Exploring multilingual reviews for aspect-based sentiment analysis using Lexicon and BERT

Yıl 2024, Cilt: 42 Sayı: 5, 1469 - 1479, 04.10.2024

Muhammad Rizwan Rashid Rana Tariq Ali Asif Nawaz

Öz

Microblogs and social media sites have gained a central place and people use these platforms to express their opinions, sentiments, and thoughts about products, news, events, blogs, etc. Sentiment analysis is the process of exploring opinions and sentiments in user reviews and tweets. This area is still in its early developmental phase and requires imperative improve-ments on various issues. One of the main issues is multilingual tweets and reviews. Earlier sen-timent analysis techniques only classified the text of a specific language, i.e., English, Turkish, etc. The accuracy of these techniques decreases in the presence of multilingual text. Existing methods are domain oriented. Using BERT and a lexicon, we propose a method for sorting out multilingual text and improving the polarity calculation of reviews. Experimental results reveal that our proposed technique achieved 90.14% accuracy and outperformed existing as-pect-based sentiment analysis techniques.

Anahtar Kelimeler

BERT, Lexicon, SentiWordNet, Sentiments, Social Media

Kaynakça

• REFERENCES
• [1] Ullah MA, Marium SA, Dipa NS. An algorithm and method for sentiment analysis using the text and emoticon. ICT Express 2020;6:357360. [CrossRef]
• [2] Wu JL and Chung WY. Sentiment-based masked language modeling for improving sentence-level valence–arousal prediction. Appl Intell 2022;52:117. [CrossRef]
• [3] Ahmed M, Chen Q, Li Z. Constructing domain-dependent sentiment dictionary for sentiment analysis. Neural Comput Appl 2019;32:1471914732. [CrossRef]
• [4] Rana MRR, Rehman SU, Nawaz A, Ali T, Ahmed M. A conceptual model for decision support systems using aspect based sentiment analysis. P Romanian Acad A 2021;22:381390.
• [5] Rana MRR, Nawaz A, Iqbal J. A survey on sentiment classification algorithms, challenges and applications. Acta U Sapien Inform 2018;10:5872. [CrossRef]
• [6] Jain A, Nandi BP, Gupta C, Tayal DK. Senti-NSetPSO: large-sized document-level sentiment analysis using Neutrosophic Set and particle swarm optimization. Soft Comput 2020;24:315. [CrossRef]
• [7] Araújo M, Pereira A, Benevenuto F. A comparative study of machine translation for multilingual sentence-level sentiment analysis. Inform Sci 2020;512:10781102. [CrossRef]
• [8] Sann R, Pai PC. Understanding homophily of service failure within the hotel guest cycle: Applying NLP-aspect-based sentiment analysis to the hospitality industry. International J Hospit Manag 2020;91:102678. [CrossRef]
• [9] Tang F, Fu L, Yao B, Xu W. Aspect based fine-grained sentiment analysis for online reviews. Inform Sci 2019;488:190204. [CrossRef]
• [10] Yurtalan G, Koyuncu M, Turhan C. A polarity calculation approach for lexicon-based Turkish sentiment analysis. Turk J Electr Eng Comput Sci 2019;27:13251339. [CrossRef] [11] Farha IA, Magdy W. A comparative study of effective approaches for arabic sentiment analysis. Inform Process Manag 2021;58:102438. [CrossRef]
• [12] Ochoa-Luna J, Ari D. Deep neural network approaches for spanish sentiment analysis of short texts. In Ibero-American Conference on Artificial Intelligence 2018:430-441. [CrossRef]
• [13] Banjar A, Ahmed Z, Daud A, Abbasi RA, Dawood H. Aspect-based sentiment analysis for polarity estimation of customer reviews on Twitter. Comput Mater Con 2021;67:22032225. [CrossRef]
• [14] Janjua SH, Siddiqui GF, Sindhu MA, Rashid U. Multi-level aspect based sentiment classification of Twitter data: using hybrid approach in deep learning. PeerJ Computer Science 2021;13. [CrossRef]
• [15] Alamanda MS, Aspect-based sentiment analysis search engine for social media data. CSI Trans ICT 2020;8:193197. [CrossRef]
• [16] Tran T, Ba H, Huynh VN. Measuring hotel review sentiment: An aspect-based sentiment analysis approach. In International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making 2019. p.393405. [CrossRef]
• [17] Nawaz A, Awan AA, Ali T, Rana MRR. Product’s behaviour recommendations using free text: an aspect-based sentiment analysis approach. Clust Comput 2020;23:12671279. [CrossRef]
• [18] Mowlaei ME, Abadeh MS, Keshavarz H. Aspect-based sentiment analysis using adaptive aspect-based lexicons. Exp Syst Appl 2020;148:113234. [CrossRef]
• [19] Devlin J, Chang HM, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 2018.
