Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Events (2309.12244v4)

Published 21 Sep 2023 in cs.HC, cs.AI, and cs.CL

Abstract: Children typically learn to identify and express emotions through sharing their stories and feelings with others, particularly their family. However, it is challenging for parents or siblings to have emotional communication with children since children are still developing their communication skills. We present ChaCha, a chatbot that encourages and guides children to share personal events and associated emotions. ChaCha combines a state machine and LLMs to keep the dialogue on track while carrying on free-form conversations. Through an exploratory study with 20 children (aged 8-12), we examine how ChaCha prompts children to share personal events and guides them to describe associated emotions. Participants perceived ChaCha as a close friend and shared their stories on various topics, such as family trips and personal achievements. Based on the findings, we discuss opportunities for leveraging LLMs to design child-friendly chatbots to support children in sharing emotions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (77)
  1. An overview of the features of chatbots in mental health: A scoping review. International Journal of Medical Informatics 132 (2019), 103978.
  2. Alberto Alegre. 2011. Parenting Styles and Children’s Emotional Intelligence: What do We Know? The Family Journal 19, 1 (2011), 56–62. https://doi.org/10.1177/1066480710387486
  3. Godwin S Ashiabi. 2000. Promoting the emotional development of preschoolers. Early childhood education journal 28 (2000), 79–84.
  4. Ana Aznar and Harriet R Tenenbaum. 2020. Gender comparisons in mother-child emotion talk: A meta-analysis. Sex roles 82 (2020), 155–162.
  5. Byung-yeul Baek. 2023. Naver’s HyperCLOVA X offers enhanced AI experience. https://www.koreatimes.co.kr/www/tech/2023/09/129_357754.html
  6. Virginia Braun and Victoria Clarke. 2006. Using Thematic Analysis in Psychology. Qualitative Research in Psychology 3, 2 (2006), 77–101. https://doi.org/10.1191/1478088706qp063oa
  7. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems (NeurIPS ’20), H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877–1901. https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
  8. HCI for Kids. In The human-computer interaction handbook. CRC Press, 819–836.
  9. Laura E Brumariu and Kathryn A Kerns. 2015. Mother–child emotion communication and childhood anxiety symptoms. Cognition and Emotion 29, 3 (2015), 416–431.
  10. To trust or to think: cognitive forcing functions can reduce overreliance on AI in AI-assisted decision-making. Proceedings of the ACM on Human-Computer Interaction 5, CSCW1 (2021), 1–21.
  11. Happy thoughts: Enhancing well-being in the classroom with a positive events diary. The Journal of Positive Psychology 13, 2 (2018), 110–121.
  12. LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation. arXiv preprint arXiv:2305.13614 (2023).
  13. Eunsil Choi and Bang HeeJeong. 2011. Reliability and Validity of the Emotion Expression Scale for Children. The Korean Journal of Developmental Psychology 24, 3 (2011), 105–128.
  14. PaLM: Scaling Language Modeling with Pathways. https://doi.org/10.48550/ARXIV.2204.02311
  15. Susanne A Denham and Sharon Auerbach. 1995. Mother-child dialogue about emotions and preschoolers’ emotional competence. Genetic, social, and general psychology monographs 121, 3 (1995), 311–337.
  16. Anthropomorphization of AI: Opportunities and Risks. arXiv:2305.14784 [cs.AI]
  17. Gilly Dosovitsky and Eduardo Bunge. 2023. Development of a chatbot for depression: adolescent perceptions and recommendations. Child and Adolescent Mental Health 28, 1 (2023), 124–127.
  18. Michael Dowling and Brian Lucey. 2023. ChatGPT for (finance) research: The Bananarama conjecture. Finance Research Letters 53 (2023), 103662.
  19. Aarthi Easwara Moorthy and Kim-Phuong L. Vu. 2015. Privacy Concerns for Use of Voice Activated Personal Assistant in the Public Space. International Journal of Human-Computer Interaction 31, 4 (April 2015), 307–335. https://doi.org/10.1080/10447318.2014.986642
  20. Missing early education and care during the pandemic: The socio-emotional impact of the COVID-19 crisis on young children. Early Childhood Education Journal 49, 5 (2021), 925–934.
  21. FastAPI. 2023. FastAPI framework, high performance, easy to learn, fast to code, ready for production. Retrieved Aug 25, 2023 from https://fastapi.tiangolo.com/
  22. Parent–child emotional communication and children’s coping in middle childhood. Social Development 14, 4 (2005), 591–612.
