Detecting fake reviews through topic modelling

ÖZTÜRK BİRİM Ş., Kazancoglu I., Kumar Mangla S., Kahraman A., Kumar S., Kazançoğlu Y.

Journal of Business Research, cilt.149, ss.884-900, 2022 (SSCI) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 149
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1016/j.jbusres.2022.05.081
  • Dergi Adı: Journal of Business Research
  • Derginin Tarandığı İndeksler: Social Sciences Citation Index (SSCI), Scopus, International Bibliography of Social Sciences, Periodicals Index Online, ABI/INFORM, Business Source Elite, Business Source Premier, CAB Abstracts, INSPEC, Psycinfo, Public Affairs Index, Veterinary Science Database
  • Sayfa Sayıları: ss.884-900
  • Anahtar Kelimeler: Machine learning techniques, Fake online reviews, Natural language processing (NLP), Online retailing, Purchasing decision
  • Manisa Celal Bayar Üniversitesi Adresli: Evet

Özet

Against the uncertainty caused by the information overload in the online world, consumers can benefit greatly by reading online product reviews before making their online purchases. However, some of the reviews are written deceptively to manipulate purchasing decisions. The purpose of present study is to determine which feature combination is most effective in fake review detection among the features of sentiment scores, topic distributions, cluster distributions and bag of words. In this study, additional feature combinations to a sentiment analysis are searched to examine the critical problem of fake reviews made to influence the decision-making process using review from amazon.com dataset. Results of the study points that behavior-related features play an important role in fake review classifications when jointly used with text-related features. Verified purchase is the only behavior related feature used comparatively with other text-related features.