Technology Category
Natural Language Processing: Conversational AI/Dialog SystemsHumans and AI: Emotional IntelligenceCognitive Modeling & Cognitive Systems: Affective Computing
Creating, Using and Assessing a Generative-AI-Based Human-Chatbot-Dialogue Dataset with User-Interaction Learning Capabilities
🤖 AI Summary
To address inadequate human–AI dialogue adaptation in customer service scenarios, this paper proposes a controllable dialogue generation method jointly conditioned on user language proficiency and real-time emotional state. We construct a high-quality Chinese dialogue dataset using ChatGPT-3.5, covering multiple language proficiency levels and emotional states, with turn-level dialogue act annotations. Language complexity is quantified via metrics such as Flesch–Kincaid, while emotion consistency and interaction plausibility are validated through combined human and automated evaluation. To our knowledge, this is the first work to jointly model and control both dimensions for dialogue generation, enabling emotion-aware interaction pattern mining and user feedback learning. Experimental results demonstrate that the generated dialogues meet practical standards in linguistic adaptability, emotional coherence, and interaction reasonableness—establishing a learnable, evaluable, and structured foundation for adaptive customer service systems.
Technology Category
Application Category
📝 Abstract
The study illustrates a first step towards an ongoing work aimed at developing a dataset of dialogues potentially useful for customer service conversation management between humans and AI chatbots. The approach exploits ChatGPT 3.5 to generate dialogues. One of the requirements is that the dialogue is characterized by a specific language proficiency level of the user; the other one is that the user expresses a specific emotion during the interaction. The generated dialogues were then evaluated for overall quality. The complexity of the language used by both humans and AI agents, has been evaluated by using standard complexity measurements. Furthermore, the attitudes and interaction patterns exhibited by the chatbot at each turn have been stored for further detection of common conversation patterns in specific emotional contexts. The methodology could improve human-AI dialogue effectiveness and serve as a basis for systems that can learn from user interactions.
Problem
Research questions and friction points this paper is trying to address.
Human-AI Interaction
Customer Service
Natural Language Processing
Innovation
Methods, ideas, or system contributions that make the work stand out.
ChatGPT 3.5
Adaptive Dialogue Generation
Enhanced Human-AI Interaction
🔎 Similar Papers
No similar papers found.
