The present master thesis examines a researcher’s challenge in searching and screening literature reviews as a basis for research papers. The process of a literature review conduct is a time intensive task and the amount and availability of literature is rising constantly. The aim of a literature review is to develop a scientific basis for a research field as well as the determination of a precisely defined research objective. The present paper develops NLP based workflows in KNIME by which literature documents are processed efficiently and effectively to generate knowledge about the topic, open research fields, relationships and further insights to reduce the amount of time of the literature review process for researchers. Numerous NLP based applications are available on the market. Such applications support researchers in managing and distilling literature reviews. This research paper examines several conducted research analyses which are based on NLP processes. However, the current applications, algorithms and methods are limited either to specific literature bases, expert users or selected NLP tasks. Therefore, the aim of the present thesis is to build AI based NLP workflows with modular functionalities which are usable for beginners in data science, covering relevant NLP methods and are versatile in application to support students with the conduct of a literature review. The goal of the workflows is to provide hints of the researched topic and of current and future research fields, related topics and sentiments.