However, for these specialized studies, it is important to consider the data relevant only to these venues within the huge number of records and manually classify the specific data for each individual research. The LBSN data have also been used in more specialized studies like finding the popularity factors of restaurants, the role of parks, tourism behavior, and many more, which are proved to be tremendously valuable in these fields. The study of these behaviors provides valuable insights into the general trends within the population for the planning and development of events, festivals, parks, shopping malls, restaurants and, ultimately, a smart city. These data provide a sample of various aspects of human behavior and traits while interacting with the LBSN during a variety of activities through check-ins from different venues. With the interactive web-based interface of modern LBSNs, researchers have more opportunities to utilize the data regarding the majority of the population for various kinds of analysis.
#RAPIDMINER STUDIO 5 DOWNLOAD MANUAL#
Therefore, some machine-learning methodologies that can classify the data based on some specific characteristics are required so that the multivenue data can be classified without the need for manual work. The dataset often includes thousands or millions of records before the data analysis and requires the filtering out of data relevant to specific venue classes previously done manually, which is a time-consuming and troublesome issue for this kind of research. These kinds of data contain heterogeneous attributes about users from multiple venues researchers need to filter out the data relevant to specific venues in order to conduct more specialized studies. The LBSN data have been used for analysis in various specialized fields, such as the study of people’s behavior in festivals, shopping malls, food venues, tourism, and many more. The research on Location-Based Social Network (LBSN) data has gained huge attention from scholars with the rapid growth of mobile technologies. We classified the data using our machine-learning models into the 10 classes we used in our previous study and predicted tourist destinations among the data to demonstrate the effectiveness of using machine learning for location-based social network data analysis, which is vital for the development of smart city environments in the current technological era. We discovered that the proposed machine-learning models are capable of accurately classifying the data, with deep learning outperforming the other models with 99% accuracy, followed by gradient-boosted tree with 98% and 93%, generalized linear model with 90% and 85%, and logistic regression with 86% and 91%, for multiclass distributions and single class predictions, respectively. We then used various assessment metrics, such as the Receiver Operating Characteristic or Area Under the Curve, Accuracy, Recall, Precision, F-score, and Sensitivity, to show how well these methods performed. We designed, tested, and evaluated these models. We proposed four models based on well-known machine-learning techniques, including the generalized linear model, logistic regression, deep learning, and gradient-boosted trees. In this study, we used a Weibo dataset as the main source of research and analyzed machine-learning methods for more efficient implementation. Therefore, we proposed a novel approach of using machine-learning models to extract these venue categories. This has previously been done through a tedious and time-consuming manual method.
The analysis of user activities and behavior from location-based social network data is often based on venue types, which require the input of data into various categories.
The current research has aimed to investigate and develop machine-learning approaches by using the data in the dataset to be applied to classify location-based social network data and predict user activities based on the nature of various locations (such as entertainment).
0 kommentar(er)
