International Journal of Sensors, Wireless Communications and Control

2210-32792210-3287

Bentham Science

645472

10.2174/0122103279275188231205094007

Computer and Information Science

Research Article

An Efficient Aspect-based Sentiment Classification with Hybrid Word Embeddings and CNN Framework

Agrawal

Monika

info@benthamscience.netMoparthi

Nageswara

info@benthamscience.net

Department of CSE, Koneru Lakshmaiah Education Foundation

01012024

141455411012025

2024

Bentham Science Publishers

https://journals.eco-vector.com/2210-3279/article/view/645472

Background:As the e-commerce product reviews and social media posts are increasing enormously, the size of the database for polarity/ sentiment detection is a challenging task, and again, predicting polarities associated with respect to aspect terms end to end in a sentence is a havoc in real-time applications. Human behavior is influenced by the various opinions generated in society. Public opinion influences our decisions most often. Businesses and establishments always need to collect the opinion of the society, which they try to obtain using customer feedback forms and questionnaires or surveys, which help them to be aware of the shortcomings if any, and to use suggestions to improve quality. It works in the same way for customers as well and the opinions of other customers about a particular product can come in handy when deciding to buy a product.

Objectives:In this work, an efficient Aspect-based Sentiment Classification technique has been introduced with a hybrid, multiple-word embedding methods and implemented using the CNN framework on large databases.

Methods:Most of the traditional models have a limitation on the dependency for one or more similar types of aspect words for sentiment classification problem. However, these conventional models such as TF-ID, Word 2Vec and Glove method consumes much more time for word embedding process and Aspect terms generation and further process of aspect level sentiment classification. Further, these models are facing problems of high true negative rate and misclassification rate on large aspect databases in sentiment classification. In this article, we have introduced an efficient Proposed ensemble word embedding model in the CNN network and defined Hybrid Word2 Vec method, Hybrid Glove word embedding method and Hybrid Random Forest model for sentiment classification.

Results:Experiments on a widely used benchmark prove that the proposed word embedding method- based classification technique results in to higher true positive rate with minimal misclassifications and also supports better runtime and accuracy than the traditional word embedding-based aspect level classification approaches.

Conclusion:In this article, a hybrid ensemble feature ranking-based classification model is proposed on the large aspect databases. In this work, advanced multiple-word embedding methods are implemented to improve the essential feature extraction problem in the aspect level sentiment process. These multiple-word embedding methods are applied to the sentiment databases in the CNN framework.

Sentiment classificationopinionWordNetmachine learningword embeddingCNN.

Akhtar MS, Garg T, Ekbal A. Multi-task learning for aspect term extraction and aspect sentiment classification. Neurocomputing 2020; 398: 247-56. doi: 10.1016/j.neucom.2020.02.093

Chen F, Yuan Z, Huang Y. Multi-source data fusion for aspect-level sentiment classification. Knowl Base Syst 2020; 187: 104831. doi: 10.1016/j.knosys.2019.07.002

Du Y, He M, Wang L, Zhang H. Wasserstein based transfer network for cross-domain sentiment classification. Knowl Base Syst 2020; 204: 106162. doi: 10.1016/j.knosys.2020.106162

Duan J, Luo B, Zeng J. Semi-supervised learning with generative model for sentiment classification of stock messages. Expert Syst Appl 2020; 158: 113540. doi: 10.1016/j.eswa.2020.113540

Fu X, Wei Y, Xu F, et al. Semi-supervised aspect-level sentiment classification model based on variational autoencoder. Knowl Base Syst 2019; 171: 81-92. doi: 10.1016/j.knosys.2019.02.008

García-Díaz JA, Cánovas-García M, Valencia-García R. Ontologydriven aspect-based sentiment analysis classification: An infodemiological case study regarding infectious diseases in Latin America. Future Gener Comput Syst 2020; 112: 641-57. doi: 10.1016/j.future.2020.06.019 PMID: 32572291

