EURO 2025 Leeds
Abstract Submission

2128. Digital Transformation Chatbot (DTchatbot): Integrating Large Language Model-based Chatbot in Acquiring Digital Transformation Needs

Invited abstract in session WA-41: Impact of AI on Soft OR, stream Soft OR and Problem Structuring Methods.

Wednesday, 8:30-10:00
Room: Newlyn GR.01

Authors (first author is the speaker)

1. Gorkem Yilmaz
Industrial Engineering, Izmir University of Economics
2. Jiawei Zheng
DigitLab, University of Exeter

Abstract

Digital transformation is a strategic imperative for organisations seeking to enhance operational efficiency, reduce manual efforts, and optimise processes by automation and digital tools. A critical challenge in this transformation lies in accurately capturing organisational needs, which traditionally relies on expert interviews. However, these methods often suffer from scheduling conflicts, recourse constraints, and inconsistency.

To address these issues, we propose a novel approach using a Large Language Model (LLM)-powered chatbot to elicit and understand digital transformation needs. Specifically, the chatbot integrates workflow-based instruction with LLM's planning capabilities, enabling it to function as a virtual expert and ask questions to users in the form of conversation in five key areas: corporate governance, customer and market management, research and development, supply chain, and production management. Moreover, the chatbot captures text and audio input in multiple languages, provides guidance on questions and technologies, and generates a comprehensive interview report.

Exploratory case studies with two Turkish manufacturing SMEs indicate that the chatbot effectively conducts conversational interviews, supports insightful user engagement, and helps initial awareness and identifying organisational needs. However, findings suggest that while it is effective for needs assessment, it needs enhanced analytical capabilities, e.g., suggesting solutions.

Keywords

Status: accepted

Back to the list of papers