Research Article
BibTex RIS Cite

Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi

Year 2023, , 875 - 882, 01.09.2023
https://doi.org/10.35234/fumbd.1335583

Abstract

Son yıllarda her zaman için her yerden ürün satın alma kolaylığı sağladığı ve ürünleri satın alan diğer kullanıcıların incelemelerinden kolayca ürün karşılaştırması sağladığından dolayı E-ticaret sitelerinden yapılan satın alma işlemleri oldukça artmıştır. E-Ticaret sitelerinde satılan ürünlerdeki kullanıcı puanları ve yorumları ürünlerin satın alma sayısını büyük ölçüde etkilemektedir. Müşteri incelemeleri aynı zamanda E-ticaret platformları için büyük miktarda metinsel veri üretmektedir. Üretilen bu verilerin analiz edilmesi satıcıların müşteri beklentilerini anlamalarını sağlayacakları için satışlarını da arttıracaktır. Bazı durumlarda müşteri değerlendirmeleri ve puanlamaları sadece ürünle ilgili olmayıp ürünün teslimatı gibi farklı konularla ilgili de olabilir. Bu durum diğer müşteriler için alışveriş riski oluşmasına sebep olmaktadır. Doğal Dil İşleme (DDİ) teknikleri aracılığıyla yapılacak olan duygu analizi, müşteriler tarafından herhangi bir ürün ile ilgili yapılan herkese açık incelemelerin analiz edilmesine odaklanır. Özellik tabanlı duygu analizi alanı, belirleyici önerilerde bulunmak için müşteri yorumlarında bulunan çeşitli görüşleri kategorize eder. Bu çalışmada E-ticaret platformlarından elde edilmiş müşteri yorumları veri setinde TF-IDF ve Word2Vec teknolojileri aracılığıyla müşteri incelemelerindeki özellikler tespit edilir. Daha sonra, tespit edilen her bir özellikle ilgili duygu ifadeleri incelenir. Çalışma, hem E-ticaret platformlarına hem de satıcılara mal ve hizmetlerini iyileştirebilmeleri için ışık tutacaktır. Aynı zamanda müşterilere alışverişlerinde özellik düzeyinde detaylı inceleme olanağı sağlayacaktır.

References

  • Ganesan, K., & Kim, H. D. (2016). Opinion Mining Tutorial (Sentiment Analysis). Opinion Mining Tutorial (Sentiment Analysis).
  • Pang, B., & Lee, L. (2004). A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. arXiv preprint cs/0409058.
  • Kim, S. M., & Hovy, E. (2004). Determining the sentiment of opinions. In COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics (pp. 1367-1373).
  • Liang, B., Su, H., Gui, L., Cambria, E., & Xu, R. (2022). Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowledge-Based Systems, 235, 107643.
  • Bhuvaneshwari, P., Rao, A. N., Robinson, Y. H., & Thippeswamy, M. N. (2022). Sentiment analysis for user reviews using Bi-LSTM self-attention based CNN model. Multimedia Tools and Applications, 81(9), 12405-12419.Fernandes, L. M., O'Connor, M., & Weaver, V. (2012). Big data, bigger outcomes. Journal of AHIMA, 83(10), 38-43.
  • Vinodhini, G., & Chandrasekaran, R. M. (2012). Sentiment analysis and opinion mining: a survey. International Journal, 2(6), 282-292.
  • Horrigan, J. (2008). Online shopping, Pew Internet & American Life project. Washington, DC Available at:< http://www. pewinternet. org/Reports/2008/Online-Shopping/01-Summary-of-Findings. aspx>[Accessed 8/8/2014].
  • Brody, S., & Elhadad, N. (2010, June). An unsupervised aspect-sentiment model for online reviews. In Human language technologies: The 2010 annual conference of the North American chapter of the association for computational linguistics (pp. 804-812).
  • Tang, D., Qin, B., & Liu, T. (2015, July). Learning semantic representations of users and products for document level sentiment classification. In Proceedings of the 53rd annual meeting of the Association for Computational Linguistics and the 7th international joint conference on natural language processing (volume 1: long papers) (pp. 1014-1023).
  • Tan, W., Wang, X., & Xu, X. (2018). Sentiment analysis for Amazon reviews. In International Conference (pp. 1-5).
  • Sadhasivam, J., & Kalivaradhan, R. B. (2019). Sentiment analysis of Amazon products using ensemble machine learning algorithm. International Journal of Mathematical, Engineering and Management Sciences, 4(2), 508.
  • Bhatt, A., Patel, A., Chheda, H., & Gawande, K. (2015). Amazon review classification and sentiment analysis. International Journal of Computer Science and Information Technologies, 6(6), 5107-5110.
  • Zhang, S., Zhang, D., Zhong, H., & Wang, G. (2020). A multiclassification model of sentiment for E-commerce reviews. IEEE Access, 8, 189513-189526.
  • Johnson, R., & Zhang, T. (2014). Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058.
  • Kaggle Dataset available at: https://www.kaggle.com/nicapotato/womens-ecommerce-clothing.
  • Onan, A. (2021). Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurrency and Computation: Practice and Experience, 33(23), e5909.
  • Hutto, C., & Gilbert, E. (2014, May). Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the international AAAI conference on web and social media (Vol. 8, No. 1, pp. 216-225).
  • Rong, X. (2014). word2vec parameter learning explained. arXiv preprint arXiv:1411.2738.
  • Heimerl, F., Lohmann, S., Lange, S., & Ertl, T. (2014, January). Word cloud explorer: Text analytics based on word clouds. In 2014 47th Hawaii international conference on system sciences (pp. 1833-1842). IEEE.

