Effect of Information Propagation on Business Popularity: A Case Study on Yelp

Venue-Popularity Prediction Using Social Data Participatory Sensing Systems and RNNs

“…An inference algorithm was developed for potentially estimating the number of customers. The effect of information diffusion on business popularity based on the social connections between visitors in the current and previous time frames, and geographical types of local and foreign visitors was studied in [27]. A combination of these two aspects of information diffusion was used to classify businesses as popular or unpopular using the Yelp dataset of different cities; for this purpose, SVM achieved the highest accuracy of 89% among all other models.…”

Location, location, location!

“…In this section, we briefly overview different streams of studies related to predicting business reviews and ratings based on business services [4], features [3], [5]- [7], and the location of business [1], [2]. Researchers have used features e.g., degree centrality and clustering coefficient, derived from graph model of user rating and business category data in Yelp, to predict user ratings [7].…”

“…Eravci et al [2] performed experiments using check-in data for New York from Foursquare and presented two solutions: Bayesian inference-based and collaborative filtering using neighborhood similarity to recommend a set of city neighborhoods as venues to successfully invest in a new specific business category. In another study [3], researchers proposed an approach to label popular and unpopular businesses based on region-wise popularity metrics. They also demonstrated the influence of local and foreign customers on the popularity of businesses and proposed a model to predict popularity of businesses with an accuracy of 89%.…”

“…We often hear the cliché, used by business experts, that the three most important factors in determining the success of a business are "location; location; location". Studies have investigated recommendation systems for optimal location to expand an existing business utilizing online customer reviews [1] and check-in patterns [2] or labeling business popularity using customers online social connections and geographical proximity to businesses [3]. However, none of these works have tried to evaluate the impact of location on the success of a business.…”

Análises de Dados de Sistemas Crowdsourcing: estudo de caso de avaliações de estabelecimentos realizadas no Yelp

“…Um grafoé gerado com os nós sendo os negócios e o peso das arestas a quantidade de clientes em comum, e concluiu-se que os clientes preferem visitar empresas que são geograficamente próximos e/ou possuem produtos e serviços similares. Em [Bhowmick et al 2017] os autores definem métricas de popularidade para rotular diversas empresas no conjunto de dados do Yelp, a principal foi a difusão da informação. Com isso, foi desenvolvido um modelo de recomendação que sugere as principais regiões para os empresários para iniciar negócios populares.…”