Predicting Road Accidents with Web Scraping and Machine Learning Techniques

Luan Sinanaj () and Lejla Abazi Bexheti ()
Additional contact information
Luan Sinanaj: South East European University
Lejla Abazi Bexheti: South East European University

A chapter in Economic Recovery, Consolidation, and Sustainable Growth, 2023, pp 781-792 from Springer

Abstract: Abstract In recent decades, with the rapid growth of urbanization, the use of vehicles has increased and urbanization has not always been adapted to road infrastructure. This, in turn, has led to an increase in traffic and road accidents, especially in the most populated areas. Regarding these problems, there is a need to focus on accident prevention by predicting the accident areas. Knowing the accident areas can facilitate the study of why they occur and improve policies to prevent them. The primary purpose of this research is to build an application using Python to identify accident areas in the state of Albania. Accident information is extracted through the application and Web Scraping techniques from some selected servers of the top media in Albania and it is processed to find the areas/cities where it happened. As a result of this research, an application is implemented. From the results obtained from this application, its accuracy (precision) in finding accident areas turns out to be 67%. The result is good and hopeful for further work in the future and for the improvement of this application. The predicted results of our application for the number of accidents are a little closer to the results of the accident reports published by the state of Albania.

Keywords: Accident areas/cities; Accident area prediction; Python application; Web scraping (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-3-031-42511-0_51

Ordering information: This item can be ordered from
http://www.springer.com/9783031425110

DOI: 10.1007/978-3-031-42511-0_51

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().