Artificial Intelligence (AI), once exclusive to sophisticated technological spheres, now plays a transformative role across all aspects of society, driving significant progress and innovation. In this backdrop, basic conversational interface aka chat emerged as the easiest, and the simplest way to interact with AI systems. However, the current Human-AI conversations are fraught with a host of challenges necessitating a critical exploration into their design, approach, and implications. As AI technologies continue to permeate our lives, the need for seamless, intuitive, and human-like conversations is amplified. While our larger research embarks on a research study to suggest a conceptual framework to help design more effective and engaging Human-AI conversations, this paper focuses on a critical aspect that surfaced as a primary gap during our literature review. Conversations are effective and engaging only when their fundamental purpose is identified and understood by their participants. Hence, formulating a purpose driven conversational typology emerged as a key design imperative to inform an array of frameworks that could help create meaningful Human-AI conversations. This study evaluates a dataset of over hundred Human-AI and Human-to-Human conversations, proposing twelve conversational archetypes central to a conceptual framework intended to enhance Human-AI conversations. Employing a hybrid methodology that integrates content analysis with case study research, this paper examines the issue from a human perspective. It aims to provide a useful resource for designers, developers, researchers, and industry professionals who seek to foster deeper connections and trust in human-AI interactions.
Read full abstract