PMID- 37346563
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20230626
IS  - 2376-5992 (Electronic)
IS  - 2376-5992 (Linking)
VI  - 9
DP  - 2023
TI  - A semi supervised approach to Arabic aspect category detection using Bert and 
      teacher-student model.
PG  - e1425
LID - 10.7717/peerj-cs.1425 [doi]
LID - e1425
AB  - Aspect-based sentiment analysis tasks are well researched in English. However, we 
      find such research lacking in the context of the Arabic language, especially with 
      reference to aspect category detection. Most of this research is focusing on 
      supervised machine learning methods that require the use of large, labeled 
      datasets. Therefore, the aim of this research is to implement a semi-supervised 
      self-training approach which utilizes a noisy student framework to enhance the 
      capability of a deep learning model, AraBERT v02. The objective is to perform 
      aspect category detection on both the SemEval 2016 hotel review dataset and the 
      Hotel Arabic-Reviews Dataset (HARD) 2016. The four-step framework firstly entails 
      developing a teacher model that is trained on the aspect categories of the 
      SemEval 2016 labeled dataset. Secondly, it generates pseudo labels for the 
      unlabeled HARD dataset based on the teacher model. Thirdly, it creates a noisy 
      student model that is trained on the combined datasets ( approximately 1 million sentences). 
      The aim is to minimize the combined cross entropy loss. Fourthly, an ensembling 
      of both teacher and student models is carried out to enhance the performance of 
      AraBERT. Findings indicate that the ensembled teacher-student model demonstrates 
      a 0.3% improvement in its micro F1 over the initial noisy student implementation, 
      both in predicting the Aspect Categories in the combined datasets. However, it 
      has achieved a 1% increase over the micro F1 of the teacher model. These results 
      outperform both baselines and other deep learning models discussed in the related 
      literature.
CI  - (c)2023 Almasri et al.
FAU - Almasri, Miada
AU  - Almasri M
AD  - Information Technology Department/Faculty of Computing and Information 
      Technology, King Abdulaziz University, Jeddah, Saudi Arabia.
FAU - Al-Malki, Norah
AU  - Al-Malki N
AD  - European Languages Department/Faculty of Arts and Humanities, King Abdulaziz 
      University, Jeddah, Saudi Arabia.
FAU - Alotaibi, Reem
AU  - Alotaibi R
AD  - Information Technology Department/Faculty of Computing and Information 
      Technology, King Abdulaziz University, Jeddah, Saudi Arabia.
LA  - eng
PT  - Journal Article
DEP - 20230608
PL  - United States
TA  - PeerJ Comput Sci
JT  - PeerJ. Computer science
JID - 101660598
PMC - PMC10280399
OTO - NOTNLM
OT  - AraBERT
OT  - Aspect Category Detection
OT  - BERT
OT  - Noisy Student model
OT  - Sentiment Analysis
OT  - Teacher model
OT  - Transformer
COIS- The authors declare there are no competing interests.
EDAT- 2023/06/22 13:09
MHDA- 2023/06/22 13:10
PMCR- 2023/06/08
CRDT- 2023/06/22 09:53
PHST- 2022/12/23 00:00 [received]
PHST- 2023/05/12 00:00 [accepted]
PHST- 2023/06/22 13:10 [medline]
PHST- 2023/06/22 13:09 [pubmed]
PHST- 2023/06/22 09:53 [entrez]
PHST- 2023/06/08 00:00 [pmc-release]
AID - cs-1425 [pii]
AID - 10.7717/peerj-cs.1425 [doi]
PST - epublish
SO  - PeerJ Comput Sci. 2023 Jun 8;9:e1425. doi: 10.7717/peerj-cs.1425. eCollection 
      2023.