Few-shot Approach for Systematic Literature Review Classifications

Maísa Kely de Melo, Maísa Kely de Melo, Allan Faria, Allan Faria, Li Weigang, Li Weigang, Arthur Nery, Arthur Nery, Flávio R. de Oliveira, Flávio R. de Oliveira, Ian Barreiro, Ian Barreiro, Victor Celestino, Victor Celestino

2022

Abstract

Systematic Literature Review (SLR) studies aim to leverage relevant insights from scientific publications to achieve a comprehensive overview of the academic progress of a specific field. In recent years, a major effort has been expended in automating the SLR process by extracting, processing, and presenting the synthesized findings. However, implementations capable of few-shot classification for fields of study with a smaller amount of material available seem to be lacking. This study aims to present a system capable of conducting automated systematic literature reviews on classification constraint by a few-shot learning. We propose an open-source, domain-agnostic meta-learning SLR framework for few-shot classification, which has been validated using 64 SLR datasets. We also define an Adjusted Work Saved over Sampling (AWSS) metric to take into account the class imbalance during validation. The initial results show that AWSS@95% scored as high as 0.9 when validating our learner with data from 32 domains (just 16 examples were used for training in each domain), and only four of them resulted in scores lower than 0.1. These findings indicate significant savings in screening time for literature reviewers.

Paper Citation

in Harvard Style

Kely de Melo M., Faria A., Weigang L., Nery A., R. de Oliveira F., Barreiro I. and Celestino V. (2022). Few-shot Approach for Systematic Literature Review Classifications. In Proceedings of the 18th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-613-2, pages 33-44. DOI: 10.5220/0011526400003318

in Bibtex Style

@conference{webist22,
author={Maísa Kely de Melo and Allan Faria and Li Weigang and Arthur Nery and Flávio R. de Oliveira and Ian Barreiro and Victor Celestino},
title={Few-shot Approach for Systematic Literature Review Classifications},
booktitle={Proceedings of the 18th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2022},
pages={33-44},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011526400003318},
isbn={978-989-758-613-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Few-shot Approach for Systematic Literature Review Classifications
SN - 978-989-758-613-2
AU - Kely de Melo M.
AU - Faria A.
AU - Weigang L.
AU - Nery A.
AU - R. de Oliveira F.
AU - Barreiro I.
AU - Celestino V.
PY - 2022
SP - 33
EP - 44
DO - 10.5220/0011526400003318