Research Article
BibTex RIS Cite

FORECASTING USEFUL COSTUMER REVIEWS VIA LOGISTIC REGRESSION

Year 2022, Volume: 7 Issue: IMISC2021 Special Issue, 15 - 32, 30.03.2022
https://doi.org/10.54452/jrb.1024602

Abstract

The increase in the number of comments and evaluations in which consumers share their purchasing experiences in the electronic environment can create a burden for potential customers who are interested in the comments made to determine the most useful and effective comments. For this purpose, e-commerce platforms perform prioritization and visibility rankings in comments with different approaches for consumer comments. These comments, which are called useful comments, are generally listed as a result of the votes of other consumers. Useful comments can leave behind current but useful comments because they are shared at a later date. In this study, the comments that were not prioritized as useful comments were estimated via logistic regression. In this way, the useful comments that remained in the background due to their current date were determined. The study presents a new approach in order to keep the interest and willingness to share consumer reviews high and to identify the most useful reviews among many potential customers.

References

  • Alzate, M., Arce-Urriza, M., & Cebollada, J. (2021). Online Reviews and Product Sales: The Role of Review Visibility. Journal of Theoretical and Applied Electronic Commerce Research, 16(4), 638-669.
  • Ay, Ş. (2020, Nisan 30). Model Performansını Değerlendirmek - Metrikler. Medium. https://medium.com/deep-learning-turkiye/model-performans%C4%B1n%C4%B1-de%C4%9Ferlendirmek-metrikler-cb6568705b1
  • Brown, J., Broderick, A. J., & Lee, N. (2007). Word of mouth communication within online communities: Conceptualizing the online social network. Journal of Interactive Marketing, 21(3), 2–20. https://doi.org/10.1002/dir.20082
  • Byun, K. A. K., Ma, M., Kim, K., & Kang, T. (2021). Buying a New Product with Inconsistent Product Reviews from Multiple Sources: The Role of Information Diagnosticity and Advertising. Journal of Interactive Marketing, 55, 81-103.
  • Chen, Y., Fay, S., & Wang, Q. (2004). Marketing implications of online consumer product reviews (Working paper). Department of marketing, University of Florida.
  • Çakar, E. N., & Akbıyık, A. Hızlı Tüketim Mallarına Yönelik Tüketici Yorumlarında Odak Sorunu: Ürün Mü, Satış Hizmeti Mi Değerlendiriliyor. AJIT-e: Bilişim Teknolojileri Online Dergisi, 9(33), 147-158. DOI: 10.5824/1309‐1581.2018.3.009.x
  • Feldman, R. (2013). Techniques and applications for sentiment analysis. Communications of the ACM, 56(4), 82-89.
  • Henning, T. T. (2003). Electronic Word of Mouth:Motives for Consequences of Reading Customer Articulations on the Internet. . International Journal of Electronic Commerce, Say:8.
  • Krestel, R., & Dokoohaki, N. (2011). Diversifying Product Review Rankings Getting the Full Picture. International Conferences on Web Intelligence and Intelligent Agent Technology
  • Nielsen. (2015). Global Trust in Advertising Report: Winning Strategies for an Evolving Media Landscape. Nielsen Insights, 1(September), 1–22.
  • Pursainen, E. (2010). Consumer motivations for providing electronic word-of-mouth in virtual pet communities. Doktora Tezi.
  • Turing, A. M. (2009). Computing machinery and intelligence. In Parsing the turing test (pp. 23-65). Springer, Dordrecht.
  • Uslu, S. (2016). Ağızdan Ağıza İletişim ile Tüketicilerin Alışveriş Merkezi Tercih Etme Davranışı Arasındaki İlişki. Aksaray Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 8(1), 97–106.
  • Yıldırım, S. (2020). Comparing Deep Neural Networks to Traditional Models for Sentiment Analysis in Turkish Language. 10.1007/978-981-15-1216-2_12
  • Yıldırım, S. (2020). savasy/bert-base-turkish-sentiment-cased · Hugging Face. https://huggingface.co/savasy/bert-base-turkish-sentiment-cased.
  • Zhang, J., Wang, C., & Chen, G. (2021). A Review Selection Method for Finding an Informative Subset from Online Reviews. INFORMS Journal on Computing, 33(1), 280-299.

