 (1994), 88–98.Google ScholarCross Ref
- [33] . 2013. A computational approach to politeness with application to social factors. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 250–259.Google Scholar
- [34] . 2023. Graph induced transformer network for detection of politeness and formality in text. In Companion Proceedings of the ACM Web Conference 2023. 221–224.Google ScholarDigital Library
- [35] . 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. Retrieved from https://arxiv.org/abs/1810.04805Google Scholar
- [36] . 2020. A turn to language: How interactional sociolinguistics informs the redesign of prompt: Response chatbot turns. Discourse Context Media 37 (2020), 100432.Google ScholarCross Ref
- [37] . 2019. Investigating capsule network and semantic feature on hyperplanes for text classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 456–465.Google ScholarCross Ref
- [38] . 2019. Controlling Japanese honorifics in English-to-Japanese neural machine translation. In Proceedings of the 6th Workshop on Asian Translation. 45–53.Google ScholarCross Ref
- [39] . 2022. EmoWOZ: A large-scale corpus and labelling scheme for emotion recognition in task-oriented dialogue systems. In Proceedings of the 13th Language Resources and Evaluation Conference. 4096–4113.Google Scholar
- [40] . 2020. Incorporating politeness across languages in customer care responses: Towards building a multi-lingual empathetic dialogue agent. In Proceedings of the 12th Language Resources and Evaluation Conference. 4172–4182.Google Scholar
- [41] . 2022. PoliSe: Reinforcing politeness using user sentiment for customer care response generation. In Proceedings of the 29th International Conference on Computational Linguistics. 6165–6175.Google Scholar
- [42] . 2023. Mixing it up: Inducing empathy and politeness using multiple behaviour-aware generators for conversational systems. In Findings of the Association for Computational Linguistics (IJCNLP-AACL’23 Findings). 336–347.Google ScholarCross Ref
- [43] . 2022. Being polite: Modeling politeness variation in a personalized dialog agent. IEEE Trans. Comput. Soc. Syst. (2022).Google Scholar
- [44] . 1965. The stylistic significance of consonantal sandhi in Trukese and Ponapean. Am. Anthropol. 67, 6 (1965), 1495–1502.Google ScholarCross Ref
- [45] . 2020. Facilitating the communication of politeness through fine-grained paraphrasing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 5127–5140.Google ScholarCross Ref
- [46] . 2012. On the effectiveness of preprocessing methods when dealing with different levels of class imbalance. Knowl.-Bas. Syst. 25, 1 (2012), 13–21.Google ScholarDigital Library
- [47] . 2001. A Critique of Politeness Theories. St Jerome, Manchester, UK.Google Scholar
- [48] Erving Goffman. 1967. Interaction ritual: Essays on face-to-face interaction (1st ed.). Routledge, New York, NY, USA.Google Scholar
- [49] . 2019. Courteously yours: Inducing courteous behavior in customer care responses using reinforced pointer generator network. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 851–860.Google ScholarCross Ref
- [50] . 2007. Disagreeing to agree: Conflict,(im) politeness and identity in a computer-mediated community. J. Pragmatics 39, 4 (2007), 742–759.Google ScholarCross Ref
- [51] . 1975. Logic and Conversation, Syntax and Semantics, vol. 3, P. Cole and J. Morgan (Eds.).Google Scholar
- [52] . 1990. Politeness phenomena in modern Chinese. J. Pragmatics 14, 2 (1990), 237–257.Google ScholarCross Ref
- [53] . 2007. How rude are you?: Evaluating politeness and affect in interaction. In International Conference on Affective Computing and Intelligent Interaction. Springer, 203–217.Google ScholarDigital Library
- [54] . 2010. When is an email really offensive?: Argumentativity and variability in evaluations of impoliteness.Google Scholar
- [55] Francis Heylighen and Jean-Marc Dewaele. 1999. Formality of language: definition, measurement and behavioral determinants. Interner Bericht, Center “Leo Apostel”, Vrije Universiteit Brüssel, Center “Leo Apostel”, Free University of Brussels, Pleinlaan 2, B-1050 Brussels, Belgium.Google Scholar
- [56] . 2017. Evaluating a computational approach to labeling politeness: Challenges for the application of machine classification to social computing data. Proc. ACM Hum.-Comput. Interact. 1, CSCW (2017), 1–14.Google ScholarDigital Library
- [57] . 1988. Paying compliments: A sex-preferential politeness strategy. J. Pragmatics 12, 4 (1988), 445–465.Google ScholarCross Ref
