ABSTRACT
Cognitive augmentation is the process of enhancing one’s abilities, including learning a new language. For this, we could utilize conversational chatbots. Conventional chatbots such as Siri, have predominantly been based on the question-and-answer model, where a communicator seeks a specific answer to accomplish a specific task. The conversational capabilities of chatbots offer great potential to promote English language learning, particularly in developing countries, such as Sri Lanka, where many young adults lack confidence in speaking English. This is due to limited exposure to conversational-style learning and a lack of opportunity to practice without social anxiety which is often rooted in the fear of making mistakes. In this paper, we developed a conversational chatbot, Kavy, as a companion to help them practice English. We investigated, in a study with 40 users, if Kavy could improve a communicator’s proficiency (e.g., verbal expression, conversation length, quality of speech) and self-confidence using both poetic and non-poetic conversational styles. We found that the users were highly motivated by the poetic version, with its use resulting in a significant increase in vocabulary. Nevertheless, a poetic chatbot may present challenges, with several users reporting that they find the poetic version confusing. We see this pioneering work as a first and promising approach that should be continued to be investigated in the future.
- Franziska Braun, Lukas Block, and Sebastian Stegmüller. 2021. Josy: Development of a Digital Companion for Elderly People–A New Way to Experience Technology. In Advances in Human Factors and Ergonomics in Healthcare and Medical Devices: Proceedings of the AHFE 2021 Virtual Conference on Human Factors and Ergonomics in Healthcare and Medical Devices, July 25-29, 2021, USA. Springer, 436–442.Google ScholarCross Ref
- Camille Cronin and Caroline Hawthorne. 2019. ‘Poetry in motion’a place in the classroom: Using poetry to develop writing confidence and reflective skills. Nurse education today 76 (2019), 73–77.Google Scholar
- Alice Dai. 2021. GPT-2 for Emily Dickinson poetry generation.Google Scholar
- Annette MB De Groot and Janet G Van Hell. 2005. The learning of foreign language vocabulary. Handbook of bilingualism: Psycholinguistic approaches (2005), 9–29.Google Scholar
- Lyra D’Souza and David Mimno. 2023. The Chatbot and the Canon: Poetry Memorization in LLMs. Proceedings http://ceur-ws. org ISSN 1613 (2023), 0073.Google Scholar
- Douglas C Engelbart. 2023. Augmenting human intellect: A conceptual framework. In Augmented Education in the Global Age. Routledge, 13–29.Google Scholar
- James Paul Gee. 2003. What video games have to teach us about learning and literacy. Computers in entertainment (CIE) 1, 1 (2003), 20–20.Google ScholarDigital Library
- Geoff Hart. [n. d.]. Ten design principles and when to violate them. ([n. d.]).Google Scholar
- TUNEL Hayrettin. 2015. The relationship between self-confidence and learning Turkish as a foreign language. Educational research and reviews 10, 18 (2015), 2575–2589.Google Scholar
- AR Kirmani. 2022. Artificial intelligence-enabled science poetry, ACS Energy Letters, 8, 574-576.Google ScholarCross Ref
- Raph Koster. 2013. Theory of fun for game design. " O’Reilly Media, Inc.".Google ScholarDigital Library
- Steve Krug 2014. Don’t make me think, Revisited. A Common Sense Approach to Web and Mobile Usability (2014).Google Scholar
- An H Kuppens. 2010. Incidental foreign language acquisition from media exposure. Learning, media and technology 35, 1 (2010), 65–85.Google Scholar
- Xixi Li, JJ Po-An Hsieh, and Arun Rai. 2013. Motivational differences across post-acceptance information system usage behaviors: An investigation in the business intelligence systems context. Information systems research 24, 3 (2013), 659–682.Google Scholar
- Thomas W Malone and Mark R Lepper. 2021. Making learning fun: A taxonomy of intrinsic motivations for learning. In Aptitude, learning, and instruction. Routledge, 223–254.Google Scholar
- Nicole Mills, Frank Pajares, and Carol Herron. 2006. A reevaluation of the role of anxiety: Self-efficacy, anxiety, and their relation to reading and listening proficiency. Foreign language annals 39, 2 (2006), 276–295.Google Scholar
- Don Norman. 2013. The design of everyday things: Revised and expanded edition. Basic books.Google Scholar
- Marc Prensky. 2003. Digital game-based learning. Computers in Entertainment (CIE) 1, 1 (2003), 21–21.Google ScholarDigital Library
- Sharina Saad, Rafidah Amat, Razanawati Nordin, Asrol Hasan, and Alia Nabella Fateha Zolkifli. 2023. From poetry out loud to thinking out loud: The ESL students’ experience. Social and Management Research Journal (SMRJ) 20, 2 (2023), 153–164.Google Scholar
- Sharina Saad, Rafidah Amat, Razanawati Nordin, Asrol Hasan, and Alia Nabella Fateha Zolkifli. 2023. Poetry out loud: fostering ESL learners public speaking skill. (2023).Google Scholar
- Piotr Sawicki, Marek Grzes, Fabricio Goes, Dan Brown, and Max Peeperkorn. [n. d.]. Khatun, Aisha (2023) Bits of Grass: Does GPT already know how to write like Whitman? Proceedings of the 14th International Conference for Computational Creativity.(In press). ([n. d.]).Google Scholar
- Sara Törnqvist. 2019. Speaking through poetry-Using spoken word poetry to lower speaking anxiety among Swedish EFL learners.Google Scholar
- Stefano Valtolina and Liliana Hu. 2021. Charlie: A chatbot to improve the elderly quality of life and to make them more active to fight their sense of loneliness. In CHItaly 2021: 14th Biannual Conference of the Italian SIGCHI Chapter. 1–5.Google Scholar
- Yangjian Wu and Gang Hu. 2023. Exploring Prompt Engineering with GPT Language Models for Document-Level Machine Translation: Insights and Findings. In Proceedings of the Eighth Conference on Machine Translation. 166–169.Google ScholarCross Ref
- Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2020. The design and implementation of xiaoice, an empathetic social chatbot. Computational Linguistics 46, 1 (2020), 53–93.Google ScholarDigital Library
Index Terms
- Kavy: Fostering Language Speaking Skills and Self-Confidence Through Conversational AI
Recommendations
An End-to-End Conversational Style Matching Agent
IVA '19: Proceedings of the 19th ACM International Conference on Intelligent Virtual AgentsWe present an end-to-end voice-based conversational agent that is able to engage in naturalistic multi-turn dialogue and align with the interlocutor's conversational style. The system uses a series of deep neural network components for speech ...
Speaking more like you: lexical, acoustic/prosodic, and discourse entrainment in spoken dialogue systems
SIGdial '08: Proceedings of the 9th SIGdial Workshop on Discourse and DialogueWhen people engage in conversation, they adapt the way they speak to the speaking style of their conversational partner in a variety of ways. For example, they may adopt a certain way of describing something based upon the way their conversational ...
Investigating Proactive Search Support in Conversations
DIS '18: Proceedings of the 2018 Designing Interactive Systems ConferenceConversations among people involve solving disputes, building common ground, and reinforce mutual beliefs and assumptions. Conversations often require external information that can support these human activities. In this paper, we study how a spoken ...
Comments