4.6 Article

Iktishaf plus : A Big Data Tool with Automatic Labeling for Road Traffic Social Sensing and Event Detection Using Distributed Machine Learning

Journal

SENSORS
Volume 21, Issue 9, Pages -

Publisher

MDPI
DOI: 10.3390/s21092993

Keywords

smart cities; big data; event detection; road traffic; distributed machine learning; automatic labeling; social media; data analytics; social media analytics; Arabic tweets

Funding

  1. Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah [RG-11-611-40]

Ask authors/readers for more resources

This paper focuses on detecting road traffic-related events using big data and distributed machine learning, particularly in Arabic language Twitter data. The study demonstrates the effectiveness of using support vector machines, naive Bayes, and logistic regression-based classifiers to detect and validate real events in Saudi Arabia, showcasing the potential of Twitter media in detecting important events without prior knowledge.
Digital societies could be characterized by their increasing desire to express themselves and interact with others. This is being realized through digital platforms such as social media that have increasingly become convenient and inexpensive sensors compared to physical sensors in many sectors of smart societies. One such major sector is road transportation, which is the backbone of modern economies and costs globally 1.25 million deaths and 50 million human injuries annually. The cutting-edge on big data-enabled social media analytics for transportation-related studies is limited. This paper brings a range of technologies together to detect road traffic-related events using big data and distributed machine learning. The most specific contribution of this research is an automatic labelling method for machine learning-based traffic-related event detection from Twitter data in the Arabic language. The proposed method has been implemented in a software tool called Iktishaf+ (an Arabic word meaning discovery) that is able to detect traffic events automatically from tweets in the Arabic language using distributed machine learning over Apache Spark. The tool is built using nine components and a range of technologies including Apache Spark, Parquet, and MongoDB. Iktishaf+ uses a light stemmer for the Arabic language developed by us. We also use in this work a location extractor developed by us that allows us to extract and visualize spatio-temporal information about the detected events. The specific data used in this work comprises 33.5 million tweets collected from Saudi Arabia using the Twitter API. Using support vector machines, naive Bayes, and logistic regression-based classifiers, we are able to detect and validate several real events in Saudi Arabia without prior knowledge, including a fire in Jeddah, rains in Makkah, and an accident in Riyadh. The findings show the effectiveness of Twitter media in detecting important events with no prior knowledge about them.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available