Which search queries are more powerful in tourism demand forecasting: searches via mobile device or PC?

Purpose While relevant research has considered aggregated data from mobile devices and personal computers (PCs), tourists’ search patterns on mobile devices and PCs differ significantly. This study aims to explore whether decomposing aggregated search queries based on the terminals from which these queries are generated can enhance tourism demand forecasting. Design/methodology/approach Mount Siguniang, a national geopark in China, is taken as a case study in this paper; another case, Kulangsu in China, is used as the robustness check. The authors decomposed the total Baidu search volume into searches from mobile devices and PCs. Weekly rolling forecasts were used to test the roles of decomposed and aggregated search queries in tourism demand forecasting. Findings Search queries generated from PCs can greatly improve forecasting performance compared to those from mobile devices and to aggregate search volumes from both terminals. Models incorporating search queries generated via multiple terminals did not necessarily outperform those incorporating search queries generated via a single type of terminal. Practical implications Major players in the tourism industry, including hotels, tourist attractions and airlines, can benefit from identifying effective search terminals to forecast tourism demand. Industry managers can also leverage search indices generated through effective terminals for more accurate demand forecasting, which can in turn inform strategic decision-making and operations management. Originality/value This study represents one of the earliest attempts to apply decomposed search query data generated via different terminals in tourism demand forecasting. It also enriches the literature on tourism demand forecasting using search engine data.

An Information Retrieval System Based on Multiple Portlets

Information retrieval systems built with a service-oriented architecture have numerous advantages, and portlets are a key technology to implement services which interact with each other in the presentation layer. This work presents an efficient approach for the communication between the components of an information retrieval system based on multiple portlets in a single user interface. It also presents the architecture and the main methods of the system implemented as a case of use for this approach. It is shown that the proposed solution yields the best inter-portlet communication mechanism in each situation, while possessing the ability to deliver aggregated search and superior user experience.

Vertical intent prediction approach based on Doc2vec and convolutional neural networks for improving vertical selection in aggregated search

Vertical selection is the task of selecting the most relevant verticals to a given query in order to improve the diversity and quality of web search results. This task requires not only predicting relevant verticals but also these verticals must be those the user expects to be relevant for his particular information need. Most existing works focused on using traditional machine learning techniques to combine multiple types of features for selecting several relevant verticals. Although these techniques are very efficient, handling vertical selection with high accuracy is still a challenging research task. In this paper, we propose an approach for improving vertical selection in order to satisfy the user vertical intent and reduce user’s browsing time and efforts. First, it generates query embeddings vectors using the doc2vec algorithm that preserves syntactic and semantic information within each query. Secondly, this vector will be used as input to a convolutional neural network model for increasing the representation of the query with multiple levels of abstraction including rich semantic information and then creating a global summarization of the query features. We demonstrate the effectiveness of our approach through comprehensive experimentation using various datasets. Our experimental findings show that our system achieves significant accuracy. Further, it realizes accurate predictions on new unseen data.