Detecting Novelty Seeking from online travel reviews:A Deep Learning Approach

Abstract

The rapid growth of user-generated content on travel platforms provides a rich source of information about traveler preferences. Detecting novelty-seeking behavior from online travel reviews can help personalized recommendation systems and improve marketing strategies. This study proposes a deep learning-based approach to automatically identify novelty-seeking tendencies in travel reviews. Leveraging a combination of recurrent neural networks (RNNs) and attention mechanisms, the model captures contextual and semantic cues from textual data to distinguish between conventional and novelty-oriented experiences. Experiments on a dataset of travel reviews demonstrate that the proposed method outperforms traditional machine learning techniques in accuracy, precision, and recall. The results highlight the potential of deep learning to understand complex user behaviors, enabling more tailored travel recommendations and enhanced user engagement