Department of Management, Zhengzhou University of Technology, Zhengzhou 450000, China.
Comput Intell Neurosci. 2022 Jun 26;2022:9566766. doi: 10.1155/2022/9566766. eCollection 2022.
Accurate recommendation of tourist attractions is conducive to improving users' travel efficiency and tourism experience. However, the choice of tourism feature factors and the difference of recommendation algorithm will affect the accuracy of scenic spot recommendation. Aiming at the problems of sparse data, insufficient tourism factors, and low recommendation accuracy in the existing tourism recommendation research, this paper puts forward a scenic spot recommendation method based on microblog data and machine learning by using the characteristics of personalized expression and strong current situation of microblog data and the intelligent prediction function of machine learning, so as to realize accurate and personalized scenic spot recommendation. This paper extracts rich tourism characteristic factors. Typical tourism recommendation algorithms choose tourism characteristic factors from scenic spots, tourists, and other aspects, without considering the travel time, tourism season, and other contextual information of tourists' destination, which can help understand users' tourism preferences from different angles. Aiming at the problem of sparse data and cold start of collaborative filtering recommendation algorithm, this paper introduces deep learning algorithm and combines the proposed multifeature tourism factors to build dynamic scenic spot prediction models (random forest preferred attraction prediction (RFPAP) and neural networks preferred attraction prediction (NNPAP)). The experimental results show that RFPAP and NNPAP methods can overcome the problem of data sparsity and achieve 89.61% and 89.51% accuracy, respectively. RFPAP method is better than NNPAP method and has stronger generalization ability.
准确的旅游景点推荐有助于提高用户的旅行效率和旅游体验。然而，旅游特色因素的选择和推荐算法的差异会影响景点推荐的准确性。针对现有旅游推荐研究中数据稀疏、旅游因素不足和推荐精度低的问题，本文利用微博数据的个性化表达特点和强时效性，以及机器学习的智能预测功能，提出了一种基于微博数据和机器学习的景点推荐方法，从而实现准确的个性化景点推荐。本文提取了丰富的旅游特色因素。典型的旅游推荐算法从景点、游客等方面选择旅游特色因素，而不考虑游客目的地的出行时间、旅游季节等上下文信息，可以从不同角度帮助理解用户的旅游偏好。针对协同过滤推荐算法中数据稀疏和冷启动的问题，本文引入深度学习算法，并结合提出的多特征旅游因素构建动态景点预测模型（随机森林首选景点预测（RFPAP）和神经网络首选景点预测（NNPAP））。实验结果表明，RFPAP 和 NNPAP 方法可以克服数据稀疏的问题，分别达到 89.61%和 89.51%的准确率。RFPAP 方法优于 NNPAP 方法，具有更强的泛化能力。
