Table 1 Literature table
From: Social media analysis of car parking behavior using similarity based clustering
Authors | Data used | Method | Results | Limitations |
|---|---|---|---|---|
Zhang et al. [38] | Data collected using surveys, and questionnaire (3000 questionnaire delivered, and 2586 validated) | Use K2 algorithm with maximum-likelihood function to estimate parameter learning for Bayesian network. The nodes of the network holds the various factors that influence the parking decision and the edges reflect relationships | Identification of the age and gender as factors influencing selection of parking spot. Women and young people tend to select a spot with discount more than others. This provides suggestions to business owners and discount distribution for parking | The predictive model for parking fee needs more research and optimizations in order to improve its accuracy |
Zong and Wang [39] | Parking data collected from the area of Beijing, China. Based on large scale surveys 46,874 parking records obtained | Investigate parking behavior, and parking search decisions by utilizing K2 algorithm, and Bayesian learning techniques to develop the Bayesian network | The parking duration, and parking location are influenced by parking period time | Limited number of parking aspects were used in the analysis |
Spiliopouloua and Antoniou [24] | Traffic data gathered from previous studies from 6 different regions in Greece | Comparative study, and analysis of the parking diagrams in a staged approach | Identify illegal parking behavior and parking preferences were elicited illegal parking occurs when people don’t find free legal spaces, together with the absence of authority systems | The study was limited to only some regions from Greece |
Teknomo and Hokao [40] | Data collected by performing questionnaires with: Parking users about their parking behavior in terms of travel and individual infos and their preferences Government officials about parking strategies programs | Analyze data using various model-based location such as regression, analytic, hierarchy to identify influence of parking, behavior especially in business areas | Revealed some factors that influence search decisions in business areas, e.g., location, duration of parking search | Parking models need more development in order to impact parking policies |
Wang et al. [48] | Collect illegal parking reports from users via a mobile app | Mobile app system integrated with Wechat app as a social media platform used to report illegal parking | Contribute security by integrating the mobile app with police systems to minimize illegal parking in the city | Limitation with the accessibility of such system to contributors The system was only integrated with one mobile App |
Mondschein et al. [41] | Parking data collected from online reviews of a business, Yelp restaurants in the region of Phoenix, Arizona, US | Analyze the sentiment that accompanies the parking online reviews | Negative sentiment often accompanies the parking online reviews Reviews where parking was mentioned give less rating | The results are moderate, and small effect is noticed in terms of the impact about businesses and ratings |
van der Waerden et al. [42] | Data collected using online questionnaires related to business trips, e.g., vehicle use, time, area. Questionnaires distributed to residents in cities of Hasselt and Genk in Belgium. 436 responses | Statistical analysis of the questionnaire data, such as frequencies, percentages, and multinomial regression analysis | Parking behavior analysis in business areas. They revealed that individuals tend to use their cars in business areas, and in a regular way | Only some parking issues and aspects are treated. Limited to analyse the parking behavior in business area. The size of the data used in the study is small and does nor reflect official national statistics |