ATAM: Arabic Traffic Analysis Model for Twitter

Abstract

Harvesting Twitter for insight and meaning in what is called sentiment analysis (SA) is a major trend stemming from computational linguistics and AI. Industry and academia are interested in maximizing efficiency while mining text to attain the most currently available data and crowdsourcing opinions. In this study, we present the ATAM model for traffic analysis using the data available on Twitter. The model comprises five components that start with data streaming and collection and ends with the road incident prediction through classification. The classification of data is done using a lexiconbased method. The predicted classes are as follows: safe, needs attention, dangerous, and neutral. The data were collected for three months in the city of Riyadh, Saudi Arabia. The model was applied on 10k tweets with an overall accuracy of the model classifying all four classes of 82%.

Literature Study: Highway Traffic Management with Sentiment Analysis and Data Mining

“…The results of the literature review carried out by researchers can be in the form of comparative analysis of research results, research gaps, and the advantages and disadvantages of the three studies [13][15][16] that have been described in Table 1. The results of the literature review can be seen in Table 2 below: After determining the results from the three articles [13][15] [16], their strengths and weaknesses were reviewed, as shown in Table 4.…”

“…This literature review study was conducted to determine whether sentiment analysis and data mining algorithms can prevent road traffic congestion through road traffic management. The literature review was conducted on three studies [13] [15] [16] by analyzing the algorithms and cases to be solved as can be seen in Table 1…”

Ontology-Based Traffic Accident Information Extraction on Twitter In Indonesia

“…Tabel 1 shows several works that extract information from Twitter for analysing traffic event. In the majority, those papers classify the Twitter data into several categories using machine learning and deep learning [2,12,11,1,4,18]. Those papers generally predict whether the Twitter data are related to traffic event or not.…”

“…TensorFlow performance is better than the SVM classifier. Classification of trafficrelated events based on lexicon methods is done by Al Farasani et al [4] for Twitter in Riyadh, Saudi Arabia. They divided data into five categories, namely safe, needs attention, dangerous, and neutral.…”