(Publisher of Peer Reviewed Open Access Journals)
Navigation

International Journal of Advanced Technology and Engineering Exploration (IJATEE)

ISSN (Print):2394-5443    ISSN (Online):2394-7454
Volume-10 Issue-102 May-2023
Full-Text PDF
Paper Title : Implicit aspect based sentiment analysis for restaurant review using LDA topic modeling and ensemble approach
Author Name : Shini George and V. Srividhya
Abstract :

Technological advancements in e-commerce and Web 2.0 have revolutionized how customers express their opinions about services and features through reviews on various websites. This trend is particularly prominent in the travel industry, where online sources offer valuable insights into the food and accommodations of destinations. However, the abundance of reviews available online presents a challenge for travelers in filtering relevant information. To tackle this issue, aspect-based sentiment analysis (ABSA) was proposed as a technique for extracting opinions based on specific features. Topic modeling and sentiment analysis are two significant techniques employed to assist in this analysis. Topic modeling involves identifying thematic relationships among documents, while sentiment analysis aims to determine the expressed opinions in the text. This study utilized one of the leading travel websites, Tripadvisor, to gather customer reviews of different restaurants. These reviews were then subjected to aspect-based sentiment analysis using latent Dirichlet allocation (LDA) and ensemble bagging support vector machine (EBSVM) classifier techniques. The objective is to identify the most relevant aspect within the restaurant domain and enhance sentiment analysis performance. To address class imbalances in the datasets, the synthetic minority over-sampling technique (SMOTE) was implemented. The performance of LDA was evaluated using the coherence score, which indicates the quality of topics generated for restaurant reviews. The effectiveness of the EBSVM classifier was measured using metrics such as accuracy, precision, recall, and F1 score. The proposed model achieved an accuracy of 96.1%, surpassing other techniques. Overall, this study demonstrates the effectiveness of aspect-based sentiment analysis in extracting relevant opinions from a large volume of reviews. It also highlights the potential of machine learning techniques in enhancing sentiment analysis performance. The suggested approach outperforms other techniques discussed in the existing literature, contributing to an overall improvement in sentiment analysis.
Keywords : LDA, Topic modeling, ABSA, EBSVM, SMOTE.
Cite this article : George S, Srividhya V. Implicit aspect based sentiment analysis for restaurant review using LDA topic modeling and ensemble approach. International Journal of Advanced Technology and Engineering Exploration. 2023; 10(102):554-568. DOI:10.19101/IJATEE.2022.10100099.
References :
[1]Aïmeur E, Amri S, Brassard G. Fake news, disinformation and misinformation in social media: a review. Social Network Analysis and Mining. 2023; 13(1):1-36.
[Crossref] [Google Scholar]
[2]Wankhade M, Rao AC, Kulkarni C. A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review. 2022; 55(7):5731-80.
[Crossref] [Google Scholar]
[3]Patruni MR, Angadi A, Gorripati SK, Saraswathi P. Artificial intelligence techniques in text and sentiment analysis. In handbook of research on artificial intelligence applications in literary works and social media 2023 (pp. 171-91). IGI Global.
[Crossref] [Google Scholar]
[4]Zhu L, Xu M, Bao Y, Xu Y, Kong X. Deep learning for aspect-based sentiment analysis: a review. Journal for Computer Science. 2022; 8: e1044.
[Crossref] [Google Scholar]
[5]Bardutz E, Bigazzi A. Communicating perceptions of pedestrian comfort and safety: Structural topic modeling of open response survey comments. Transportation Research Interdisciplinary Perspectives. 2022; 14:100600.
[Crossref] [Google Scholar]
[6]Mutanga MB, Abayomi A. Tweeting on COVID-19 pandemic in South Africa: LDA-based topic modelling approach. African Journal of Science, Technology, Innovation and Development. 2022; 14(1):163-72.
[Google Scholar]
[7]Bagul DV, Barve S. A novel content-based recommendation approach based on LDA topic modeling for literature recommendation. In 6th international conference on inventive computation technologies 2021 (pp. 954-61). IEEE.
[Crossref] [Google Scholar]
[8]Guo C, Lu M, Wei W. An improved LDA topic modeling method based on partition for medium and long texts. Annals of Data Science. 2021; 8:331-44.
[Crossref] [Google Scholar]
[9]Eirinaki M, Pisal S, Singh J. Feature-based opinion mining and ranking. Journal of Computer and System Sciences. 2012; 78(4):1175-84.
[Google Scholar]
[10]Savanur SR, Sumathi R. SentiNeg: algorithm to process negations at sentence level in sentiment analysis. International Journal of Software Innovation. 2023; 11(1):1-27.
[Crossref] [Google Scholar]
[11]Ozyurt B, Akcayol MA. A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA. Expert Systems with Applications. 2021; 168.
[Crossref] [Google Scholar]
[12]Latif S, Shafait F, Latif R. Analyzing LDA and NMF topic models for urdu tweets via automatic labeling. IEEE Access. 2021; 9:127531-47.
