Tailored experiences: Unraveling T–A–P dynamics in activity-driven tourism recommendations for special interest travelers

Recommendation systems have become crucial in recent years, particularly in the travel industry, helping travelers discover appealing destinations. Special interest travelers seeking unique experiences require tailored activity-based recommendations. However, relying solely on search engines tends to yield generic results, often leading to repetitive information streams. To address this, our paper proposes a framework for extracting tourism activities and linking them to tourism types and destinations. We employed grammar-based techniques and n-gram characteristics to effectively extract these activities. The concept of the T–A–P Triangle connects tourism type (T), tourism activity (A), and tourism place (P), providing a comprehensive understanding of these associations. The study assesses the effectiveness of the feature combination used by the Conditional Random Fields (CRF) model to improve the extraction process. Our experiments reveal that our framework successfully extracts tourism-related activities. In particular, the three features of the model — word characteristics, part of speech (PoS), and named entity recognition (NER) — outperformed the single baseline feature, which is only word characteristics, with improvements of 5.26% in precision, 14.68% in recall, and 10.13% in the F1-score.