Bus exterior advertising plays a significant role in outdoor advertising, since it provides frequent exposure to a large number of residents. Traditional route selection methods are generally based on a rough estimation, for example, the number of total passengers of a bus route or the geographical features along the bus route. Targeted bus exterior advertising remains a challenge as little is known about the characteristics of the people along the bus route. In this study, we are aiming at determining a set of bus routes for a given ad category to maximize advertising effectiveness, by mining multiple data sources, including mobile phone data, bus GPS data, smart card data (SCD), and land use data. Specifically, we first estimated the distribution of potential target audiences using mobile phone data and land use data. Two optimization models are proposed considering different advertising requirements. For well-established brands that audiences are familiar with, a wide coverage-oriented bus route selection model is proposed to maximize the coverage of potential target audiences. For new brands that require a high level of exposure before they become recognizable, a deep coverage-oriented bus route selection model is proposed to maximize the total exposure times of the ads. Both models were demonstrated with a case study in Shenzhen, China to explicitly present the outcomes of the models and the differences between them. The calculation results show that the wide coverage-oriented model achieves an average of 84.8% improvement compared with baseline 1 which selects the bus routes with the most passengers, while an average of 9.2% improvement compared with baseline 2 which selects the bus route with the maximum coverage of the target area in reaching more potential target audiences. The exposure intensity of the deep coverage-oriented model is almost 3.7 times of the wide coverage-oriented model. The proposed models provide new options for advertisers to select a suitable advertising strategy according to their needs.
Knowledge Graphs (KGs) are composed of structured information in the form of entities and relations. And the process of extracting entities and relations from data is called Knowledge Extraction. Knowledge extraction is a fundamental task in the field of Natural Language Processing (NLP) and a key part of knowledge graph construction. In this paper, we provide comprehensive research on knowledge extraction in knowledge graph construction. We first introduce the technical architecture of the KGs and the classification of knowledge extraction. Then, we systematically categorize existing works based on the development of knowledge extraction. Finally, we review current open-source tools for knowledge extraction and summarize their advantages and disadvantages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.