[Crossref] [Google Scholar]
[13]Pratama MD, Sarno R, Abdullah R. Sentiment analysis user regarding hotel reviews by aspect based using latent dirichlet allocation, semantic similarity, and support vector machine method. International Journal of Intelligent Engineering and Systems. 2022; 15(3):514-24.
[Crossref] [Google Scholar]
[14]Mishra RK, Urolagin S, Jothi JA, Neogi AS, Nawaz N. Deep learning-based sentiment analysis and topic modeling on tourism during Covid-19 pandemic. Frontiers in Computer Science. 2021; 3: 775368.
[Crossref] [Google Scholar]
[15]Alsayat A. Improving sentiment analysis for social media applications using an ensemble deep learning language model. Arabian Journal for Science and Engineering. 2022; 47(2):2499-511.
[Crossref] [Google Scholar]
[16]Abdullah R, Suhariyanto S, Sarno R. Aspect based sentiment analysis for explicit and implicit aspects in restaurant review using grammatical rules, hybrid approach, and SentiCircle. International Journal of Intelligent Systems. 2021; 14(5):294-305.
[Google Scholar]
[17]AlGhamdi N, Khatoon S, Alshamari M. Multi-aspect oriented sentiment classification: Prior knowledge topic modelling and ensemble learning classifier approach. Applied Sciences. 2022; 12(8).
[Crossref] [Google Scholar]
[18]Gangadharan V, Gupta D. Recognizing named entities in agriculture documents using LDA based topic modelling techniques. Procedia Computer Science. 2020; 171:1337-45.
[Crossref] [Google Scholar]
[19]Banjar A, Ahmed Z, Daud A, Abbasi RA, Dawood H. Aspect-based sentiment analysis for polarity estimation of customer reviews on Twitter. Computers, Materials & Continua. 2021; 67(2):2203-25.
[Crossref] [Google Scholar]
[20]Kishan JG. Enhanced heterogeneous ensemble technique for improving software fault prediction. International Journal on Technical and Physical Problems of Engineering. 2021; 49(13):63-71.
[Google Scholar]
[21]Wang L, Han M, Li X, Zhang N, Cheng H. Review of classification methods on unbalanced data sets. IEEE Access. 2021; 9:64606-28.
[Google Scholar]
[22]Desuky AS, Hussain S. An improved hybrid approach for handling class imbalance problem. Arabian Journal for Science and Engineering. 2021; 46:3853-64.
[Crossref] [Google Scholar]
[23]Naim FA. Bangla aspect-based sentiment analysis based on corresponding term extraction. In international conference on information and communication technology for sustainable development 2021 (pp. 65-9). IEEE.
[Crossref] [Google Scholar]
[24]Arseniev-Koehler A, Cochran SD, Mays VM, Chang KW, Foster JG. Integrating topic modeling and word embedding to characterize violent deaths. Proceedings of the National Academy of Sciences. 2022; 119(10).
[Crossref] [Google Scholar]
[25]Sunardi PN, Harjo RA. Aspect-based sentiment analysis for hotel review using LDA, semantic similarity, and BERT. International Journal of Intelligent Engineering and Systems. 2022; 15(5):232-43.
[Crossref] [Google Scholar]
[26]Wen H, Zhao J. Sentiment analysis model of imbalanced comment texts based on BiLSTM. 2023.
[Crossref] [Google Scholar]
[27]Sethi SC. Reviewing flipkart product comments using methods based on sentiment analysis. International Research Journal of Modernization in Engineering Technology and Science. 2023; 5(2): 806-10.
[Google Scholar]
[28]D Aniello G, Gaeta M, La Rocca I. KnowMIS-ABSA: an overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis. Artificial Intelligence Review. 2022; 55(7):5543-74.
[Crossref] [Google Scholar]
[29]Cyril CP, Beulah JR, Subramani N, Mohan P, Harshavardhan A, Sivabalaselvamani D. An automated learning model for sentiment analysis and data classification of Twitter data using balanced CA-SVM. Concurrent Engineering. 2021; 29(4):386-95.
[Crossref] [Google Scholar]
[30]Mujahid M, Lee E, Rustam F, Washington PB, Ullah S, Reshi AA, Ashraf I. Sentiment analysis and topic modeling on tweets about online education during COVID-19. Applied Sciences. 2021; 11(18): 8438.
[Crossref] [Google Scholar]
[31]Tao J, Zhou L. Can online consumer reviews signal restaurant closure: a deep learning-based time-series analysis. IEEE Transactions on Engineering Management. 2020; 70 (3): 834-848.
[Crossref] [Google Scholar]
[32]Obiedat R, Qaddoura R, Ala M AZ, Al-Qaisi L, Harfoushi O, Alrefai MA, et al. Sentiment analysis of customers’ reviews using a hybrid evolutionary SVM-based approach in an imbalanced data distribution. IEEE Access. 2022; 10:22260-73.
[Crossref] [Google Scholar]
[33]Sattar K, Umer Q, Vasbieva DG, Chung S, Latif Z, Lee C. A multi-layer network for aspect-based cross-lingual sentiment classification. IEEE Access. 2021; 9:133961-73.
