Methods of treatment (case reports)

Abstract

The increased popularity of micro-blogging applications together with the widespread of location-aware devices have resulted in the creation of large streams of geo-tagged data. Such data provides a great opportunity for researchers to explore event detection and prediction. In particular, road traffic detection and prediction are of great importance to various applications, i.e. Intelligent Transportation Systems. Current works proposed traffic jam detection from a single data source with a single language. However, for countries where the residents are speaking two, or more, languages and are interacting with more than one online social platform, single-language and single-source systems are insufficient to capture the necessary online information. Therefore, in this paper, we introduce SNSJam, an effective system to detect and predict road traffic jams using cross-lingual (English and Arabic) data collected from multiple dynamic sources, such as Twitter and Instagram. SNSJam classifier not only detect traffic events, but also identifies the causes of traffic jams. To identify the location of a traffic event, a Location Recognizer is developed that extracts locations from text and GPS of the post. Additionally, the Location Recognizer supports user-defined locations, which are common names among people. Our experiments show that by combining Arabic and English data streams, the accuracies of traffic events detection and prediction are significantly improved as compared with that of the individual languages. Additionally, combining data streams from multiple sources (Twitter and Instagram) further improved the accuracies of event detection and prediction over any individual source. A visualization interface was developed to show the detected spatio-temporal traffic events on a dynamic map. The detection and prediction results are validated against ground truth data obtained from the concerned authorities in the UAE.