- [58] . 2013. Women, Men and Politeness. Routledge.Google ScholarCross Ref
- [59] . 1990. Politeness as universal: Cross-cultural perceptions of request strategies and inferences based on their use. J. Pers. Soc. Psychol. 59, 4 (1990), 719.Google ScholarCross Ref
- [60] . 1987. Generating natural language under pragmatic constraints. J. Pragmatics 11, 6 (1987), 689–719.Google ScholarCross Ref
- [61] . 1994. About 37% of word-tokens are nouns. Language 70, 2 (1994), 331–339.Google ScholarCross Ref
- [62] . 2014. Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 8. 216–225.Google ScholarCross Ref
- [63] . 2019. Politeness counts: Perceptions of peacekeeping robots. IEEE Trans. Hum.-Mach. Syst. 49, 3 (2019), 232–240.Google ScholarCross Ref
- [64] . 1979. Formality and informality in communicative events. Am. Anthropol. 81, 4 (1979), 773–790.Google ScholarCross Ref
- [65] . 1993. Universality and relativity in cross-cultural politeness research: A historical perspective. Multilingua 12, 1 (1993), 13–50.Google Scholar
- [66] . 2019. Communicating with warmth in distributive negotiations is surprisingly counterproductive. Manage. Sci. 65, 12 (2019), 5813–5837.Google ScholarDigital Library
- [67] . 2004. Politeness in tutoring dialogs:“run the factory, that’s what I’d do.” In International Conference on Intelligent Tutoring Systems. Springer, 67–76.Google Scholar
- [68] . 2004. Generating socially appropriate tutorial dialog. In Tutorial and Research Workshop on Affective Dialogue Systems. Springer, 254–264.Google ScholarCross Ref
- [69] . 2017. Personalization in goal-oriented dialog. arXiv:1706.07503. Retrieved from https://arxiv.org/abs/1706.07503Google Scholar
- [70] . 2008. Impoliteness and emotional arguments.Google Scholar
- [71] Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR’17), Palais des Congrès Neptune, Toulon, France. Retrieved from https://openreview.net/forum?id=SJU4ayYglGoogle Scholar
- [72] . 2004. Introducing the Enron corpus. In Proceedings of the Conference on Email and Anti-Spam (CEAS’04).Google Scholar
- [73] Klaus Krippendorff. 2007. Computing krippendorff.s alpha-reliability. http://www.asc.upenn.edu/Krippendorff/Google Scholar
- [74] . 2012. Challenges in the development of annotated corpora of computer-mediated communication in Indian languages: A case of Hindi. In Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC’12). 299–302.Google Scholar
- [75] . 2014. Developing politeness annotated corpus of hindi blogs. In Proceedings of the International Conference on Language Resources and Evaluation (LREC’14). 1275–1280.Google Scholar
- [76] . 2021. Towards automatic identification of linguistic politeness in Hindi texts. arXiv:2111.15268. Retrieved from https://arxiv.org/abs/2111.15268Google Scholar
- [77] . 2010. Translating politeness across cultures: Case of Hindi and English. In Proceedings of the 3rd International Conference on Intercultural Collaboration. 175–178.Google ScholarDigital Library
- [78] . 2014. Crosslinguistic and crosscultural approaches to pragmatic development. In Pragmatic Development in First Language Acquisition, 317–342.Google Scholar
- [79] . 1973. Language and woman’s place. Lang. Soc. 2, 1 (1973), 45–79.Google ScholarCross Ref
- [80] . 1973. The logic of politeness: Or, minding your p’s and q’s. In Proceedings from the Annual Meeting of the Chicago Linguistic Society, Vol. 9. Chicago Linguistic Society, 292–305.Google Scholar
- [81] Robin Tolmach Lakoff. 1989. The limits of politeness: Therapeutic and courtroom discourse in linguistic politeness II. Multilingua 8, 2.3 (1989), 101–129.Google Scholar
- [82] . 2017. (Im) politeness and emotion. In The Palgrave Handbook of Linguistic (Im) Politeness. Springer, 287–322.Google ScholarCross Ref
- [83] . 1983. Principles of Pragmatics. Longman Group Ltd., London.Google Scholar
- [84] . 1992. Pragmatic principles in Shaw’s you never can tell. Language, Text and Context: Essays in Stylistics (1992), 259–78.Google Scholar
- [85] . 2005. Politeness: Is there an east-west divide. J. Foreign Lang. 6, 3 (2005), 1–30.Google Scholar
- [86] . 2020. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7871–7880.Google ScholarCross Ref
- [87] . 2023. How well can language models understand politeness? In Proceedings of the IEEE Conference on Artificial Intelligence (CAI’23). IEEE, 230–231.Google ScholarCross Ref
