A systematic mapping study of the empirical explicit aspect extractions in sentiment analysis

Maitama, Jaafar Zubairu and Idris, Norisma and Zakari, Abubakar (2020) A systematic mapping study of the empirical explicit aspect extractions in sentiment analysis. IEEE Access, 8. pp. 113878-113899. ISSN 2169-3536, DOI https://doi.org/10.1109/ACCESS.2020.3003625.

Full text not available from this repository.


Aspect-based sentiment analysis (ABSA) is described as one of the most vibrant research areas over the last decade. However, due to the exponential increase in aspect-based sentiment researches, there is a massive interest in advanced explicit aspect extraction (EAE) techniques. This interest brings about a huge amount of literature in the EAE domain. This study aims to investigate and identify the existing approaches, techniques, types of research, quantity of publications, publication trends and demographics shaping the EAE research domain in the last decade (2009 - 2019). Accordingly, an evidence-based systematic methodology was adopted to effectively capture all the relevant studies. The main findings revealed that, 1) there is considerable and continuous rise of EAE research activities around different parts of the globe in the last five years, particularly Asia, Middle-East, and European countries; 2) EAE research has been very limited among African countries which need to be addressed due its role on business intelligence as well as semantic values; 3) three research facets were highlighted based on this study, i.e. solution research, validation research, and evaluation research, in which solution research gets the highest attention; and finally 4) the EAE challenges, as well as feasible future recommendations, were highlighted in this study.

Item Type: Article
Funders: Universiti Malaya (GPF007D-2018)
Uncontrolled Keywords: Aspect-based sentiment analysis; Aspect detection; aspect extraction; Explicit aspect; Feature extraction
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Computer Science & Information Technology > Department of Artificial Intelligence
Depositing User: Ms Zaharah Ramly
Date Deposited: 31 May 2023 03:19
Last Modified: 31 May 2023 03:19
URI: http://eprints.um.edu.my/id/eprint/37099

Actions (login required)

View Item View Item