Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications

Natural Language Processing (NLP) has been recently extensively incorporated into industrial and domain applications. For example, NLP is used for speeding up processes, e.g., automation classification of types of customer feedback or filtering out spam emails, information extraction, e.g., named entity recognition to extract symptoms, diagnoses, and treatments from medical records, or auto-completing input forms with language models. Despite the broad integration, domain-specific NLP applications may require practicing more user-driven methodologies to address user needs with these applications. Often, the data-driven approach falls short in exploring the needs of the domain users (Yang, 2018). On the one hand, domain users are often integrated into development at the late test phase to evaluate the usability of ML/NLP applications (Carney, 2019). Unlike user-driven software development, the development of NLP applications depends mainly on data availability or experimenting with machine learning (ML)/NLP trends and thus is a major driver of application development. On the other hand, the user-driven development of a domain-specific ML/NLP application in medicine showed that close collaboration with the domain users in the earlier stages increases the effectiveness of the final product (Yang, 2017). Therefore, integrating user experience (UX) and human-computer interaction (HCI) research into ML/NLP research addresses users' needs, fuses their expertise, and increases intuitiveness, transparency, simplicity, and trust for the system users (Boukhelifa et al, 2018; Paleyes et al, 2022).