- [88] . 2020. Studying politeness across cultures using english twitter and mandarin weibo. Proc. ACM Hum.-Comput. Interact. 4, CSCW2 (2020), 1–15.Google ScholarDigital Library
- [89] . 2018. Microsoft dialogue challenge: Building end-to-end task-completion dialogue systems. arXiv:1807.11125. Retrieved from https://arxiv.org/abs/1807.11125Google Scholar
- [90] . 2017. DailyDialog: A manually labelled multi-turn dialogue dataset. In Proceedings of the 8th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 986–995.Google Scholar
- [91] . 2022. Can large language models reason about medical questions? arXiv:2207.08143. Retrieved from https://arxiv.org/abs/2207.08143Google Scholar
- [92] . 2004. Rouge: A package for automatic evaluation of summaries. In Text Summarization Branches Out. 74–81.Google Scholar
- [93] . 2023. LLM-Eval: Unified multi-dimensional automatic evaluation for open-domain conversations with large language models. In Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI’23), and (Eds.). Association for Computational Linguistics, 47–58.
DOI: Google ScholarCross Ref - [94] Miriam A Locher. 2006. Polite behavior within relational work: The discursive approach to politeness. Multilingua 25, 3 (2006), 249–267.Google Scholar
- [95] . 2006. Power and politeness in action: Disagreements in oral communication. Lang. Soc. Lond. 35, 5 (2006), 729–732.Google ScholarCross Ref
- [96] . 2005. Politeness theory and relational work.Google Scholar
- [97] . 2008. Relational work and impoliteness: Negotiating norms of linguistic behaviour. Lang. Power Soc. Process 21 (2008), 77.Google Scholar
- [98] . 2020. Politeness transfer: A tag and generate approach. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 1869–1881.Google ScholarCross Ref
- [99] . 1973. Nonegocentric communication abilities in preschool children. Child Dev. (1973), 697–700.Google ScholarCross Ref
- [100] . 1996. Language and gender. Sociolinguist. Lang. Teach. (1996), 218.Google Scholar
- [101] . 2012. Interrater reliability: The kappa statistic. Biochem. Med. 22, 3 (2012), 276–282.Google ScholarCross Ref
- [102] . 2007. A computational approach to etiquette and politeness: An “Etiquette Engine™” for cultural interaction training. In Conference on Behavior Representation in Modeling and Simulation (BRIMS’07).Google Scholar
- [103] . 2006. A computational approach to etiquette and politeness: Initial test cases. In Conference on Behavior Representation in Modeling and Simulation (BRIMS’06). 15–18.Google Scholar
- [104] . 2008. A computational approach to etiquette: Operationalizing Brown and Levinson’s politeness model. IEEE Intell. Syst. 23, 4 (2008), 28–35.Google ScholarDigital Library
- [105] . 2003. Gender and Politeness. Number 17. Cambridge University Press.Google ScholarCross Ref
- [106] . 2020. Why won’t you listen to me? Measuring receptiveness to opposing views. Manage. Sci. 66, 7 (2020), 3069–3094.Google ScholarDigital Library
- [107] . 2022. Please be polite: Towards building a politeness adaptive dialogue system for goal-oriented conversations. Neurocomputing 494 (2022), 242–254.Google ScholarCross Ref
- [108] . 2022. Predicting politeness variations in goal-oriented conversations. IEEE Trans. Comput. Soc. Syst. (2022).Google Scholar
- [109] . 2023. GenPADS: Reinforcing politeness in an end-to-end dialogue system. PLoS One 18, 1 (2023), e0278323.Google ScholarCross Ref
- [110] . 2023. e-THERAPIST: I suggest you to cultivate a mindset of positivity and nurture uplifting thoughts. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 13952–13967.Google ScholarCross Ref
- [111] . 2023. Help me heal: A reinforced polite and empathetic mental health and legal counseling dialogue system for crime victims. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 14408–14416.Google ScholarDigital Library
- [112] . 2023. PAL to lend a helping hand: Towards building an emotion adaptive polite and empathetic counseling conversational agent. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 12254–12271.Google ScholarCross Ref
- [113] . 2022. PEPDS: A polite and empathetic persuasive dialogue system for charity donation. In Proceedings of the 29th International Conference on Computational Linguistics. 424–440.Google Scholar
- [114] . 2020. A politeness control method for conversational agents considering social relationships with users. In Annual Conference of the Japanese Society for Artificial Intelligence. Springer, 224–231.Google Scholar