• [20] Pak A and Paroubek P, Twitter as a corpus for sentiment analysis and opinion mining. Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10). In LREc 2010;10:1320-1326.
• [21] Xu H, Liu B, Shu L, Yu PS. Bert post-training for review reading comprehension and aspect-based sentiment analysis. arXiv preprint arXiv:1904.02232 2019.
• [22] Gao Z, Feng A, Song X, Wu X. Target-dependent sentiment classification with BERT. IEEE Access 2019;7:154290154299. [CrossRef]
• [23] Da L, Rafal R, Kenji A. HEMOS: A novel deep learning-based fine-grained humor detecting method for sentiment analysis of social media. Inform Process Manag 2020;57:102290. [CrossRef]
• [24] Wu H, Huang C, Deng S. Improving aspect-based sentiment analysis with knowledge-aware dependency graph network. Inf Fusion 2023;92:289-299. [CrossRef]
• [25] Jiang W, Zhou K, Xiong C, Du G, Ou C, Zhang J. KSCB: A novel unsupervised method for text sentiment analysis. Appl Intell 2023;53:301311. [CrossRef]
• [26] Qian Y, Wang J, Li D, Zhang X. Interactive capsule network for implicit sentiment analysis. Appl Intell 2023;53:31093123. [CrossRef]
• [27] Prottasha NJ, Sami AA, Kowsher M, Murad SA, Bairagi AK, Masud M, Baz M. Transfer learning for sentiment analysis using BERT based supervised fine-tuning. Sensors 2022;22:4157. [CrossRef]
• [28] Keung P, Lu Y, Szarvas G, Smith NA. The multilingual Amazon reviews corpus, arXiv preprint arXiv:2010.02573 2020. [CrossRef]
• [29] Mir J, Mahmood A. Movie aspects identification model for aspect based sentiment analysis, Inform Technol Control 2020;49:564582. [CrossRef]
• [30] Manguri KH, Ramadhan RN, Amin PRM. Twitter sentiment analysis on worldwide COVID-19 outbreaks. Kurdistan J Appl Res 2020;5:5465. [CrossRef]
• [31] Rescigno AA, Vanmassenhove E, Monti J, Way A. A Case Study of Natural Gender Phenomena in Translation: A Comparison of Google Translate, Bing Microsoft Translator and DeepL for English to Italian, French and Spanish, In CLiC-it 2020. [CrossRef]
• [32] Alasadi SA, Bhaya WS. Review of data preprocessing techniques in data mining. J Eng Appl Sci 2017;12:4102-4107.
• [33] Patil CG, Patil SS. Use of Porter stemming algorithm and SVM for emotion extraction from news headlines. Int J Electron Commun Soft Comput Sci Eng 2013;2:913.
• [34] Aldabbagh G, Alghazzawi DM, Hasan SH. Optimal learning behavior prediction system based on cognitive style using adaptive optimization-based neural network. Complexity 2020;202:113. [CrossRef]
• [35] Nandito A, Abdiansah A, Yusliani N. The Effect of brill tagger on the classification results of sentiment analysis using multinomial naïve bayes algorithm. Sriwijaya J Inform Appl 2021;2:817. [CrossRef] [36] Naseem A, Anwar M, Ahmed S, Satti QA, Hashmi FR, Malik T. Tagging Urdu sentences from English POS Taggers. Int J Adv Comput Sci Appl 2017;8:231238. [CrossRef]
• [37] Alaparthi S, Mishra N. Bidirectional Encoder Representations from Transformers (BERT): A sentiment analysis odyssey, arXiv preprint arXiv:2007.01127 2020.
• [38] Kumar K, Rout JR, Jena SK. Sentiment analysis using weight model based on SentiWordNet 3.0. In Kumar Sa P, Bakshi S, Hatzilygeroudis IK, Narayan Sahoo M, editors. Recent Findings in Intelligent Computing Techniques. Berlin, Heidelberg, Dordrecht, and New York City: Springer Link; 2018. p. 131139. [CrossRef]
• [39] Dou Z, Wei W, Wan X. Improving word embeddings for antonym detection using thesauri and sentiwordnet, In CCF International Conference on Natural Language Processing and Chinese Computing. 2018. p. 6779. [CrossRef]
• [40] Dong J, He F, Guo Y, Zhang F. A commodity review sentiment analysis based on BERT-CNN model, In 2020 5th International Conference on Computer and Communication Systems 2020. p. 143147. [CrossRef]
• [41] Wang Y, Sun A, Huang M, Zhu X. Aspect-level sentiment analysis using as-capsules. In The World Wide Web Conference 2019. p. 20332044. [CrossRef]
• [42] Veyseh APB, Nour N, Dernoncourt F, Tran QH, Dou D, Nguyen TH. Improving aspect-based sentiment analysis with gated graph convolutional networks and syntax- based regulation. arXiv preprint arXiv:2010.13389, 2020.
• [43] Cheng LC, Chen YL, Liao YY. Aspect-based sentiment analysis with component focusing multi-head co-attention networks. Neurocomputing 2022;489:917. [CrossRef]
• [44] Liang B, Su H, Gui L, Cambria E, Xu R. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowl-Based Syst 2022;235:107643. [CrossRef]