Aspect-based sentiment analysis: an overview in the use of Arabic language

被引:16
|
作者
Bensoltane, Rajae [1 ]
Zaki, Taher [1 ]
机构
[1] Ibn Zohr Univ, Fac Sci, IRF SIC Lab, Agadir, FP, Morocco
关键词
Natural language processing; Sentiment analysis; Aspect-based; Aspect extraction; Aspect sentiment classification; Arabic language; DEEP LEARNING-MODEL; NEURAL-NETWORK; TWEETS; COMBINATION; EXTRACTION; ATTENTION; MACHINE; SET;
D O I
10.1007/s10462-022-10215-3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sentiment analysis has become one of the most active research areas in natural language processing, and the Arabic language retains its importance in this field. It is so because of the increased use of Arabic on the internet that pushes many users to share their views or thoughts about certain products and services. Despite its crucial importance, most of the existing Arabic sentiment analysis studies have been performed on document or sentence levels with little attention to the aspect level. However, the aspect level's main objective, also known as aspect-based sentiment analysis, is to extract the discussed aspects and identify their related sentiment polarities from a given review or text. The result is to provide more detailed information than general sentiment analysis. Therefore, this paper seeks to provide a comprehensive review of the Arabic aspect-based sentiment analysis studies and highlights the main challenges that face the different proposed approaches. The relevant gaps in the current literature and the future research directions in this area are also discussed. This survey can guide future researchers who want to contribute to the improvement of this domain.
引用
收藏
页码:2325 / 2363
页数:39
相关论文
共 50 条
  • [21] Aspect-Based Sentiment Analysis for User Reviews
    Du, Jinyang
    Zhang, Yin
    Ma, Xiao
    Wen, Haoyu
    Fortino, Giancarlo
    COGNITIVE COMPUTATION, 2021, 13 (05) : 1114 - 1127
  • [22] Gated recurrent unit with multilingual universal sentence encoder for Arabic aspect-based sentiment analysis
    AL-Smadi, Mohammad
    Hammad, Mahmoud M.
    Al-Zboon, Sa'ad A.
    AL-Tawalbeh, Saja
    Cambria, Erik
    KNOWLEDGE-BASED SYSTEMS, 2023, 261
  • [23] Autoregressive Feature Extraction with Topic Modeling for Aspect-based Sentiment Analysis of Arabic as a Low-resource Language
    Sweidan, Asmaa Hashem
    El-Bendary, Nashwa
    Elhariri, Esraa
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2024, 23 (02)
  • [24] AraMAMS: Arabic Multi-Aspect, Multi-Sentiment Restaurants Reviews Corpus for Aspect-Based Sentiment Analysis
    AlMasaud, Alanod
    Al-Baity, Heyam H.
    SUSTAINABILITY, 2023, 15 (16)
  • [25] Survey on aspect detection for aspect-based sentiment analysis
    Trusca, Maria Mihaela
    Frasincar, Flavius
    ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (05) : 3797 - 3846
  • [26] A systematic review and research contributions on aspect-based sentiment analysis using twitter data
    Preetha, N. S. Ninu
    Brammya, G.
    Majumder, Mahbub Arab
    Nagarajan, M. K.
    Therasa, M.
    INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS, 2023, 17 (04): : 1061 - 1083
  • [27] Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis
    Mughal, Nimra
    Mujtaba, Ghulam
    Shaikh, Sarang
    Kumar, Aveenash
    Daudpota, Sher Muhammad
    IEEE ACCESS, 2024, 12 : 60943 - 60959
  • [28] Aspect-based sentiment analysis in Urdu language: resource creation and evaluation
    Altaf, Amna
    Anwar, Muhammad Waqas
    Jamal, Muhammad Hasan
    Bajwa, Usama Ijaz
    Rani, Sadaf
    Neural Computing and Applications, 2024, 36 (34) : 21365 - 21381
  • [29] Ensemble Deep Learning for Aspect-based Sentiment Analysis
    Mohammadi, Azadeh
    Shaverizade, Anis
    INTERNATIONAL JOURNAL OF NONLINEAR ANALYSIS AND APPLICATIONS, 2021, 12 : 29 - 38
  • [30] Aspect-based sentiment analysis using smart government review data
    Alqaryouti, Omar
    Siyam, Nur
    Monem, Azza Abdel
    Shaalan, Khaled
    APPLIED COMPUTING AND INFORMATICS, 2024, 20 (1/2) : 142 - 161