Investigating the role of socio-economic factors in comprehension of traffic signs using decision tree algorithm.

Introduction: Drivers' ability to comprehend the meaning of traffic signs is essential to safe driving. Drivers' personal characteristics are believed to play a crucial role in determining drivers' comprehension of traffic signs.

Method: This study investigates the role of age, gender, marital status, license category, educational level, driving experience, monthly income, and number of traffic violation during the last five years in drivers' comprehension of 39 posted traffic signs in the city of Irbid, Jordan. These signs include 15 regulatory signs, 17 warning signs, and 7 guidance signs. A total of 400 paper-based surveys were completed by drivers with different socio-economic characteristics. Subsequently, a decision tree was created for each category of traffic signs to identify the most influential factors affecting drivers' comprehension. Each tree was created twice; once using the whole data set for building and validating the tree, and a second time only using 80% of the data for building and 20% for validating.

Results: The accuracy of the generated trees in predicting drivers' comprehension of regulatory, guidance, and warning traffic signs was 70%, 71%, and 66.5%, respectively, when using the whole data for building and validating the tree, and was 65%, 62.5%, and 61.3%, respectively, when using only 80% of the data for building and the remaining for validating.

Conclusions: The generated decision trees showed that driving experience, marital status, age, and education background are the most influential factors in determining drivers' comprehension of traffic signs as they were primary splitters in such trees.

Practical Application: The rules obtained from the decision tree can be utilized by transportation agencies to determine the drivers who need help with understanding the road traffic signs.