Effects of Emotional Expressiveness on Voice Chatbot Interactions

Zhu, Qingxiaoyang; Chau, Austin; Cohn, Michelle; Liang, Kai-Hui; Wang, Hao-Chuan; Zellou, Georgia; Yu, Zhou

doi:10.1145/3543829.3543840

Cited by 7 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three main types of AI-powered tools were used and analysed within the selected sample of papers. The most dominant group of papers (N=9) comprised studies based using learning apps with AI-powered modules including a chatbot (Citrayasa, 2019;Chuyen., Linh & Phuc, 2021, El Shazly, 2021Sumakul, Hamied & Sukyadi, 2022;Zhu et al, 2022, Annamalai et al, 2023Isbell, Crowther & Nishizawa, 2023;Khampusaen, Chanprasopchai, & Lao-un, 2023;Zou et al 2023).…”

Section: Ai-powered Tools Used and Observedmentioning

confidence: 99%

“…However, the difference in pronouncing longer words was detected when shadowing the human speaker. Another study focusing on including prosody in chatbots and the consequent responses of their users was carried out by Zhu et al (2022). The authors predicted that more emotional expressions would increase positive perceptions of chatbots.…”

Section: Framework For Using Ai-powered Tools In Pronunciation Trainingmentioning

confidence: 99%

See 1 more Smart Citation

AI and AI-powered tools for pronunciation training

Vančová

2023

Journal of Language and Cultural Education

View full text Add to dashboard Cite

Artificial intelligence (AI) is taking over many spheres of human life, including language pedagogy. While some areas need to find their ground with AI and resolve ethical issues arising from its use, other spheres of education, such as pronunciation, may benefit from the system’s ability to communicate with learners and provide them with implicit feedback while carrying out different communication tasks. This technical advancement of AI then opens doors for further educational opportunities that have not existed in the past. The study aims to explore the existing use of AI-powered tools in foreign language pronunciation training by meta-analysis of 15 research papers benefiting from using AI and AI-powered tools (mobile and web applications, chatbots, intelligent virtual assistants) and provide suggestions for their future applications in educational practice. The research results also indicate that this field of study is still underrepresented in language pedagogy. The existing experience with AI-powered tools confirms a relatively good experience in developing intelligibility, increasing motivation and addressing the speaking anxiety of foreign language learners in formal and informal learning settings.

show abstract

Section: Ai-powered Tools Used and Observedmentioning

confidence: 99%

Section: Framework For Using Ai-powered Tools In Pronunciation Trainingmentioning

confidence: 99%

AI and AI-powered tools for pronunciation training

Vančová

2023

Journal of Language and Cultural Education

View full text Add to dashboard Cite

show abstract

Towards a general user model to develop intelligent user interfaces

Gaspar,

Gil,

Panach

et al. 2024

Multimed Tools Appl

View full text Add to dashboard Cite

The way end-users interact with a system plays a crucial role in the high acceptance of software. Related to this, the concept of Intelligent User Interfaces has emerged as a solution to learn from user interactions with the system and adapt interfaces to the user’s characteristics and preferences. However, existing approaches to designing intelligent user interfaces are limited by their user models, which are not capable of representing each and every user characteristic valid for any context. This work aims to address this limitation by presenting a user model that can abstractly represent a wide set of user characteristics in any context of interaction. The model is based on a synthesis of previous works that have proposed specific user models. After the analysis of these works, a more sophisticated user model has been defined, including some required characteristics not existing in previous works. This model has been validated with 62 real end-users who have expressed the users’ characteristics that they consider as relevant to adapt the interaction. The results show that most of these characteristics can be represented by the proposed user model. This user model is the first step towards creating intelligent user interfaces that can adapt interactions to users with similar characteristics and preferences in similar contexts.

show abstract