KIT | KIT-Bibliothek | Impressum | Datenschutz

Improving Explainability and Accuracy through Feature Engineering: A Taxonomy of Features in NLP-based Machine Learning

Wambsganss, Thiemo; Engel, Christian; Fromm, Hansjörg 1,2
1 Karlsruhe Service Research Institute (KSRI), Karlsruher Institut für Technologie (KIT)
2 Institut für Wirtschaftsinformatik (WIN), Karlsruher Institut für Technologie (KIT)

Abstract (englisch):

Natural Language Processing (NLP)-based machine learning receives continuous attention in Information System (IS) research and practice. Despite the success of deep learning models, NLP feature engineering still plays a vital role in contexts where only little annotated data is available, and in which explainability is a precondition for productive deployment. However, NLP feature engineering is a labor-intensive and time-consuming endeavor, and there is still limited shared knowledge about the distinctive characteristics of NLP features from an interdisciplinary perspective. To address this gap, we draw on a systematic literature review and develop a five-dimensional NLP feature taxonomy based on 133 unique features from 211 scientific studies. This helps IS researchers and practitioners to classify, compare, and evaluate their NLP studies. Moreover, we used cluster heat mapping analysis to derive three clusters and several white spots to provide further assistance for developing and designing new NLP solutions in IS.


Zugehörige Institution(en) am KIT Institut für Wirtschaftsinformatik (WIN)
Karlsruhe Service Research Institute (KSRI)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2024
Sprache Englisch
Identifikator ISBN: 978-171389360-8
KITopen-ID: 1000199296
Erschienen in Building sustainability and resilience wit IS: a call for action : International Conference on Information Systems (ICIS 2021) : Austin, Texas, USA, 12-15 December 2021. Vol.: 3
Veranstaltung 42nd International Conference on Information Systems (ICIS 2021), Austin, TX, USA, 12.12.2021 – 15.12.2021
Verlag AIS Electronic Library (AISeL)
Seiten 2006-2022
Serie ICIS 2021 Proceedings
Vorab online veröffentlicht am 25.10.2021
Externe Relationen Abstract/Volltext
Schlagwörter Natural Language Processing, Text Features, Clustering, Taxonomy
Nachgewiesen in Scopus
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page