Aspect-Based Sentiment Analysis in E-Commerce User Reviews Using Natural Language Processing Techniques

Year 2023, , 875 - 882, 01.09.2023
https://doi.org/10.35234/fumbd.1335583

Abstract

In recent years, purchases made from E-commerce sites have increased considerably, as it provides the convenience of purchasing products from anywhere at all times and provides an easy product comparison from the reviews of other users who have purchased the products. User ratings and comments on products sold on e-commerce sites significantly affect the number of purchases of products. Customer reviews also generate large amounts of textual data for E-commerce platforms. Analyzing these produced data will increase the sellers' sales by enabling them to understand customer expectations. In some cases, customer reviews and ratings are not only about the product but also about different issues, such as the delivery of the product. This situation creates a shopping risk for other customers. Sentiment analysis through Natural Language Processing (DDI) techniques focuses on analyzing public reviews of any product by customers. The feature-based sentiment analysis field categorizes the various opinions found in customer reviews to make decisive recommendations. In this study, the features in customer reviews are determined through TF-IDF and Word2Vec technologies in the customer reviews dataset obtained from e-commerce platforms. Then, the emotional expressions related to each detected feature are examined. The study will shed light on both E-commerce platforms and sellers so that they can improve their goods and services. At the same time, it will allow customers to examine their purchases in detail at the feature level.

