Detecting Sentiment Analysis Correlation Between Hotel Employee and Customer Reviews Using Machine Learning Algorithms


Bakan B., KARCIOĞLU A. A., Katırcıoğlu E.

ICCK Transactions on Emerging Topics in Artificial Intelligence, cilt.3, sa.3, ss.188-201, 2026 (Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 3 Sayı: 3
  • Basım Tarihi: 2026
  • Doi Numarası: 10.62762/tetai.2026.991738
  • Dergi Adı: ICCK Transactions on Emerging Topics in Artificial Intelligence
  • Derginin Tarandığı İndeksler: Scopus
  • Sayfa Sayıları: ss.188-201
  • Anahtar Kelimeler: multi-source correlation detection, semi-supervised preprocessing, sentiment analysis, service intelligence, topic modeling
  • Ondokuz Mayıs Üniversitesi Adresli: Evet

Özet

Analyzing heterogeneous online reviews from multiple stakeholder groups represents an emerging challenge in AI-driven service intelligence. This study proposes a two-stage sentiment correlation detection framework and applies it to customer and employee reviews of the Istanbul Marriott Şişli hotel. During dataset construction, a semi-supervised domain-specific blacklisting approach was developed alongside standard preprocessing steps to improve sentiment signal quality. In the first phase, customer and employee reviews were treated as separate datasets, and 5-fold cross-validation was applied using TF-IDF, BOW, and Word2Vec representations with multiple classifiers, achieving 99.8% and 93.8% F1-scores respectively. In the second phase, correlation analysis on the combined dataset yielded a 97.1% F1-score. In the final phase, LDA-based topic modeling identified three topic clusters, with the topic-based model achieving a 97.5% F1-score. The findings demonstrate that customer and employee perceptions converge at the macro level but diverge on a topic-by-topic basis. The proposed framework offers a generalizable approach for multi-source sentiment correlation analysis in domain-specific AI applications.