Abstract
Positive reframing is a cognitive process that involves giving negative events a new positive interpretation, leading to positive behavioral options and perceptions. Our research project aims to promote positive emotions by presenting positive reframing sentences to the negative ones the user has entered using a keyboard. To achieve this, we propose using GPT-3, a natural language processing model, to generate a large number of reframing dictionary entries in a short time. We trained GPT-3 on manually generated reframing pairs and tested it on new negative sentences. Our results show that, with three or more pairs of training data, GPT-3 can generally reframe negative sentences as expected. Our technique can be used to construct a high-quality reframing dictionary, which can help promote positive emotions and well-being.
This work is supported by JSPS KAKENHI Grant Number JP20K11904.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Calvo, R.A., Peters, D.: Positive Computing: Technology for Wellbeing and Human Potential. MIT Press, Cambridge (2014)
Lambert, N.M., Fincham, F.D., Stillman, T.F.: Gratitude and depressive symptoms: the role of positive reframing and positive emotion. Cogn. Emot. 26(4), 615–633 (2012)
Cavanaugh, M.A., Boswell, W.R., Roehling, M.V., Boudreau, J.W.: An empirical examination of self-reported work stress among U.S. managers. J. Appl. Psychol. 85(1), 65–74 (2000)
Seligman, M.E.P.: The Optimistic Child: A Proven Program to Safeguard Children Against Depression and Build Lifelong Resilience. HarperOne, California (2007)
Go, K., Moriya, Y., Kinoshita, Y., Li, J., Fukumoto, F.: Happy text entering: promoting subjective well-being using an input method for presenting positive words and phrases. In: Proceedings of the 2022 Conference, pp. 153–158. ACM (2022). https://doi.org/10.1145/3520495.3520521
Turney, P.D.: Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (ACL 2002), pp. 417–424. Association for Computational Linguistics, USA (2002). https://doi.org/10.3115/1073083.1073153
Mohammad, S.M., Turney, P.D.: Crowdsourcing a Word-Emotion Association Lexicon. Comput. Intell. 29(3), 436–465 (2013). https://doi.org/10.1111/j.1467-8640.2012.00460.x
Mohammad, S.M., Turney, P.D.: Emotions evoked by common words and phrases: using mechanical turk to create an emotion lexicon. In: Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pp. 26–34. Association for Computational Linguistics, Los Angeles, CA (2010)
Saif, H., He, Y., Fernandez, M., Alani, H.: Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter. In: Presutti, V., Blomqvist, E., Troncy, R., Sack, H., Papadakis, I., Tordai, A. (eds.) ESWC 2014. LNCS, vol. 8798, pp. 54–63. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11955-7_5
Preoţiuc-Pietro, D., et al.: The role of personality, age, and gender in tweeting about mental illness. In: 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, pp. 21–30. Association for Computational Linguistics, Denver, Colorado (2015). https://doi.org/10.3115/v1/W15-1203
Muhammad, A., Wiratunga, N., Lothian, R.: Contextual sentiment analysis for social media genres. Knowl.-Based Syst. 108, 92–101 (2016). https://doi.org/10.1016/j.knosys.2016.05.032
OpenAI: GPT-3. https://openai.com/. Accessed 15 Mar 2023
Dathathri, S., et al.: Plug and play language models: a simple approach to controlled text generation. arXiv preprint https://arxiv.org/abs/1912.02164 (2019)
Elicit. https://elicit.org/. Accessed 15 Mar 2023
Ought. https://ought.org/. Accessed 15 Mar 2023
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fukasawa, H., Go, K., Fukumoto, F., Li, J., Kinoshita, Y. (2023). Creating a Positive Reframing Dictionary Using Machine Learning. In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds) HCI International 2023 Posters. HCII 2023. Communications in Computer and Information Science, vol 1836. Springer, Cham. https://doi.org/10.1007/978-3-031-36004-6_56
Download citation
DOI: https://doi.org/10.1007/978-3-031-36004-6_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36003-9
Online ISBN: 978-3-031-36004-6
eBook Packages: Computer ScienceComputer Science (R0)