Research Article
A Roadmap for Composing Automatic Literature Reviews: A Text Mining Approach
@INPROCEEDINGS{10.1007/978-3-030-77417-2_17, author={Eug\"{e}nio Monteiro da Silva J\^{u}nior and Mois\^{e}s Lima Dutra}, title={A Roadmap for Composing Automatic Literature Reviews: A Text Mining Approach}, proceedings={Data and Information in Online Environments. Second EAI International Conference, DIONE 2021, Virtual Event, March 10--12, 2021, Proceedings}, proceedings_a={DIONE}, year={2021}, month={6}, keywords={Systematic review Text mining Automation}, doi={10.1007/978-3-030-77417-2_17} }- Eugênio Monteiro da Silva Júnior
Moisés Lima Dutra
Year: 2021
A Roadmap for Composing Automatic Literature Reviews: A Text Mining Approach
DIONE
Springer
DOI: 10.1007/978-3-030-77417-2_17
Abstract
Due to accelerated growth in the number of scientific papers, writing literature reviews has become an increasingly costly activity. Therefore, the search for computational tools to assist in this process has been gaining ground in recent years. This work presents an overview of the current scenario of development of artificial intelligence tools aimed to assist in the production of systematic literature reviews. The process of creating a literature review is both creative and technical. The technical part of this process is liable to automation. For the purpose of organization, we divide this technical part into four steps: searching, screening, extraction, and synthesis. For each of these steps, we present artificial intelligence techniques that can be useful to its realization. In addition, we also present the obstacles encountered for the application of each technique. Finally, we propose a pipeline for the automatic creation of systematic literature reviews, by combining and placing existing techniques in stages where they possess the greatest potential to be useful.
