Automated Classification of SAP Literature: Predicting Impact and Trends

Abstract

The rapid evolution of business systems such as SAP (Systems, Applications, and Products in Data Processing) has generated a growing body of research on implementations, innovations, and business impacts. Determining high-impact papers and detecting emerging trends remains challenging due to the volume of literature. This study presents a machine learning powered pipeline for collecting, pre-processing, and classifying SAP-related research articles retrieved from Semantic Scholar. The pipeline employs natural language processing techniques, including text cleaning, lemmatization, and SciBERT embeddings, to generate richer feature representations, along with metadata features such as vocabulary diversity, novelty score, paper age, and citation velocity. To analyse research impact and trends, we trained a set of classical machine learning models, Random Forest, XGBoost, and LightGBM, and a set of large language models (LLMs), BERT, RoBERTa, and ELECTRA, fine-tuned for classification. The LLMs demonstrated superior performance compared to classical models, achieving accuracies of approximately 93% to 97% for impact classification and 96% to 97% for trend categorization. The models classify papers along two key dimensions: impact classification (High Impact, Niche, Low Impact) and trend categorization (Hot Trend, Recent Classic, Established, Historic), defined using proxy-based bibliometric indicators. This contribution provides an automated framework for literature analysis in the SAP context, enabling researchers and practitioners to identify high-impact studies and support the identification of emerging research directions.