LOJİSTİK REGRESYON İLE FAYDALI MÜŞTERİ YORUMLARINI TAHMİNLEME

Year 2022, Volume: 7 Issue: IMISC2021 Special Issue, 15 - 32, 30.03.2022
https://doi.org/10.54452/jrb.1024602

Abstract

Tüketicilerin elektronik ortamda gerçekleştirdiği satınalma deneyimlerini paylaştıkları yorum ve değerlendirme sayılarındaki! artış, yapılan yorumlarla !ilgilenen potansiyel müşteriler için en faydalı ve etkin yorumları belirleme konusunda yük oluşturabilmektedir. Bu amaçla e-ticaret platformları tüketici! yorumlarına yönelik olarak farklı yaklaşımlarla yorumlarda önceliklendirme ve görünür kılma sıralamaları gerçekleştirmektedir. Faydalı yorum olarak adlandırılan, genellikle diğer tüketicilerin oylamaları neticesinde sıralanan bu yorumlar, güncel olan ancak faydalı olabilecek yorumları daha geç paylaşılması nedeniyle geride bırakabilmektedir. Bu çalışmada, lojistik regresyon aracılığıyla faydalı yorum olarak önceliklendirilmemiş olan yorumların tahminlemesi gerçekleştirilerek güncel tarihli olması nedeniyle geri planda kalan faydalı yorumlar belirlenmiştir. Çalışma, tüketici yorumlarına olan ilgi ve paylaşım isteğinin yüksek tutulması ve potansiyel müşteriler için çok sayıda yorum arasından en faydalı olanların belirlenmesi adına yeni bir yaklaşım sunmaktadır.

References

  • Alzate, M., Arce-Urriza, M., & Cebollada, J. (2021). Online Reviews and Product Sales: The Role of Review Visibility. Journal of Theoretical and Applied Electronic Commerce Research, 16(4), 638-669.
  • Ay, Ş. (2020, Nisan 30). Model Performansını Değerlendirmek - Metrikler. Medium. https://medium.com/deep-learning-turkiye/model-performans%C4%B1n%C4%B1-de%C4%9Ferlendirmek-metrikler-cb6568705b1
  • Brown, J., Broderick, A. J., & Lee, N. (2007). Word of mouth communication within online communities: Conceptualizing the online social network. Journal of Interactive Marketing, 21(3), 2–20. https://doi.org/10.1002/dir.20082
  • Byun, K. A. K., Ma, M., Kim, K., & Kang, T. (2021). Buying a New Product with Inconsistent Product Reviews from Multiple Sources: The Role of Information Diagnosticity and Advertising. Journal of Interactive Marketing, 55, 81-103.
  • Chen, Y., Fay, S., & Wang, Q. (2004). Marketing implications of online consumer product reviews (Working paper). Department of marketing, University of Florida.
  • Çakar, E. N., & Akbıyık, A. Hızlı Tüketim Mallarına Yönelik Tüketici Yorumlarında Odak Sorunu: Ürün Mü, Satış Hizmeti Mi Değerlendiriliyor. AJIT-e: Bilişim Teknolojileri Online Dergisi, 9(33), 147-158. DOI: 10.5824/1309‐1581.2018.3.009.x
  • Feldman, R. (2013). Techniques and applications for sentiment analysis. Communications of the ACM, 56(4), 82-89.
  • Henning, T. T. (2003). Electronic Word of Mouth:Motives for Consequences of Reading Customer Articulations on the Internet. . International Journal of Electronic Commerce, Say:8.
  • Krestel, R., & Dokoohaki, N. (2011). Diversifying Product Review Rankings Getting the Full Picture. International Conferences on Web Intelligence and Intelligent Agent Technology
  • Nielsen. (2015). Global Trust in Advertising Report: Winning Strategies for an Evolving Media Landscape. Nielsen Insights, 1(September), 1–22.
  • Pursainen, E. (2010). Consumer motivations for providing electronic word-of-mouth in virtual pet communities. Doktora Tezi.
  • Turing, A. M. (2009). Computing machinery and intelligence. In Parsing the turing test (pp. 23-65). Springer, Dordrecht.
  • Uslu, S. (2016). Ağızdan Ağıza İletişim ile Tüketicilerin Alışveriş Merkezi Tercih Etme Davranışı Arasındaki İlişki. Aksaray Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 8(1), 97–106.
  • Yıldırım, S. (2020). Comparing Deep Neural Networks to Traditional Models for Sentiment Analysis in Turkish Language. 10.1007/978-981-15-1216-2_12
  • Yıldırım, S. (2020). savasy/bert-base-turkish-sentiment-cased · Hugging Face. https://huggingface.co/savasy/bert-base-turkish-sentiment-cased.
  • Zhang, J., Wang, C., & Chen, G. (2021). A Review Selection Method for Finding an Informative Subset from Online Reviews. INFORMS Journal on Computing, 33(1), 280-299.
There are 16 citations in total.

Details

Primary Language Turkish
Subjects Business Administration
Journal Section Articles
Authors

Adem Akbıyık 0000-0001-7634-4545

Oğuzhan Arı 0000-0002-7081-905X

Early Pub Date March 28, 2022
Publication Date March 30, 2022
Submission Date November 16, 2021
Acceptance Date March 28, 2022
Published in Issue Year 2022 Volume: 7 Issue: IMISC2021 Special Issue

Cite

APA Akbıyık, A., & Arı, O. (2022). LOJİSTİK REGRESYON İLE FAYDALI MÜŞTERİ YORUMLARINI TAHMİNLEME. Journal of Research in Business, 7(IMISC2021 Special Issue), 15-32. https://doi.org/10.54452/jrb.1024602