Liu F, Zheng L, Zheng J. HieNN-DWE: A hierarchical neural network with dynamic word embeddings for document level sentiment classification. Neurocomputing 2020; 403: 21-32. doi: 10.1016/j.neucom.2020.04.084

Liu S, Lee K, Lee I. Document-level multi-topic sentiment classification of Email data with BiLSTM and data augmentation. Knowl Base Syst 2020; 197: 105918. doi: 10.1016/j.knosys.2020.105918

Ma R, Wang K, Qiu T, Sangaiah AK, Lin D, Liaqat HB. Featurebased compositing memory networks for aspect-based sentiment classification in social internet of things. Future Gener Comput Syst 2019; 92: 879-88. doi: 10.1016/j.future.2017.11.036

10.

Mekelė D, Frasincar F. ALDONAr: A hybrid solution for sentence-level aspect-based sentiment analysis using a lexicalized domain ontology and a regularized neural attention model. Inf Process Manage 2020; 57(3): 102211. doi: 10.1016/j.ipm.2020.102211

11.

Mowlaei ME, Saniee Abadeh M, Keshavarz H. Aspect-based sentiment analysis using adaptive aspect-based lexicons. Expert Syst Appl 2020; 148: 113234. doi: 10.1016/j.eswa.2020.113234

12.

Nguyen HT, Nguyen LM. ILWAANet: An interactive lexiconaware word-aspect attention network for aspect-level sentiment classification on social networking. Expert Syst Appl 2020; 146: 113065. doi: 10.1016/j.eswa.2019.113065

13.

Park H, Song M, Shin KS. Deep learning models and datasets for aspect term sentiment classification: Implementing holistic recurrent attention on target-dependent memories. Knowl Base Syst 2020; 187: 104825. doi: 10.1016/j.knosys.2019.06.033

14.

Pham DH, Le AC. Exploiting multiple word embeddings and one-hot character vectors for aspect-based sentiment analysis. Int J Approx Reason 2018; 103: 1-10. doi: 10.1016/j.ijar.2018.08.003

15.

Shuang K, Gu M, Li R, Loo J, Su S. Interactive POS-aware network for aspect-level sentiment classification. Neurocomputing 2020; (Sep): doi: 10.1016/j.neucom.2020.08.013

16.

Shuang K, Ren X, Yang Q, Li R, Loo J. AELA-DLSTMs: Attention-enabled and location-aware double LSTMs for aspect-level sentiment classification. Neurocomputing 2019; 334: 25-34. doi: 10.1016/j.neucom.2018.11.084

17.

Wen J, Zhang G, Zhang H, Yin W, Ma J. Speculative text mining for document-level sentiment classification. Neurocomputing 2020; 412: 52-62. doi: 10.1016/j.neucom.2020.06.024

18.

Xu Q, Zhu L, Dai T, Yan C. Aspect-based sentiment classification with multi-attention network. Neurocomputing 2020; 388: 135-43. doi: 10.1016/j.neucom.2020.01.024

19.

Yang M, Jiang Q, Shen Y, Wu Q, Zhao Z, Zhou W. Hierarchical human-like strategy for aspect-level sentiment classification with sentiment linguistic knowledge and reinforcement learning. Neural Netw 2019; 117: 240-8. doi: 10.1016/j.neunet.2019.05.021 PMID: 31195206

20.

Ye X, Dai H, Dong L, Wang X. Multi-view ensemble learning method for microblog sentiment classification. Expert Syst Appl 2021; 166(Sep): 113987. doi: 10.1016/j.eswa.2020.113987

21.

Zhang J, Chen M, Sun H, Li D, Wang Z. Object semantics sentiment correlation analysis enhanced image sentiment classification. Knowl Base Syst 2020; 191: 105245. doi: 10.1016/j.knosys.2019.105245

22.

Zhang M, Palade V, Wang Y, Ji Z. Attention-based word embeddings using artificial bee colony algorithm for aspect-level sentiment classification. Inf Sci 2020; (Sep): doi: 10.1016/j.ins.2020.09.038

23.