- [115] . 2013. Crowdsourcing a word–emotion association lexicon. Comput. Intell. 29, 3 (2013), 436–465.Google ScholarCross Ref
- [116] . 1998. Multiple modals in LAGS. In From the Gulf States and Beyond: The Legacy of Lee Pederson and LAGS, 90.Google Scholar
- [117] . 2023. Polite Chatbot: A text style transfer application. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop. 87–93.Google Scholar
- [118] . 2013. Identifying social and expressive factors in request texts using transaction/sequence model. In Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP’13). 496–503.Google Scholar
- [119] . 2002. Polite language usage in mother-infant interactions: A look at language socialization. Stud. Lang. Sci. 2 (2002), 175–191.Google Scholar
- [120] . 2017. Automatically identifying good conversations online (yes, they do exist!). In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 11. 628–631.Google ScholarCross Ref
- [121] . 2017. Finding good conversations online: The yahoo news annotated comments corpus. In Proceedings of the 11th Linguistic Annotation Workshop. 13–23.Google ScholarCross Ref
- [122] . 2018. Polite dialogue generation without parallel data. Trans. Assoc. Comput. Ling. 6 (2018), 373–389.Google ScholarCross Ref
- [123] . 1988. The cognitive structure of emotions. Cambridge University Press, Cambridge, UK.Google Scholar
- [124] . 2002. Bleu: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311–318.Google ScholarDigital Library
- [125] James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates 71, 2001 (2001), 2001.Google Scholar
- [126] . 2019. What makes a good counselor? learning to distinguish between high-quality and low-quality counseling conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 926–935.Google ScholarCross Ref
- [127] . 2019. Multi-domain goal-oriented dialogues (multidogo): Strategies toward curating and annotating large scale dialogue data. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 4526–4536.Google ScholarCross Ref
- [128] . 1968. A scale of politeness of request forms in English. Term paper for Speech 164A. University of California, Berkeley.Google Scholar
- [129] . 2023. A multi-task learning framework for politeness and emotion detection in dialogues for mental health counselling and legal aid. Expert Syst. Appl. 224 (2023), 120025.Google ScholarDigital Library
- [130] . 2023. PARTNER: A persuasive mental health and legal counselling dialogue system for women and children crime victims. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI’23), (Ed.), 6183–6191.
DOI: AI for Good .Google ScholarDigital Library - [131] . 2023. ChatGPT vs human-authored text: Insights into controllable text summarization and sentence style transfer. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), , , and (Eds.). Association for Computational Linguistics, 1–18.
DOI: Google ScholarCross Ref - [132] . 2019. A benchmark dataset for learning to intervene in online hate speech. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 4755–4764.Google ScholarCross Ref
- [133] . 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.Google Scholar
- [134] . 2022. Is reinforcement learning (not) for natural language processing?: Benchmarks, baselines, and building blocks for natural language policy optimization. arXiv:2210.01241. https://arxiv.org/abs/2210.01241Google Scholar
- [135] . 2021. Effect of polite triggers in chatbot conversations on user experience across gender, age, and personality. In Proceedings of the 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN’21). IEEE, 813–819.Google ScholarDigital Library
- [136] Bernd Renner. 2020. (In) directness as an (im) politeness strategy in the contact between german and Brazilian portuguese as additional languages. phdthesis. Universidade de Brasília, Brasília.Google Scholar
- [137] . 2021. Recipes for building an open-domain chatbot. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 300–325.Google ScholarCross Ref
- [138] . 2004. Politeness and summarization: An exploratory study. In Proceedings of AAAI Spring Symposium on Exploring Attitude and Affect in Text: Theories and Applications (AAAI-EAAT’04).Google Scholar
- [139] . 2006. Politeness and bias in dialogue summarization: Two exploratory studies. In Computing Attitude and Affect in Text: Theory and Applications. Springer, 171–185.Google ScholarCross Ref
- [140] . 2022. CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech. In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI’22), (Ed.), 5157–5163.