References

  • Ganesan, K., & Kim, H. D. (2016). Opinion Mining Tutorial (Sentiment Analysis). Opinion Mining Tutorial (Sentiment Analysis).
  • Pang, B., & Lee, L. (2004). A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. arXiv preprint cs/0409058.
  • Kim, S. M., & Hovy, E. (2004). Determining the sentiment of opinions. In COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics (pp. 1367-1373).
  • Liang, B., Su, H., Gui, L., Cambria, E., & Xu, R. (2022). Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowledge-Based Systems, 235, 107643.
  • Bhuvaneshwari, P., Rao, A. N., Robinson, Y. H., & Thippeswamy, M. N. (2022). Sentiment analysis for user reviews using Bi-LSTM self-attention based CNN model. Multimedia Tools and Applications, 81(9), 12405-12419.Fernandes, L. M., O'Connor, M., & Weaver, V. (2012). Big data, bigger outcomes. Journal of AHIMA, 83(10), 38-43.
  • Vinodhini, G., & Chandrasekaran, R. M. (2012). Sentiment analysis and opinion mining: a survey. International Journal, 2(6), 282-292.
  • Horrigan, J. (2008). Online shopping, Pew Internet & American Life project. Washington, DC Available at:< http://www. pewinternet. org/Reports/2008/Online-Shopping/01-Summary-of-Findings. aspx>[Accessed 8/8/2014].
  • Brody, S., & Elhadad, N. (2010, June). An unsupervised aspect-sentiment model for online reviews. In Human language technologies: The 2010 annual conference of the North American chapter of the association for computational linguistics (pp. 804-812).
  • Tang, D., Qin, B., & Liu, T. (2015, July). Learning semantic representations of users and products for document level sentiment classification. In Proceedings of the 53rd annual meeting of the Association for Computational Linguistics and the 7th international joint conference on natural language processing (volume 1: long papers) (pp. 1014-1023).
  • Tan, W., Wang, X., & Xu, X. (2018). Sentiment analysis for Amazon reviews. In International Conference (pp. 1-5).
  • Sadhasivam, J., & Kalivaradhan, R. B. (2019). Sentiment analysis of Amazon products using ensemble machine learning algorithm. International Journal of Mathematical, Engineering and Management Sciences, 4(2), 508.
  • Bhatt, A., Patel, A., Chheda, H., & Gawande, K. (2015). Amazon review classification and sentiment analysis. International Journal of Computer Science and Information Technologies, 6(6), 5107-5110.
  • Zhang, S., Zhang, D., Zhong, H., & Wang, G. (2020). A multiclassification model of sentiment for E-commerce reviews. IEEE Access, 8, 189513-189526.
  • Johnson, R., & Zhang, T. (2014). Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058.
  • Kaggle Dataset available at: https://www.kaggle.com/nicapotato/womens-ecommerce-clothing.
  • Onan, A. (2021). Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurrency and Computation: Practice and Experience, 33(23), e5909.
  • Hutto, C., & Gilbert, E. (2014, May). Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the international AAAI conference on web and social media (Vol. 8, No. 1, pp. 216-225).
  • Rong, X. (2014). word2vec parameter learning explained. arXiv preprint arXiv:1411.2738.
  • Heimerl, F., Lohmann, S., Lange, S., & Ertl, T. (2014, January). Word cloud explorer: Text analytics based on word clouds. In 2014 47th Hawaii international conference on system sciences (pp. 1833-1842). IEEE.
There are 19 citations in total.

Details

Primary Language Turkish
Subjects Deep Learning
Journal Section MBD
Authors

Serpil Aslan 0000-0001-8009-063X

Publication Date September 1, 2023
Submission Date July 31, 2023
Published in Issue Year 2023

Cite

APA Aslan, S. (2023). Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 35(2), 875-882. https://doi.org/10.35234/fumbd.1335583
AMA Aslan S. Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi. September 2023;35(2):875-882. doi:10.35234/fumbd.1335583
Chicago Aslan, Serpil. “Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi”. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 35, no. 2 (September 2023): 875-82. https://doi.org/10.35234/fumbd.1335583.
EndNote Aslan S (September 1, 2023) Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 35 2 875–882.
IEEE S. Aslan, “Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi”, Fırat Üniversitesi Mühendislik Bilimleri Dergisi, vol. 35, no. 2, pp. 875–882, 2023, doi: 10.35234/fumbd.1335583.
ISNAD Aslan, Serpil. “Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi”. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 35/2 (September 2023), 875-882. https://doi.org/10.35234/fumbd.1335583.
JAMA Aslan S. Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi. 2023;35:875–882.
MLA Aslan, Serpil. “Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi”. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, vol. 35, no. 2, 2023, pp. 875-82, doi:10.35234/fumbd.1335583.
Vancouver Aslan S. Doğal Dil İşleme Teknikleri Kullanarak E-Ticaret Kullanıcı İncelemelerinde Özellik Tabanlı Duygu Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi. 2023;35(2):875-82.