Improving The Efficiency of Aspect-Based Sentiment Analysis Using Ensemble Deep Learning.
Keywords:
Sentiment, aspect, entity, classification, machine learningAbstract
Aspect-Based Sentiment Analysis (ABSA) is a specialized subfield of sentiment analysis that incorporates named entity recognition (NER), entity-sentence identification, and sentiment analysis. Executing each of these tasks requires the application of sophisticated language processing algorithms. For instance, NER typically employs a combination of linguistic heuristics and machine learning models, such as Hidden Markov Models (HMMs) or Support Vector Machines (SVMs), to discern aspects within an input sentence. Similarly, identifying sentences relevant to a given aspect or entity demands intricate ontology graph methodologies. Given the complex nature of these processing stages, it is imperative to utilize high-accuracy algorithms. This paper presents an advanced ABSA system that merges an ensemble sentiment analyzer with a convolutional neural network (CNN) for entity and entity-sentence identification. The proposed algorithm employs the VGGNet architecture, augmented by a dynamic ontology graph, to enhance the precision of entity and entity-sentence identification. Subsequently, an ensemble sentiment analyzer is introduced, integrating outputs from four distinct sentiment analyzers to boost the overall system's accuracy levels. Evaluation of the proposed algorithm on multiple datasets demonstrates its superior performance in comparison to contemporary state-of-the-art systems. In particular, the algorithm exhibits a 9% improvement in classification accuracy on a restaurant dataset, along with 10% and 14% accuracy enhancements on laptop and Twitter datasets & samples.
Downloads
References
R. Obiedat, D. Al-Darras, E. Alzaghoul and O. Harfoushi, "Arabic Aspect-Based Sentiment Analysis: A Systematic Literature Review," in IEEE Access, vol. 9, pp. 152628-152645, 2021, doi: 10.1109/ACCESS.2021.3127140.
Y. Bie and Y. Yang, "A multitask multiview neural network for end-to-end aspect-based sentiment analysis," in Big Data Mining and Analytics, vol. 4, no. 3, pp. 195-207, Sept. 2021, doi: 10.26599/BDMA.2021.9020003.
Q. Yang, Z. Kadeer, W. Gu, W. Sun and A. Wumaier, "Affective Knowledge Augmented Interactive Graph Convolutional Network for Chinese-Oriented Aspect-Based Sentiment Analysis," in IEEE Access, vol. 10, pp. 130686-130698, 2022, doi: 10.1109/ACCESS.2022.3228299.
J. He, A. Wumaier, Z. Kadeer, W. Sun, X. Xin and L. Zheng, "A Local and Global Context Focus Multilingual Learning Model for Aspect-Based Sentiment Analysis," in IEEE Access, vol. 10, pp. 84135-84146, 2022, doi: 10.1109/ACCESS.2022.3197218.
T. Lin and I. Joe, "An Adaptive Masked Attention Mechanism to Act on the Local Text in a Global Context for Aspect-Based Sentiment Analysis," in IEEE Access, vol. 11, pp. 43055-43066, 2023, doi: 10.1109/ACCESS.2023.3270927.
A. Nazir, Y. Rao, L. Wu and L. Sun, "Issues and Challenges of Aspect-based Sentiment Analysis: A Comprehensive Survey," in IEEE Transactions on Affective Computing, vol. 13, no. 2, pp. 845-863, 1 April-June 2022, doi: 10.1109/TAFFC.2020.2970399.
W. An, F. Tian, P. Chen and Q. Zheng, "Aspect-Based Sentiment Analysis With Heterogeneous Graph Neural Network," in IEEE Transactions on Computational Social Systems, vol. 10, no. 1, pp. 403-412, Feb. 2023, doi: 10.1109/TCSS.2022.3148866.
W. Ahmad, H. U. Khan, T. Iqbal and S. Iqbal, "Attention-Based Multi-Channel Gated Recurrent Neural Networks: A Novel Feature-Centric Approach for Aspect-Based Sentiment Classification," in IEEE Access, vol. 11, pp. 54408-54427, 2023, doi: 10.1109/ACCESS.2023.3281889.
N. Zhao, H. Gao, X. Wen and H. Li, "Combination of Convolutional Neural Network and Gated Recurrent Unit for Aspect-Based Sentiment Analysis," in IEEE Access, vol. 9, pp. 15561-15569, 2021, doi: 10.1109/ACCESS.2021.3052937.
A. Nazir, Y. Rao, L. Wu and L. Sun, "IAF-LG: An Interactive Attention Fusion Network With Local and Global Perspective for Aspect-Based Sentiment Analysis," in IEEE Transactions on Affective Computing, vol. 13, no. 4, pp. 1730-1742, 1 Oct.-Dec. 2022, doi: 10.1109/TAFFC.2022.3208216.
A. H. Sweidan, N. El-Bendary and H. Al-Feel, "Sentence-Level Aspect-Based Sentiment Analysis for Classifying Adverse Drug Reactions (ADRs) Using Hybrid Ontology-XLNet Transfer Learning," in IEEE Access, vol. 9, pp. 90828-90846, 2021, doi: 10.1109/ACCESS.2021.3091394.
B. Liang et al., "Embedding Refinement Framework for Targeted Aspect-Based Sentiment Analysis," in IEEE Transactions on Affective Computing, vol. 14, no. 1, pp. 279-293, 1 Jan.-March 2023, doi: 10.1109/TAFFC.2021.3071388.
W. Ali, Y. Yang, X. Qiu, Y. Ke and Y. Wang, "Aspect-Level Sentiment Analysis Based on Bidirectional-GRU in SIoT," in IEEE Access, vol. 9, pp. 69938-69950, 2021, doi: 10.1109/ACCESS.2021.3078114.
H. Huan, Z. He, Y. Xie and Z. Guo, "A Multi-Task Dual-Encoder Framework for Aspect Sentiment Triplet Extraction," in IEEE Access, vol. 10, pp. 103187-103199, 2022, doi: 10.1109/ACCESS.2022.3210180.
P. Mishra and S. K. Panda, "Dependency Structure-Based Rules Using Root Node Technique for Explicit Aspect Extraction From Online Reviews," in IEEE Access, vol. 11, pp. 65117-65137, 2023, doi: 10.1109/ACCESS.2023.3287830.
P. K. Soni and R. Rambola, "A Survey on Implicit Aspect Detection for Sentiment Analysis: Terminology, Issues, and Scope," in IEEE Access, vol. 10, pp. 63932-63957, 2022, doi: 10.1109/ACCESS.2022.3183205.
S. Nayab, M. K. Hanif, R. Talib and M. U. Sarwar, "Aspect-Context Level Information Extraction via Transformer Based Interactive Attention Mechanism for Sentiment Classification," in IEEE Access, vol. 11, pp. 57683-57692, 2023, doi: 10.1109/ACCESS.2023.3279396.
K. Xu, F. Li, D. Xie and D. Ji, "Revisiting Aspect-Sentiment-Opinion Triplet Extraction: Detailed Analyses Towards a Simple and Effective Span-Based Model," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 2918-2927, 2022, doi: 10.1109/TASLP.2022.3202122.
N. Liu, J. Hu, S. Yao, D. Liu and M. Yang, "IDCN: A Novel Interactive Dual Channel Network for Aspect Sentiment Triplet Extraction," in IEEE Access, vol. 10, pp. 116453-116466, 2022, doi: 10.1109/ACCESS.2022.3219986.
J. Liu, Q. Zhong, L. Ding, H. Jin, B. Du and D. Tao, "Unified Instance and Knowledge Alignment Pretraining for Aspect-Based Sentiment Analysis," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2629-2642, 2023, doi: 10.1109/TASLP.2023.3290431.
Z. Chen and T. Qian, "Retrieve-and-Edit Domain Adaptation for End2End Aspect Based Sentiment Analysis," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 659-672, 2022, doi: 10.1109/TASLP.2022.3146052.
Y. Lin, C. Wang, H. Song and Y. Li, "Multi-Head Self-Attention Transformation Networks for Aspect-Based Sentiment Analysis," in IEEE Access, vol. 9, pp. 8762-8770, 2021, doi: 10.1109/ACCESS.2021.3049294.
İ. Aygün, B. Kaya and M. Kaya, "Aspect Based Twitter Sentiment Analysis on Vaccination and Vaccine Types in COVID-19 Pandemic With Deep Learning," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 5, pp. 2360-2369, May 2022, doi: 10.1109/JBHI.2021.3133103.
N. Lin, Y. Fu, X. Lin, D. Zhou, A. Yang and S. Jiang, "CL-XABSA: Contrastive Learning for Cross-Lingual Aspect-Based Sentiment Analysis," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2935-2946, 2023, doi: 10.1109/TASLP.2023.3297964.
A. Boumhidi, A. Benlahbib and E. H. Nfaoui, "Cross-Platform Reputation Generation System Based on Aspect-Based Sentiment Analysis," in IEEE Access, vol. 10, pp. 2515-2531, 2022, doi: 10.1109/ACCESS.2021.3139956.
K. Sattar, Q. Umer, D. G. Vasbieva, S. Chung, Z. Latif and C. Lee, "A Multi-Layer Network for Aspect-Based Cross-Lingual Sentiment Classification," in IEEE Access, vol. 9, pp. 133961-133973, 2021, doi: 10.1109/ACCESS.2021.3116053.
S. Poria, D. Hazarika, N. Majumder and R. Mihalcea, "Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research," in IEEE Transactions on Affective Computing, vol. 14, no. 1, pp. 108-132, 1 Jan.-March 2023, doi: 10.1109/TAFFC.2020.3038167.
X. Ye, Y. Xu and M. Luo, "ALBERTC-CNN Based Aspect Level Sentiment Analysis," in IEEE Access, vol. 9, pp. 94748-94755, 2021, doi: 10.1109/ACCESS.2021.3094026.
Y. Bie, Y. Yang and Y. Zhang, "Fusing Syntactic Structure Information and Lexical Semantic Information for End-to-End Aspect-Based Sentiment Analysis," in Tsinghua Science and Technology, vol. 28, no. 2, pp. 230-243, April 2023, doi: 10.26599/TST.2021.9010095.
H. T. Phan, N. T. Nguyen and D. Hwang, "Aspect-Level Sentiment Analysis Using CNN Over BERT-GCN," in IEEE Access, vol. 10, pp. 110402-110409, 2022, doi: 10.1109/ACCESS.2022.3214233.
Z. Zhang, Y. Zuo and J. Wu, "Aspect Sentiment Triplet Extraction: A Seq2Seq Approach With Span Copy Enhanced Dual Decoder," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 2729-2742, 2022, doi: 10.1109/TASLP.2022.3198802.
Y. S. Mehanna and M. B. Mahmuddin, "A Semantic Conceptualization Using Tagged Bag-of-Concepts for Sentiment Analysis," in IEEE Access, vol. 9, pp. 118736-118756, 2021, doi: 10.1109/ACCESS.2021.3107237.
P. Lin, M. Yang and J. Lai, "Deep Selective Memory Network With Selective Attention and Inter-Aspect Modeling for Aspect Level Sentiment Classification," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1093-1106, 2021, doi: 10.1109/TASLP.2021.3058540.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
