Students and researchers regularly need to review and summarize the state-of-the-art of a given research direction for papers, proposals, or state-of-the-art reports. In a systematic review process, researchers parse all papers of a given set of digital libraries and include or reject papers for further consideration based on some more or less ill-defined criteria. From these papers, relevant information is extracted, categorized, and summarized according to the aspects relevant for the given research. The selection, categorization, and summarization processes are mostly done manually, as there is no sufficient tool support to at least partially automatize them.
The goal of this work is to design and implement a prototype for state-of-the-art research tool that automatically queries digital libraries based on given meta-data criteria (e.g., journals, time periods) and a set of keywords. To help the user select relevant content and categorize it, the tool should provide a smart interface using supervised machine learning that gradually learns what aspects the user is interested in and recommends suitable text fragments that fit these categories.
This project can be implemented as web service or as desktop application, depending on the student’s interests and prior experiences. We recommend to use Python for natural language processing and machine learning.