The analysis of data from social media and social networking sites may be instrumental in achieving a better understanding of human-environment interactions and in shaping future conservation and environmental management. In this study, we systematically map the application of social media data in environmental research. The quantitative review of 169 studies reveals that most studies focus on the analysis of people’s behavior and perceptions of the environment, followed by environmental monitoring and applications in environmental planning and governance. The literature testifies to a very rapid growth in the field, with Twitter (52 studies) and Flickr (34 studies) being most frequently used as data sources. A growing number of studies combine data from multiple sites and jointly investigates multiple types of media. A broader, more qualitative review of the insights provided by the investigated studies suggests that while social media data offer unprecedented opportunities in terms of data volume, scale of analysis, and real-time monitoring, researchers are only starting to cope with the challenges of data’s heterogeneity and noise levels, potential biases, ethics of data acquisition and use, and uncertainty about future data availability. Critical areas for the development of the field include integration of different types of information in data mashups, development of quality assurance procedures and ethical codes, improved integration with existing methods, and assurance of long-term, free and easy-to-access provision of public social media data for future environmental researchers.

Passive crowdsourcing of social media in environmental research: A systematic map

A range of applications, from predicting the spread of human and electronic viruses to city planning and resource management in mobile communications, depend on our ability to foresee the whereabouts and mobility of individuals, raising a fundamental question: To what degree is human behavior predictable? Here we explore the limits of predictability in human dynamics by studying the mobility patterns of anonymized mobile phone users. By measuring the entropy of each individual's trajectory, we find a 93% potential predictability in user mobility across the whole user base. Despite the significant differences in the travel patterns, we find a remarkable lack of variability in predictability, which is largely independent of the distance users cover on a regular basis.

http://absimage.aps.org/image/MAR10/MWS_MAR10-2009-007155.pdf

Limits of predictability in human mobility

Most machine learning tasks can be categorized into classification or regression problems. Regression and classification models are normally used to extract useful geographic information from observed or measured spatial data, such as land cover classification, spatial interpolation, and quantitative parameter retrieval. This paper reviews the progress of four advanced machine learning methods for spatial data handling, namely, support vector machine (SVM)-based kernel learning, semi-supervised and active learning, ensemble learning, and deep learning. These four machine learning modes are representative because they improve learning performances from different views, for example, feature space transform and decision function (SVM), optimized uses of samples (semi-supervised and active learning), and enhanced learning models and capabilities (ensemble learning and deep learning). For spatial data handling via machine learning that can be improved by the four machine learning models, three key elements are learning algorithms, training samples, and input features. To apply machine learning methods to spatial data handling successfully, a four-level strategy is suggested: experimenting and evaluating the applicability, extending the algorithms by embedding spatial properties, optimizing the parameters for better performance, and enhancing the algorithm by multiple means. Firstly, the advances of SVM are reviewed to demonstrate the merits of novel machine learning methods for spatial data, running the line from direct use and comparison with traditional classifiers, and then targeted improvements to address multiple class problems, to optimize parameters of SVM, and to use spatial and spectral features. To overcome the limits of small-size training samples, semi-supervised learning and active learning methods are then utilized to deal with insufficient labeled samples, showing the potential of learning from small-size training samples. Furthermore, considering the poor generalization capacity and instability of machine learning algorithms, ensemble learning is introduced to integrate the advantages of multiple learners and to enhance the generalization capacity. The typical research lines, including the combination of multiple classifiers, advanced ensemble classifiers, and spatial interpolation, are presented. Finally, deep learning, one of the most popular branches of machine learning, is reviewed with specific examples for scene classification and urban structural type recognition from high-resolution remote sensing images. By this review, it can be concluded that machine learning methods are very effective for spatial data handling and have wide application potential in the big data era.