Zhao P, Hou L, Wu O. Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification. Knowl Base Syst 2020; 193: 105443. doi: 10.1016/j.knosys.2019.105443

24.

Zhou J, Chen Q, Huang JX, Hu QV, He L. Position-aware hierarchical transfer model for aspect-level sentiment classification. Inf Sci 2020; 513: 1-16. doi: 10.1016/j.ins.2019.11.048

25.

Zhou J, Huang JX, Hu QV, He LSK-GCN. Modeling syntax and knowledge via graph convolutional network for aspect-level sentiment classification. Knowl Base Syst 2020; 205: 106292. doi: 10.1016/j.knosys.2020.106292

26.

Agrawal M, Moparthi NR. An efficient multiple-word embeddingbased cross-domain feature extraction and aspect sentiment classification Meas: Sens 2023; 100851. doi: 10.1016/j.measen.2023.100851

27.

Wang X, Tang M, Yang T, Wang Z. A novel network with multiple attention mechanisms for aspect-level sentiment analysis. Knowl Base Syst 2021; 227: 107196. doi: 10.1016/j.knosys.2021.107196

28.

Wang X, Li F, Zhang Z, Xu G, Zhang J, Sun X. A unified position-aware convolutional neural network for aspect based sentiment analysis. Neurocomputing 2021; 450: 91-103. doi: 10.1016/j.neucom.2021.03.092

29.

Wei L, Hu D, Zhou W, et al. Hierarchical interaction networks with the rethinking mechanism for document-level sentiment analysis. Proceedings, Part III September 1418, 2020;. 2021; pp. 633-49. doi: 10.1007/978-3-030-67664-3_38

30.

Agrawal M, Moparthi NR. A Comprehensive Survey on Aspect Based Word Embedding Models and Sentiment Analysis Classification Approaches. Recent Trends in Intensive Computing 2021. doi: 10.3233/APC210175

31.

Rodrigues AP, Chiplunkar NN. A new big data approach for topic classification and sentiment analysis of Twitter data. Evol Intell 2019; 1-11.

32.

Patel D, Amin K. Multi-source domain adaptation in sentiment analysis using optimized neural network and cross-domain semantic libra. Int J Intell Eng Syst 2021; 14(5) doi: 10.22266/ijies2021.1031.47

33.

Senevirathne L, Demotte P, Karunanayake B, Munasinghe U, Ranathunga S. Sentiment analysis for sinhala language using deep learning techniques. arXiv:201107280 2020.

34.

Poria S, Hazarika D, Majumder N, Mihalcea R. Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research. IEEE Trans Affect Comput 2020.

35.

Li Z, Wei Y, Zhang Y, Zhang X, Li X. Exploiting coarse-to-fine task transfer for aspect-level sentiment classification. Proc Conf AAAI Artif Intell 2019; 33(1): 4253-60. doi: 10.1609/aaai.v33i01.33014253

36.

Li L, Zhu F, Sun H, Hu Y, Yang Y, Jin D. Multi-source information fusion and deep-learning-based characteristics measurement for exploring the effects of peer engagement on stock price synchronicity. Inf Fusion 2021; 69: 1-21. doi: 10.1016/j.inffus.2020.11.006

37.

Yin C, Zhang S, Zeng Q. Hybrid representation and decision fusion towards visual-textual sentiment. ACM Trans Intell Syst Technol 2023; 14(3): 1-17. doi: 10.1145/3583076

38.

Song W, Wen Z, Xiao Z, Park SC. Semantics perception and refinement network for aspect-based sentiment analysis. Knowl Base Syst 2021; 214: 106755. doi: 10.1016/j.knosys.2021.106755

39.

Liu M, Zhou F, Chen K, Zhao Y. Co-attention networks based on aspect and context for aspect-level sentiment analysis. Knowl Base Syst 2021; 217: 106810. doi: 10.1016/j.knosys.2021.106810

40.