DOI: AI for Good .Google ScholarCross Ref - [141] . 2019. DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. In NeurIPS EMC\(^2\) Workshop.Google Scholar
- [142] . 2017. Proximal policy optimization algorithms. arXiv:1707.06347. Retrieved from https://arxiv.org/abs/1707.06347Google Scholar
- [143] . 1969. Speech Acts: An Essay in the Philosophy of Language. Vol. 626. Cambridge University Press.Google ScholarCross Ref
- [144] . 2016. Controlling politeness in neural machine translation via side constraints. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 35–40.Google ScholarCross Ref
- [145] . 2013. Exploiting synergies between open resources for german dependency parsing, pos-tagging, and morphological analysis. In Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP’13). 601–609.Google Scholar
- [146] . 2020. A computational approach to understanding empathy expressed in text-based mental health support. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 5263–5276.Google ScholarCross Ref
- [147] . 1973. The development of communication skills: Modifications in the speech of young children as a function of listener. Monogr. Soc. Res. Child Dev. (1973), 1–38.Google ScholarCross Ref
- [148] . 2022. Polite task-oriented dialog agents: To generate or to rewrite?. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis. 304–314.Google ScholarCross Ref
- [149] . 2022. EmoInHindi: A multi-label emotion and intensity annotated dataset in hindi for emotion recognition in dialogues. In Proceedings of the 13th Language Resources and Evaluation Conference. 5829–5837.Google Scholar
- [150] . 2023. Appreciation vs. apology: Research on the influence mechanism of chatbot service recovery based on politeness theory. J. Retail. Consum. Serv. 73 (2023), 103323.Google ScholarCross Ref
- [151] . 2016. The interaction of politeness systems in Korean learners of French. In Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers. 163–171.Google Scholar
- [152] . 2022. TyDiP: A dataset for politeness classification in nine typologically diverse languages. In Findings of the Association for Computational Linguistics: EMNLP’22. 5723–5738.Google ScholarCross Ref
- [153] . 2010. The power of positive psychology: Psychological capital and work engagement. In Work Engagement: A Handbook of Essential Theory and Research, Vol. 54, 68.Google Scholar
- [154] . 2001. Politeness in Cypriot Greek: A Frame-based Approach. Ph. D. Dissertation. Citeseer.Google Scholar
- [155] . 2002. Politeness and formulaicity: Evidence from Cypriot Greek. J. Greek Ling. 3, 1 (2002), 179–201.Google ScholarCross Ref
- [156] Marina Terkourafi. 2005. Beyond the micro-level in politeness research. Journal of Politeness Research 1, (2005), 237262.Google Scholar
- [157] . 2005. Pragmatic correlates of frequency of use: The case for a notion of “minimal context.” Trends Ling. Stud. Monogr. 161 (2005), 209.Google Scholar
- [158] . 2014. Meaning in Interaction: An Introduction to Pragmatics. Routledge.Google ScholarCross Ref
- [159] . 2012. Parallel data, tools and interfaces in OPUS. In Proceedings of the International Conference on Language Resources and Evaluation (LREC’12), Vol. 2012. Citeseer, 2214–2218.Google Scholar
- [160] . 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https://arxiv.org/abs/2302.13971Google Scholar
- [161] . 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998–6008.Google ScholarDigital Library
- [162] . 2019. Controlling formality and style of machine translation output using AutoML. In Annual International Symposium on Information Management and Big Data. Springer, 306–313.Google Scholar
- [163] . 2015. Some puzzles of politeness and impoliteness within a formal semantics of offensive language. In Conflict and Multimodal Communication: Social Research and Machine Intelligence, 223–241.Google ScholarCross Ref
- [164] . 2017. Language from police body camera footage shows racial disparities in officer respect. Proc. Natl. Acad. Sci. U.S.A. 114, 25 (2017), 6521–6526.Google ScholarCross Ref
- [165] . 1997. Improvising linguistic style: Social and affective bases for agent personality. In Proceedings of the 1st International Conference on Autonomous Agents. 96–105.Google ScholarDigital Library
