Skip to Main content Skip to Navigation
Conference papers

Leveraging Conversational Systems to Assists New Hires During Onboarding

Abstract : The task of onboarding a new hire consumes great amounts of resources from organizations. The faster a “newbie” becomes an “insider”, the higher the chances of job satisfaction, retention, and advancement in their position. Conversational agents (AI agents) have the potential to effectively transform productivity in many enterprise workplace scenarios so applying them to the onboarding process can prove to be a very solid use case for such agents. In this work, we present a conversational system to aid new hires through their onboarding process. Users interact with the system via an instant messaging platform, to fulfill their work related information needs as if it were a human assistant. We describe the end-to-end process involved in building a domain specific conversational system and share our experiences in deploying it to 344 new hires in a month-long study. The feasibility of our approach is evaluated by analyzing message logs and questionnaires. Through three different measures, we observed an accuracy of about 60% at the message level and a higher than average retention rate for the agent. Our results suggest that this agent-based approach can very well compete with the existing tools for new hires.
Document type :
Conference papers
Complete list of metadata

Cited literature [29 references]  Display  Hide  Download
Contributor : Hal Ifip <>
Submitted on : Tuesday, January 9, 2018 - 11:16:51 AM
Last modification on : Tuesday, January 9, 2018 - 11:19:06 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Praveen Chandar, Yasaman Khazaeni, Matthew Davis, Michael Muller, Marco Crasso, et al.. Leveraging Conversational Systems to Assists New Hires During Onboarding. 16th IFIP Conference on Human-Computer Interaction (INTERACT), Sep 2017, Bombay, India. pp.381-391, ⟨10.1007/978-3-319-67684-5_23⟩. ⟨hal-01678485⟩



Record views


Files downloads