Advances of Four Machine Learning Methods for Spatial Data Handling: a Review

Exploring spatio-temporal changes of city inbound tourism flow: The case of Shanghai, China

Numerous number of tourism attractions along with a huge amount of information about them on web and social platforms have made the decision-making process for selecting and visiting them complicated. In this regard, the tourism recommendation systems have become interesting for tourists, but challenging for designers because they should be able to provide personalized services. This paper introduces a tourism recommendation system that extracts users' preferences in order to provide personalized recommendations. To this end, users' reviews on tourism social networks are used as a rich source of information to extract their preferences. Then, the comments are preprocessed, semantically clustered, and sentimentally analyzed to detect a tourist's preferences. Similarly, all users aggregated reviews about an attraction are utilized to extract the features of these points of interest. Finally, the proposed recommendation system, semantically compares the preferences of a user with the features of attractions to suggest the most matching points of interest to the user. In addition, the system utilizes the vital contextual information of time, location, and weather to filter unsuitable items and increase the quality of suggestions regarding the current situation. The proposed recommendation system is developed by Python and evaluated on a dataset gathered from TripAdvisor platform. The evaluation results show that the proposed system improves the f-measure criterion in comparison with the previous systems.

Tourism recommendation system based on semantic clustering and sentiment analysis

In the big data era, the social media data that contain users’ geographical locations are growing explosively. These kinds of spatiotemporal data provide a new perspective for us to observe the human movement behavior. By mining such spatiotemporal data, we can incorporate the users’ collective wisdom, build novel services and bring convenience to people. Through spatial clustering of the original user locations, both the ‘natural’ boundaries and the human activity information of the tourist attractions are generated, which facilitate performing popularity analysis of tourist attractions and extracting the travelers’ spatio-temporal patterns or travel laws. On the one hand, the potential extracted knowledge could provide decision supports to the tourism management department in both tourism planning and resource development; on the other hand, the travel preferences are able to be extracted from the clustering-generated attractions, and thus, intelligent tourism recommendation services could be developed for the tourist to promote the realization of ‘smart tourism’. Hence, this paper proposes a new method for discovering popular tourist attractions, which extracts hotspots through integrating spatial clustering and text mining approaches. We carry out tourist attraction discovery experiments based on the Flickr geotagged images within the urban area of Beijing from 2005 to 2016. The results show that compared with the traditional DBSCAN method, this novel approach can distinguish adjacent high-density areas when discovering popular tourist attractions and has better adaptability in the case of an uneven density distribution. In addition, based on the finding results of scenic hotspots, this paper analyzes the popularity distribution laws of Beijing’s tourist attractions under different temporal and weather contexts.

https://www.mdpi.com/2220-9964/6/7/216/pdf

A Novel Popular Tourist Attraction Discovering Approach Based on Geo-Tagged Social Media Big Data

Inferring demographics from human trajectories and geographical context

Geo-tagged travel photos on social networks often contain location data such as points of interest (POIs), and also users’ travel preferences. In this paper, we propose a hybrid ensemble learning m...

A hybrid ensemble learning method for tourist route recommendations based on geo-tagged social networks

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...

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

In the era of big data, Internet-based geospatial information services such as various LBS apps are deployed everywhere, followed by an increasing number of queries against the massive spatial data. As a result, the traditional relational spatial database (e.g., PostgreSQL with PostGIS and Oracle Spatial) cannot adapt well to the needs of large-scale spatial query processing. Spark is an emerging outstanding distributed computing framework in the Hadoop ecosystem. This paper aims to address the increasingly large-scale spatial query-processing requirement in the era of big data, and proposes an effective framework GeoSpark SQL, which enables spatial queries on Spark. On the one hand, GeoSpark SQL provides a convenient SQL interface; on the other hand, GeoSpark SQL achieves both efficient storage management and high-performance parallel computing through integrating Hive and Spark. In this study, the following key issues are discussed and addressed: (1) storage management methods under the GeoSpark SQL framework, (2) the spatial operator implementation approach in the Spark environment, and (3) spatial query optimization methods under Spark. Experimental evaluation is also performed and the results show that GeoSpark SQL is able to achieve real-time query processing. It should be noted that Spark is not a panacea. It is observed that the traditional spatial database PostGIS/PostgreSQL performs better than GeoSpark SQL in some query scenarios, especially for the spatial queries with high selectivity, such as the point query and the window query. In general, GeoSpark SQL performs better when dealing with compute-intensive spatial queries such as the kNN query and the spatial join query.

Xia Peng

Papers

A Novel Popular Tourist Attraction Discovering Approach Based on Geo-Tagged Social Media Big Data

Inferring demographics from human trajectories and geographical context

A hybrid ensemble learning method for tourist route recommendations based on geo-tagged social networks

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

GeoSpark SQL: An Effective Framework Enabling Spatial Queries on Spark