Comparison of Word2Vec with GloVe in Multi-Aspect Sentiment Analysis Classification of Nvidia RTX Products with Naïve Bayes Classifier
DOI:
https://doi.org/10.30865/jurikom.v10i1.5528Keywords:
Naive Bayes Classifier, Word2Vec, Glove, Confusion Matrix, Multi-Aspect Sentiment AnalysisAbstract
The increasing number of gamers has increased the demand for Graphics Processing Unit (GPU) products, one example of which is the Nvidia RTX product. Many users submit their reviews on social media Twitter in the form of tweets. These Tweets can be analyzed to determine the quality of a product. But most of the tweets talking about the product as a whole ignoring the category aspects of the product, making it difficult for both users and companies to pinpoint which aspects need attention. In this research, a multi-aspect based sentiment analysis will be carried out on tweets on Nvidia RTX products based on aspects of the product. The classification method used is Naive Bayes Classifier which will then compare feature extraction using Word2Vec and GloVe. Performance parameters are measured using a confusion matrix to produce values for accuracy, precision, recall, and f1-score. The highest accuracy results obtained were 60.71% on the price aspect, GloVe feature extraction, and classification with Gaussian Naive Bayes.
Keywords: naive bayes classifier; Word2Vec; GloVe; confusion matrix; multi-aspect sentiment analysis
References
V. v. Sanzharov, A. I. Gorbonosov, V. A. Frolov, and A. G. Voloboy, “Examination of the Nvidia RTX,†in CEUR Workshop Proceedings, 2019, vol. 2485, pp. 7–12. doi: 10.30987/graphicon-2019-2-7-12.
A. Bayhaqy, S. Sfenrianto, K. Nainggolan, and E. R. Kaburuan, “Sentiment Analysis about E-Commerce from Tweets Using Decision Tree, K-Nearest Neighbor, and Naïve Bayes.†[Online]. Available: http://dlvr.it/Qb83n8pic.twitter.com/8MucIMhUMO,
T. Haque UI, N. Saber N, and F. Shah M, “Sentiment Analysis on Large Scale Amazon Product Reviews,†2018 IEEE International Conference on Innovative Research and Development (ICIRD), May 2018.
J. Song, K. T. Kim, B. Lee, S. Kim, and H. Y. Youn, “A novel classification approach based on Naïve Bayes for Twitter sentiment analysis,†KSII Transactions on Internet and Information Systems, vol. 11, no. 6, pp. 2996–3011, 2017, doi: 10.3837/tiis.2017.06.011.
A. L. F. Alves, C. de S. Baptista, A. A. Firmino, M. G. de Oliveira, and A. C. de Paiva, “A comparison of SVM versus naive-bayes techniques for sentiment analysis in tweets: A case study with the 2013 FIFA confederations cup,†in WebMedia 2014 - Proceedings of the 20th Brazilian Symposium on Multimedia and the Web, Nov. 2014, pp. 123–130. doi: 10.1145/2664551.2664561.
M. Guia, R. R. Silva, and J. Bernardino, “Comparison of Naive Bayes, support vector machine, decision trees and random forest on sentiment analysis,†in IC3K 2019 - Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, 2019, vol. 1, pp. 525–531. doi: 10.5220/0008364105250531.
R. Novendri, A. S. Callista, D. N. Pratama, and C. E. Puspita, “Sentiment Analysis of YouTube Movie Trailer Comments Using Naïve Bayes,†Bulletin of Computer Science and Electrical Engineering, vol. 1, no. 1, pp. 26–32, Jun. 2020, doi: 10.25008/bcsee.v1i1.5.
I. P. Ananda, M. Utama, S. Prasetyowati, and Y. Sibaroni, “Multi-Aspect Sentiment Analysis Hotel Review Using RF, SVM, and Naïve Bayes based Hybrid Classifier,†JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 2, pp. 630–639, Apr. 2021, doi: 10.30865/MIB.V5I2.2959.
O. B. Deho, W. A. Agangiba, F. L. Aryeh, and J. A. Ansah, “Sentiment Analysis with Word Embedding.â€
H. Li, X. Li, D. Caragea, and C. Caragea, “Comparison of Word Embeddings and Sentence Encodings as Generalized Representations for Crisis Tweet Classification Tasks.†[Online]. Available: http://aidr.qcri.org/
T. Shi and Z. Liu, “Linking GloVe with word2vec,†Nov. 2014, [Online]. Available: http://arxiv.org/abs/1411.5595
M. Avinash and E. Sivasankar, “A study of feature extraction techniques for sentiment analysis,†Advances in Intelligent Systems and Computing, vol. 814, pp. 475–486, 2019, doi: 10.1007/978-981-13-1501-5_41/COVER.
C. A. Iglesias and A. Moreno, “Sentiment Analysis for Social Mediaâ€, Accessed: Jan. 30, 2023. [Online]. Available: www.mdpi.com/journal/applsci
R. V. O. I. Sudiro, S. S. Prasetiyowati, and Y. Sibaroni, “Aspect Based Sentiment Analysis with Combination Feature Extraction LDA and Word2vec,†2021 9th International Conference on Information and Communication Technology, ICoICT 2021, pp. 611–615, Aug. 2021, doi: 10.1109/ICOICT52021.2021.9527506.
I. K. Yoga, S. S. Prasetyowati, and Y. Sibaroni, “PREDICTION AND MAPPING RAINFALL CLASSIFICATION USING NAIVE BAYES AND SIMPLE KRIGING,†JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 7, no. 4, pp. 1244–1253, Nov. 2022, doi: 10.29100/JIPI.V7I4.3264.
D. Krstinić et al., “Multi-label Classifier Performance Evaluation with Confusion Matrix,†Computer Science & Information Technology (CS & IT) Vol.10, No.8, vol. 10, no. 8, p. 1, Jun. 2020, doi: 10.5121/CSIT.2020.100801.
A. Hussain, “Socio-Affective Computing Volume 5 Series Editorâ€, Accessed: Jan. 30, 2023. [Online]. Available: http://www.springer.com/series/13199
W. Etaiwi and G. Naymat, “The Impact of applying Different Preprocessing Steps on Review Spam Detection,†in Procedia Computer Science, 2017, vol. 113, pp. 273–279. doi: 10.1016/j.procs.2017.08.368.
S. Al-Saqqa and A. Awajan, “The Use of Word2vec Model in Sentiment Analysis: A Survey,†in ACM International Conference Proceeding Series, Dec. 2019, pp. 39–43. doi: 10.1145/3388218.3388229.
E. M. Alshari, A. Azman, S. Doraisamy, N. Mustapha, and M. Alkeshr, “Improvement of sentiment analysis based on clustering of Word2Vec features,†in Proceedings - International Workshop on Database and Expert Systems Applications, DEXA, Sep. 2017, vol. 2017-August, pp. 123–126. doi: 10.1109/DEXA.2017.41.