  23. Emma: An emotion-aware wellbeing chatbot. In 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE, 1–7.
  24. Daniel Goleman. 2005. Emotional Intelligence: Why it Can Matter More Than IQ (10th anniversary ed.). Bloomsbury. 384 pages.
  25. Google, Inc. 2023. Bard - Chat Based AI Tool from Google, Powered by PaLM 2. Retrieved Aug 25, 2023 from https://bard.google.com/
  26. J.M. Gottman and J. Declaire. 1998. Raising An Emotionally Intelligent Child. Simon & Schuster. https://books.google.co.kr/books?id=ovawL4cGhJ0C
  27. Emotion coaching: A universal strategy for supporting and promoting sustainable emotional and behavioural well-being. Educational & Child Psychology 32, 1 (2015), 31–41.
  28. An emotion-focused early intervention for children with emerging conduct problems. Journal of abnormal child psychology 43 (2015), 749–760.
  29. Sophie S. Havighurst and Christiane E. Kehoe. 2021. Tuning in to Kids: An Emotion Coaching Approach to Working with Parents. Cambridge University Press, 269–283. https://doi.org/10.1017/9781108682053.021
  30. Children and adolescents’ mental health following Covid-19: the possible role of difficulty in emotional regulation. Frontiers in Psychiatry 13 (2022), 865435.
  31. Toward integrating research on parent–child emotion talk and linguistic theory: A spotlight on parents’(in) direct communication. Social Development 30, 1 (2021), 38–56.
  32. Challenges in Building Intelligent Open-Domain Dialog Systems. ACM Trans. Inf. Syst. 38, 3, Article 21 (apr 2020), 32 pages. https://doi.org/10.1145/3383123
  33. Inflection AI. 2023. Pi, your personal AI. Retrieved Aug 25, 2023 from https://pi.ai/talk
  34. Dot’s World: An Emotional Development Support Platform for Children. In Proceedings of the 20th Annual ACM Interaction Design and Children Conference (Athens, Greece) (IDC ’21). Association for Computing Machinery, New York, NY, USA, 568–572. https://doi.org/10.1145/3459990.3465198
  35. What type of content are smartphone users addicted to?: SNS vs. games. Computers in human behavior 54 (2016), 10–17.
  36. Personallm: Investigating the ability of gpt-3.5 to express personality traits and gender differences. arXiv preprint arXiv:2305.02547 (2023).
  37. Understanding the Benefits and Challenges of Deploying Conversational AI Leveraging Large Language Models for Public Health Intervention. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI ’23). Association for Computing Machinery, New York, NY, USA, Article 18, 16 pages. https://doi.org/10.1145/3544548.3581503
  38. What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 3405–3424. https://doi.org/10.18653/v1/2021.emnlp-main.274
  39. Can a machine tend to teenagers’ emotional needs? A study with conversational agents. In Extended abstracts of the 2018 CHI conference on human factors in computing systems. 1–6.
  40. Data@Hand: Fostering Visual Exploration of Personal Data On Smartphones Leveraging Speech and Touch Interaction. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan) (CHI ’21). ACM, New York, NY, USA, Article 462, 17 pages. https://doi.org/10.1145/3411764.3445421
  41. Gender differences in the relationship between social communication and emotion recognition. Journal of the American Academy of Child & Adolescent Psychiatry 52, 11 (2013), 1148–1157.
  42. The chatbot feels you-a counseling service using emotional response generation. In 2017 IEEE international conference on big data and smart computing (BigComp). IEEE, 437–440.
  43. DAPIE: Interactive Step-by-Step Explanatory Dialogues to Answer Children’s Why and How Questions. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI ’23). Association for Computing Machinery, New York, NY, USA, Article 450, 22 pages. https://doi.org/10.1145/3544548.3581369
  44. Towards an online empathetic chatbot with emotion causes. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2041–2045.
  45. Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Comput. Surv. 55, 9, Article 195 (jan 2023), 35 pages. https://doi.org/10.1145/3560815
  46. Meta. 2023. React: The library for web and native user interfaces. Retrieved Aug 25, 2023 from https://react.dev
  47. Microsoft. 2023. TypeScript. Retrieved Aug 25, 2023 from https://www.typescriptlang.org
  48. A transdiagnostic, emotion regulation app (Eda) for children: design, development, and lessons learned. JMIR Formative Research 6, 1 (2022), e28300.
