Treffer: Improve issue-handling efficiency in government QA systems: an automatic issue classification and distribution system.

Question-answering (QA) systems are vital for organizations to efficiently address customers' issues. Nevertheless, studies on QA systems in government are still lacking. Government QA systems face significant optimization challenges, including long response times, issue accumulation, and ineffective prioritization. This study develops an AI-driven system that leverages advanced BERT-based models to automatically classify issues, predict key attributes, and distribute them to appropriate departments using a novel matching algorithm. Trained on 812,322 citizens' inquiries from Messaging Borad for Leaders in China, our proposed system significantly reduces response times, minimizes uneven issue distribution, and decreases manual work and costs. The BERT-based models improve issue classification and attribute prediction accuracy by 5%–10% compared to baselines, while effectively reducing departmental overload. This study contributes to both organizational efficiency and New Public Management (NPM) literature by demonstrating how the government QA system's efficiency and service quality can be improved with the assistance of AI. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Management Analytics is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)