Regional difference and dynamic mechanism of locality of the Chinese farming-pastoral ecotone based on geotagged photos from Panoramio

Cross-regional locality research reflects the influences of natural environment and the human activities due to the abundant land types and the multiple landscape combinations in related regions. The Chinese farming-pastoral ecotone is a typical large-scale region but few studies were conducted. This research contributed to the understanding of cross-regional locality of the Chinese farming-pastoral ecotone from different scales, including national, sectional, and provincial administrative units by utilizing geotagged photos（GTPs） obtained from the Panoramio website. The major results were as follows：（1） the locality elements of the Chinese farming-pastoral ecotone included 52 free nodes classified into 8 types of scene attributes;（2） there were huge differences between locality elements of different regions, and there was a negative correlation between the similarity degree of elements of different provinces and their spatial distances;（3） the Chinese farming-pastoral ecotone could be divided into the northern, central and southern sections, whose localities had differences in element constitution, association structure and the strength of elements, system stability and the anti-interference capability; and（4） the evolution of the localities of the northern and central sections was mainly influenced by human activities, while the locality of southern section retained more natural features. On a theoretical level, this research aimed to establish the research methodology of locality from the perspective of open data on the web with strong operability and replicability. On a practical level, this research could enrich the structuring recognition of the locality of the Chinese farming-pastoral ecotone and the comprehension of its dynamic mechanism. The results provide a reference for locality differentiation protection and the development of a cross-regional scale.

Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

When travelling,people are accustomed to taking and uploading photos on social media websites,which has led to the accumulation of huge numbers of geotagged photos.Combined with multisource information(e.g.weather,transportation,or textual information),these geotagged photos could help us in constructing user preference profiles at a high level of detail.Therefore,using these geotagged photos,we built a personalised recommendation system to provide attraction recommendations that match a user’s preferences.Specifically,we retrieved a geotagged photo collection from the public API for Flickr(Flickr.com)and fetched a large amount of other contextual information to rebuild a user’s travel history.We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation(the matching process)and candidate ranking.In the matching process,we used a support vector machine model that was modified for multiclass classification to generate the candidate list.In addition,we used a gradient boosting regression tree to score each candidate and rerank the list.Finally,we evaluated our recommendation results with respect to accuracy and ranking ability.Compared with widely used memory-based methods,our proposed method performs significantly better in the cold-start situation and when mining‘long-tail’data.

Personalized tourist route recommendation model with a trajectory understanding via neural networks

Travel recommendations form a major part of tourism service. Traditional collaborative filtering and Markov model are not appropriate for expressing the trajectory features,for travel preferences of tourists are dynamic and affected by previous behaviors. Inspired by the success of deep learning in sequence learning,a personalized recurrent neural network (P-RecN) is proposed for tourist route recommendation. It is data-driven and adaptively learns the unknown mapping of historical trajectory input to recommended route output. Specifically,a trajectory encoding module is designed to mine the semantic information of trajectory data,and LSTM neural networks are used to capture the sequence travel patterns of tourists. In particular,a temporal attention mechanism is integrated to emphasize the main behavioral intention of tourists. We retrieve a geotagged photo dataset in Shanghai,and evaluate our model in terms of accuracy and ranking ability. Experimental results illustrated that P-RecN outperforms other baseline approaches and can effectively understand the travel patterns of tourists.