Rajput GK, Kundu S, Kumar A. The impact of feature extraction on multi-source sentiment analysis. 2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART) 2021; 79: 510-5. doi: 10.1109/SMART52563.2021.9676201

41.

Afyouni I, Aghbari ZA, Razack RA. Multi-feature, multi-modal, and multi-source social event detection: A comprehensive survey. Inf Fusion 2022; 79: 279-308. doi: 10.1016/j.inffus.2021.10.013

42.

Jiang L, Liu L, Yao J, Shi L. A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion. J Cloud Comput 2020; 9: 1-16.

43.

Zhu L, Zhu Z, Zhang C, Xu Y, Kong X. Multimodal sentiment analysis based on fusion methods: A survey. Inf Fusion 2023; 95: 306-25. doi: 10.1016/j.inffus.2023.02.028

44.

Sarker A, Canto AC, Mozaffari Kermani M, Azarderakhsh R. Error detection architectures for hardware/software co-design approaches of number-theoretic transform. IEEE Trans Comput Aided Des Integrated Circ Syst 2023; 42(7): 2418-22. doi: 10.1109/TCAD.2022.3218614

45.

Mehran MKR. Integrating emerging cryptographic engineering research and security education. ASEE Annual Conference & Exposition. 1-26.

46.

Ausmita Sarker, Alvaro Cintas Canto, Mehran Mozaffari Kermani, Reza Azarderakhsh,. "Error Detection Architectures for Hardware/ Software Co-design Approaches of Number-Theoretic Transform", IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol 42, Issue 7, July 2023.

47.

Sarker A, Kermani MM, Azarderakhsh R. Efficient error detection architectures for postquantum signature Falcons sampler and KEM SABER. IEEE Trans Very Large Scale Integr VLSI Syst 2022; 30(6): 794-802. doi: 10.1109/TVLSI.2022.3156479

48.

Canto AC, Kaur J, Kermani MM, Azarderakhsh R. Algorithmic security is insufficient: A comprehensive survey on implementation attacks haunting post-quantum security. arXiv:230513544 2023.

49.

Kaur J, Canto AC, Kermani MM, Azarderakhsh R. A comprehensive survey on the implementations, attacks, and countermeasures of the current NIST lightweight cryptography standard. arXiv:230406222 2023.

50.

Elkhatib R, Koziel B, Azarderakhsh R, Kermani MM. Accelerated RISC-V for SIKE. 2021 IEEE 28th Symposium on Computer Arithmetic (ARITH) 14-16 June 2021; Lyngby, Denmark 2021. doi: 10.1109/ARITH51176.2021.00035

51.

Canto AC, Kaur J, Kermani MM, Azarderakhsh R. ChatGPT vs. Lightweight security: First work implementing the NIST cryptographic standard ASCON. arXiv:230608178 2023.

52.

Chauhan GS, Meena YK. An unsupervised multiple word-embedding method with attention model for cross domain aspect term extraction. 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE2020). doi: 10.1109/ICETCE48199.2020.9091738

53.

Medhat W, Hassan A, Korashy H. Sentiment analysis algorithms and applications: A survey. Ain Shams Eng J 2014; 5(4): 1093-113. doi: 10.1016/j.asej.2014.04.011

54.

Toqir AR, Cheah YN. Aspect extraction in sentiment analysis: comparative analysis and survey. Springer 2016. doi: 10.1007/s10462-016-9472-z

55.

Abirami AM, Gayathri V. A survey on sentiment analysis methods and approach. 2016 Eighth International Conference on Advanced Computing (ICoAC). 19-21 January 2017; Chennai, India. 2016.

56.

Araque O, Zhu G, Garcia-Amado M, Iglesias CA. Mining the opinionated web: Classification and detection of aspect contexts for aspect based sentiment analysis. 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW). 12-15 December 2016; Barcelona, Spain. 2016. doi: 10.1109/ICDMW.2016.0132

57.