  49. A gamified app on emotion recognition and anger management for pre-school children. International Journal of Child-Computer Interaction 31 (2022), 100449.
  50. OpenAI. 2023a. ChatGPT: Optimizing Language Models for Dialogue. Retrieved Aug 25, 2023 from https://openai.com/blog/chatgpt/
  51. OpenAI. 2023b. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]
  52. OpenAI. 2023c. OpenAI API. Retrieved Aug 25, 2023 from https://openai.com/api/
  53. Samir Passi and Mihaela Vorvoreanu. 2022. Overreliance on AI Literature Review. Microsoft Research (2022).
  54. Susan Penza-Clyve and Janice Zeman. 2002. Initial validation of the emotion expression scale for children (EESC). Journal of Clinical Child and Adolescent Psychology 31, 4 (2002), 540–547.
  55. Motiis: Fostering Parents’ Awareness of Their Adolescents Emotional Experiences during Gaming. In Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society (Tallinn, Estonia) (NordiCHI ’20). Association for Computing Machinery, New York, NY, USA, Article 58, 11 pages. https://doi.org/10.1145/3419249.3420173
  56. Language Model Tokenizers Introduce Unfairness Between Languages. arXiv:2305.15425 [cs.CL]
  57. Jean Piaget and Margaret Cook. 1952. The origins of intelligence in children. Vol. 8. International Universities Press New York.
  58. Robert Plutchik. 1980. A general psychoevolutionary theory of emotion. In Theories of emotion. Elsevier, 3–33.
  59. Carolyn Saarni. 1999. The development of emotional competence. Guilford press.
  60. Carolyn Saarni. 2022. Emotional development in childhood. https://www.child-encyclopedia.com/emotions/according-experts/emotional-development-childhood
  61. Emotional development: Action, communication, and understanding. Handbook of child psychology 3 (2007).
  62. Therapist vibe: children’s expressions of their emotions through storytelling with a chatbot. In Proceedings of the interaction design and children conference. 483–494.
  63. Let’s Connect: A developmentally-driven emotion-focused parenting intervention. Journal of Applied Developmental Psychology 63 (2019), 33–41.
  64. LaMDA: Language Models for Dialog Applications. arXiv:2201.08239 [cs.CL]
  65. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL]
  66. Employing a Voice-Based Emotion-Recognition Function in a Social Chatbot to Foster Social and Emotional Learning Among Preschoolers. In International Conference on Human-Computer Interaction. Springer, 341–356.
  67. Lev S Vygotsky. 1978. Mind in society Harvard university press. Cambridge, MA (1978).
  68. Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data. arXiv:2301.05843 [cs.HC]
  69. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824–24837.
  70. Wes McKinney. 2010. Data Structures for Statistical Computing in Python. In Proceedings of the 9th Python in Science Conference, Stéfan van der Walt and Jarrod Millman (Eds.). 56 – 61. https://doi.org/10.25080/Majora-92bf1922-00a
  71. Terry Winograd. 1986. A Language/Action Perspective on the Design of Cooperative Work. In Proceedings of the 1986 ACM Conference on Computer-Supported Cooperative Work (Austin, Texas) (CSCW ’86). Association for Computing Machinery, New York, NY, USA, 203–220. https://doi.org/10.1145/637069.637096
  72. Getting To Know You: User Attribute Extraction from Dialogues. arXiv:1908.04621 [cs.CL]
  73. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (New Orleans, LA, USA) (CHI ’22). Association for Computing Machinery, New York, NY, USA, Article 385, 22 pages. https://doi.org/10.1145/3491102.3517582
  74. Deniz Yucel and Anastasia Vogt Yuan. 2015. Do siblings matter? The effect of siblings on socio-emotional development and educational aspirations among early adolescents. Child Indicators Research 8 (2015), 671–697.
  75. Janice Zeman and Judy Garber. 1996. Display rules for anger, sadness, and pain: It depends on who is watching. Child development 67, 3 (1996), 957–973.
  76. A Survey of Large Language Models. arXiv:2303.18223 [cs.CL]
  77. PAED: Zero-Shot Persona Attribute Extraction in Dialogues. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Toronto, Canada, 9771–9787. https://doi.org/10.18653/v1/2023.acl-long.544
Citations (16)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets