Abstract
Generative AI tools, exemplified by ChatGPT, are transforming the way users interact with information by enabling dialogue-based querying instead of traditional keyword searches. While this conversational approach can simplify user interactions, it also presents challenges in structuring effective searches, refining prompts, and verifying AI-generated content. This study addresses these complexities by repurposing traditional search tactics for use in conversational AI environments, specifically to support the Searching as Learning (SaL) paradigm. Forty-five adapted tactics are introduced to aid users in defining information needs, refining queries, and evaluating ChatGPT's responses for relevance, utility, and reliability. Using the Efficient Search Tactic Identification (ESTI) method and constant comparison analysis, these tactics were mapped into a stratified model with seven categories. The framework provides a structured approach for users to leverage conversational agents more effectively, promoting critical thinking and iterative learning. This research underscores the importance of developing robust search strategies tailored to conversational AI environments, facilitating deeper learning and reflective information engagement. Additionally, it highlights the need for ongoing research into the design and evaluation of future chat-and-search systems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callSimilar Papers
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