Liu R, Shi Y, Ji C, Jia M. A survey of sentiment analysis based on transfer learning. IEEE Access 2019; 7: 85401-12. doi: 10.1109/ACCESS.2019.2925059

58.

Poria S. Aspect extraction for opinion mining with a deep convolutional neural network. KBS 2016; 108: 42-9. doi: 10.1016/j.knosys.2016.06.009

59.

Zhou Z, Liu F. Filter gate network based on multi-head attention for aspect-level sentiment classification. Neurocomputing 2021; 441: 214-25. doi: 10.1016/j.neucom.2021.02.041

60.

Zhou T, Law K, Creighton D. A weakly-supervised graph-based joint sentiment topic model for multi-topic sentiment analysis. Inf Sci 2022; 609: 1030-51. doi: 10.1016/j.ins.2022.07.126

61.

Zhao Z, Tang M, Tang W, Wang C, Chen X. Graph convolutional network with multiple weight mechanisms for aspect-based sentiment analysis. Neurocomputing 2022; 500: 124-34. doi: 10.1016/j.neucom.2022.05.045

62.

Zhao Q, Niu J, Liu X. ALS-MRS: Incorporating aspect-level sentiment for abstractive multi-review summarization. Knowl Base Syst 2022; 258: 109942. doi: 10.1016/j.knosys.2022.109942

63.

Zhang H, Chen Z, Chen B, et al. Complete quadruple extraction using a two-stage neural model for aspect-based sentiment analysis. Neurocomputing 2022; 492: 452-63. doi: 10.1016/j.neucom.2022.04.027

64.

Yang L, Na JC, Yu J. Cross-modal multitask transformer for end-to-end multimodal aspect-based sentiment analysis. Inf Process Manage 2022; 59(5): 103038. doi: 10.1016/j.ipm.2022.103038

65.

Xu L, Pang X, Wu J, Cai M, Peng J. Learn from structural scope: Improving aspect-level sentiment analysis with hybrid graph convolutional networks. Neurocomputing 2023; 518: 373-83. doi: 10.1016/j.neucom.2022.10.071

66.

Xianghua F, Guo L, Yanyan G, Zhiqiang W. Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon. Knowl Base Syst 2013; 37: 186-95. doi: 10.1016/j.knosys.2012.08.003

67.

Wu H, Huang C, Deng S. Improving aspect-based sentiment analysis with Knowledge-aware Dependency Graph Network. Inf Fusion 2023; 92: 289-99. doi: 10.1016/j.inffus.2022.12.004

68.

Wang X, Xu G, Zhang Z, Jin L, Sun X. End-to-end aspect-based sentiment analysis with hierarchical multi-task learning. Neurocomputing 2021; 455: 178-88. doi: 10.1016/j.neucom.2021.03.100

69.

Shaik T, Tao X, Dann C, Xie H, Li Y, Galligan L. Sentiment analysis and opinion mining on educational data: A survey. J Nat Lang Process 2023; 2: 100003. doi: 10.1016/j.nlp.2022.100003

70.

Rahmani S, Hosseini S, Zall R, Kangavari MR, Kamran S, Hua W. Transfer-based adaptive tree for multimodal sentiment analysis based on user latent aspects. Knowl Base Syst 2023; 261: 110219. doi: 10.1016/j.knosys.2022.110219

71.

Phan HT, Nguyen NT, Hwang D. Aspect-level sentiment analysis: A survey of graph convolutional network methods. Inf Fusion 2023; 91: 149-72. doi: 10.1016/j.inffus.2022.10.004

72.

Peng H, Ma Y, Li Y, Cambria E. Learning multi-grained aspect target sequence for Chinese sentiment analysis. Knowl Base Syst 2018; 148: 167-76. doi: 10.1016/j.knosys.2018.02.034

73.

Ma X, Zeng J, Peng L, Fortino G, Zhang Y. Modeling multi-aspects within one opinionated sentence simultaneously for aspect-level sentiment analysis. Future Gener Comput Syst 2019; 93: 304-11. doi: 10.1016/j.future.2018.10.041