{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T10:05:59Z","timestamp":1771668359407,"version":"3.50.1"},"reference-count":0,"publisher":"Slovenian Association Informatika","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJCAI"],"abstract":"<jats:p>Tourism is a vital sector for economic development and cultural preservation, and understanding visitor experiences is crucial for effective destination management. However, existing sentiment analysis methods do not effectively integrate multimodal data, limiting accurate interpretation of visitor perceptions and experience evaluation. This research intends to develop a deep learning (DL)-driven multimodal framework that integrates textual, visual, and rating data to perform sentiment analysis and evaluation prediction for cultural tourism attractions. Textual reviews are preprocessed using lemmatization, while images are prepared through resizing and z-score normalization. Contrastive Language\u2013Image Pre-training (CLIP) is employed to extract semantic visual features. The intermediate fusion process is used to integrate textual, visual, and rating features cohesively, enabling richer cross-modal representation and more precise sentiment prediction. The textual and visual features are fused using an Artificial Gorilla Troops Optimizer-driven Intelligent Convolutional Deep Belief Network (AGT-ICDBN) to predict sentiment and evaluate cultural tourism attractions. In this framework, CLIP textual and visual embeddings are concatenated and routed through ICDBN layers, where convolutional Restricted Boltzmann Machines record hierarchical cross-modal dependencies. The AGT improves convergence and prediction resilience by fine-tuning model parameters, optimizing feature selection, and balancing exploration-exploitation. Experiments on a curated dataset of cultural attractions demonstrate that integrating multimodal information improves classification accuracy (CA) to 0.9895, precision to 0.9876, recall to 0.9893,AUC to 0.9853 and F1-score to 0.9877 compared to unimodal approaches, achieving strong correlations between sentiment and evaluation scores using Python 3.9. The proposed framework provides a foundation for real-time, interpretable, and data-driven evaluation of cultural tourism attractions.<\/jats:p>","DOI":"10.31449\/inf.v50i6.12220","type":"journal-article","created":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T09:24:19Z","timestamp":1771665859000},"source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Sentiment and Evaluation Prediction for Cultural Tourism Using an AGT-Optimized Convolutional Deep Belief Network (AGT-ICDBN)"],"prefix":"10.31449","volume":"50","author":[{"given":"Yuanhui","family":"Gong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"16141","published-online":{"date-parts":[[2026,2,21]]},"container-title":["Informatica"],"original-title":[],"link":[{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/12220\/6458","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/12220\/6458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T09:24:19Z","timestamp":1771665859000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/view\/12220"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":0,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,2,21]]}},"URL":"https:\/\/doi.org\/10.31449\/inf.v50i6.12220","relation":{},"ISSN":["1854-3871","0350-5596"],"issn-type":[{"value":"1854-3871","type":"electronic"},{"value":"0350-5596","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2,21]]}}}