[Crossref] [Google Scholar]
[34]Chen Y, Chang C, Gan J. A template approach for summarizing restaurant reviews. IEEE Access. 2021; 9:115548-62.
[Crossref] [Google Scholar]
[35]Rupapara V, Rustam F, Shahzad HF, Mehmood A, Ashraf I, Choi GS. Impact of SMOTE on imbalanced text features for toxic comments classification using RVVC model. IEEE Access. 2021; 9:78621-34.
[Crossref] [Google Scholar]
[36]Pradha S, Halgamuge MN, Vinh NT. Effective text data preprocessing technique for sentiment analysis in social media data. In 11th international conference on knowledge and systems engineering 2019 (pp. 1-8). IEEE.
[Crossref] [Google Scholar]
[37]Mukherjee M, Khushi M. SMOTE-ENC: a novel SMOTE-based method to generate synthetic data for nominal and continuous features. Applied System Innovation. 2021; 4(1):1-12.
[Crossref] [Google Scholar]
[38]Susan S, Kumar A. The balancing trick: Optimized sampling of imbalanced datasets-a brief survey of the recent State of the Art. Engineering Reports. 2021; 3(4): e12298.
[Crossref] [Google Scholar]
[39]Khong WH, Soon LK, Goh HN, Haw SC. Leveraging part-of-speech tagging for sentiment analysis in short texts and regular texts. In semantic technology: 8th joint international conference, JIST, Awaji, 2018, Proceedings 2018 (pp. 182-97). Springer International Publishing.
[Crossref] [Google Scholar]
[40]Jelodar H, Wang Y, Yuan C, Feng X, Jiang X, Li Y, Zhao L. Latent dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications. 2019; 78:15169-211.
[Crossref] [Google Scholar]
[41]Grootendorst B. Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794. 2022.
[Google Scholar]
[42]Gupta RK, Agarwalla R, Naik BH, Evuri JR, Thapa A, Singh TD. Prediction of research trends using LDA based topic modeling. Global Transitions Proceedings. 2022; 3(1):298-304.
[Crossref] [Google Scholar]
[43]Catelli R, Pelosi S, Esposito M. Lexicon-based vs. Bert-based sentiment analysis: a comparative study in Italian. Electronics. 2022; 11(3): 374.
[Crossref] [Google Scholar]
[44]Raza GM, Butt ZS, Latif S, Wahid A. Sentiment analysis on COVID tweets: an experimental analysis on the impact of count vectorizer and TF-IDF on sentiment predictions using deep learning models. In international conference on digital futures and transformative technologies 2021 (pp. 1-6). IEEE.
[Crossref] [Google Scholar]
[45]Luo C. A comparison analysis for credit scoring using bagging ensembles. Expert Systems. 2022; 39(2).
[Crossref] [Google Scholar]
[46]Syed S, Spruit M. Full-text or abstract? examining topic coherence scores using latent dirichlet allocation. In international conference on data science and advanced analytics (DSAA) 2017 (pp. 165-74). IEEE.
[Crossref] [Google Scholar]
[47]Valdivia A, Luzón MV, Herrera F. Sentiment analysis in tripadvisor. IEEE Intelligent Systems. 2017; 32(4):72-7.
[Crossref] [Google Scholar]
[48]Kalaivani P, Dinesh D. Machine learning approach to analyze classification result for twitter sentiment. In international conference on smart electronics and communication 2020 (pp. 107-12). IEEE.
[Crossref] [Google Scholar]
[49]Huang CY, Dai HL. Learning from class-imbalanced data: review of data driven methods and algorithm driven methods. Data Science in Finance and Economics. 2021; 1(1):21-36.
[Crossref] [Google Scholar]
[50]Mutinda J, Mwangi W, Okeyo G. Sentiment analysis of text reviews using lexicon-enhanced bert embedding (LeBERT) model with convolutional neural network. Applied Sciences. 2023; 13(3): 1445.
[Crossref] [Google Scholar]
[51]Kaur G, Sharma A. A deep learning-based model using hybrid feature extraction approach for consumer sentiment analysis. Journal of Big Data. 2023; 10(1):1-23.
[Crossref] [Google Scholar]
[52]Sazzed S. A hybrid approach of opinion mining and comparative linguistic analysis of restaurant reviews. In proceedings of the international conference on recent advances in natural language processing 2021 (pp. 1281-8).
[Google Scholar]
[53]AlGhamdi N, Khatoon S. Improving sentiment prediction using heterogeneous and homogeneous ensemble methods: a comparative study. Procedia Computer Science. 2021; 194:60-8.
[Crossref] [Google Scholar]
[54]Nurifan F, Sarno R, Sungkono KR. Aspect based sentiment analysis for restaurant reviews using hybrid elmo-wikipedia and hybrid expanded opinion lexicon-senticircle. International Journal of Intelligent Engineering and Systems. 2019; 12(6):47-58.
[Crossref] [Google Scholar]