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

Abstract

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 \c{S}i\c{s}li 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.