Extraction and Analysis of Social Networks Data to Detect Traffic Accidents

Abstract

Traffic accident detection is an important strategy governments can use to implement policies intended to reduce accidents. They usually use techniques such as image processing, RFID devices, among others. Social network mining has emerged as a low-cost alternative. However, social networks come with several challenges such as informal language and misspellings. This paper proposes a method to extract traffic accident data from Twitter in Spanish. The method consists of four phases. The first phase establishes the data collection mechanisms. The second consists of vectorially representing the messages and classifying them as accidents or non-accidents. The third phase uses named entity recognition techniques to detect the location. In the fourth phase, locations pass through a geocoder that returns their geographic coordinates. This method was applied to Bogota city and the data on Twitter were compared with the official traffic information source; comparisons showed some influence of Twitter on the commercial and industrial area of the city. The results reveal how effective the information on accidents reported on Twitter can be. It should therefore be considered as a source of information that may complement existing detection methods.

Advancements in Machine Learning and Data Mining Techniques for Collision Prediction and Hazard Detection in Internet of Vehicles

“…Suat-Rojas et al [14] propose a low-cost road accident identification technique using social network mining and Twitter data, showing its potential impact on supplementing traditional detection methods. Yet, the accuracy of this method could be influenced by the reliability of social media data and the potential for misinformation.…”

“…[13] Transfer learning model for vehicle collision prediction Feature analysis, IoV dataset Limited to predicting vehicle collisions Suat-Rojas, N., et al[14] Low-cost technique for road accident identification Social network mining, vectorial repr.…”

Smart Cities, Smarter Roads: A Review of Leveraging Cutting-Edge Technologies for Intelligent Event Detection from Social Media

“…Subsequently, they developed a mobile application to send notifications to users based on classified tweets about traffic. Suat-Rojas et al [27] built a classifier to detect accidents from tweets in the Spanish language. They classified tweets into accident and non-accident.…”

“…[22] Traffic-relevant, traffic-irrelevant NB, dictionary of frequently occurring words [23] Heavy-vehicle, traffic-jam, park-footpath autometer, wrong-side, breakdown, jump-signal, U-turn, no-parking. Random forest classifier [24] Weather Random forest classifier [40] Roadwork traffic jam, freight traffic, road closure, weather, accident Dictionary, clustering algorithm [41] Earthquakes, forest fires, floods, and droughts Checking a set of predefined weighed keywords, KNN algorithm [25] City-related events CRF model, dictionary-based spotting [26] Traffic-congested and non-traffic-congested NB [27] Accident and non-accident SVM, NB, RF and Neural Networks [29] Traffic-relevant, traffic-irrelevant LDA [30] Leisure, sports, music, movies, art, and other LDA [31] Traffic, non-traffic OLDA [32] Roadwork accidents, weather, special events, obstacle vehicles. sLDA, SNB [33] Accidents, traffic jams, weather LDA, SVM, NB, K-Nearest…”

A Comprehensive Analysis of Privacy-Preserving Solutions Developed for Online Social Networks

“…The sharing and analysis of G have a wide range of benefits for people. For example, better service/product recommendations by community-based clustering [4], information diffusion to targeted users [5], appropriate friend recommendations [6], point of interest recommendations [7], traffic incidents analysis [8], influence spreading [9], and route recommendations [10], to name a few. The usage of SN offers users many other benefits such as increasing their reputation, influencing others, recieving brand offers, receiving support, and connecting with a huge community [11] .…”