- [166] . 2019. Persuasion for good: Towards a personalized persuasive dialogue system for social good. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5635–5649.Google ScholarCross Ref
- [167] . 2020. Can you be more social? Injecting politeness and positivity into task-oriented conversational agents. arXiv:2012.14653. Retrieved from https://arxiv.org/abs/2012.14653Google Scholar
- [168] . 2006. An Introduction to Sociolinguistics.Google Scholar
- [169] . 2017. Understanding abuse: A typology of abusive language detection subtasks. In Proceedings of the 1st Workshop on Abusive Language Online. 78–84.Google ScholarCross Ref
- [170] . 2003. Politeness. Cambridge University Press.Google ScholarCross Ref
- [171] . 2005. 2. Linguistic politeness and politic verbal behaviour: Reconsidering claims for universality. In Politeness in Language Studies in its History, Theory and Practice, 43–69.Google ScholarCross Ref
- [172] . 2022. Mental Disorders. Retrieved from https://www.who.int/news-room/fact-sheets/detail/mental-disordersGoogle Scholar
- [173] . 2014. The dialog state tracking challenge series. AI Mag. 35, 4 (2014), 121–124.Google ScholarDigital Library
- [174] . 2018. The politeness package: Detecting politeness in natural language. R J. 10, 2 (2018).Google ScholarCross Ref
- [175] . 2020. Conversational receptiveness: Improving engagement with opposing views. Org. Behav. Hum. Decis. Process. 160 (2020), 131–148.Google ScholarCross Ref
- [176] . 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31, 7 (2019), 1235–1270.Google ScholarDigital Library
- [177] . 2020. The Study of Language. Cambridge University Press.Google Scholar
- [178] . 2018. Conversations gone awry: Detecting early signs of conversational failure. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1350–1361.Google ScholarCross Ref
- [179] . 2020. DIALOGPT: Large-scale generative pre-training for conversational response generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 270–278.Google ScholarCross Ref
- [180] . 2023. Is ChatGPT equipped with emotional dialogue capabilities? arXiv:2304.09582. Retrieved from https://arxiv.org/abs/2304.09582Google Scholar
- [181] . 2023. A survey of large language models. arXiv:2303.18223. Retrieved from https://arxiv.org/abs/2303.18223Google Scholar
- [182] . 2020. Condolence and empathy in online communities. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 609–626.Google ScholarCross Ref
- [183] . 2023. Can large language models transform computational social science? arXiv:2305.03514. Retrieved from https://arxiv.org/abs/2305.03514Google Scholar
Index Terms
- Computational Politeness in Natural Language Processing: A Survey
Recommendations
Exploring how politeness impacts the user experience of chatbots for mental health support
AbstractPoliteness is important in human–human interaction when asking people to engage in sensitive conversations. If politeness manifests similarly in human–chatbot interaction, it may play an important role in the design of sensitive chatbot ...
Highlights- Politeness can both positively and negatively impact the chatbot user experience.
- The Personal politeness chatbot was experienced as caring and encouraging.
- The Passive politeness chatbot was experienced as too apologetic and ...
Investigating politeness strategies in chatbots through the lens of Conversation Analysis
IHC '23: Proceedings of the XXII Brazilian Symposium on Human Factors in Computing SystemsDespite gaining popularity in recent years, chatbots frequently fall short of meeting user expectations. These interaction challenges arise from the limitations of chatbots, including their capacity to accurately understand user queries, deliver ...
Modeling Politeness in Human-Robot Interaction
HRI '24: Companion of the 2024 ACM/IEEE International Conference on Human-Robot InteractionPoliteness is a linguistic phenomenon central to human communication. The many influences on the choice and interpretation of politeness in language make the phenomenon very complex to model and to account for in Human-Robot Interaction. I therefore ...
Comments