Online tourist reviews, a major form of user-generated content (UGC), are often short and unstructured, complicating the identification of tourist experience dimensions and their relationships. This study presents an integrated framework combining Topic-RoBERTa, topic-level semantic network analysis, and Graph Attention Networks (GAT) to extract experience topics and model their semantic associations. The authors validated the framework on 186,429 reviews from the OD-TripM TripAdvisor review dataset released by the Data Science and Computational Intelligence (DaSCI) research group on GitHub and the Yelp Open Dataset, identifying 12 tourist experience dimensions and constructing a community-structured semantic network. The results show that the proposed method can extract interpretable topics, reveal fine-grained attention-weighted associations, and provide a more structured understanding of tourist experiences. The findings offer valuable insights for tourism management and service optimization.
Yawei Wu, Xin Liu, A. Cheema· Journal of Organizational an...· 0 citations
Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven by benchmarks that evaluate end-to-end task success, these evaluations largely overlook two fundamental sources of difficulty in real web browsing: complex actions over rich user interfaces and visual perception of dynamically rendered content, especially in workflows that span multiple websites. We introduce CAP, a scalable benchmark for evaluating browser agents on cross-site, human-like web tasks that require non-trivial UI interactions and visual understanding. Specifically, we adopt a decomposition-and-recomposition pipeline that first abstracts each website into a structured site card capturing user-facing functions, complex execution operations, and perceptual requirements, and then recomposes these components into realistic cross-site workflows. Each task is therefore grounded in multiple specific operations on each website, enabling fine-grained diagnosis. Built on this framework, we construct 420 tasks across 108 real-world websites and 24 domains under careful quality control. Experiments on state-of-the-art browser agents using our verifiable agent-as-a-judge evaluation framework show low success rates and reveal that perception-heavy interactions remain a major bottleneck, exposing substantial gaps between current agents and real-world web browsing demands.