Investigating “Texting while Driving” Behavior at Different Roadway Configurations Using a Driving Simulator Setting

This study investigates the safety impact of distracted driving (texting while driving) for different roadway configurations (intersections, segments, freeways, and roundabouts; urban, suburban, and rural sections; and straight and curved road cross-sections) and various lighting conditions (nighttime and daytime) using a driving simulator. The study took place at Western Kentucky University in Bowling Green, KY. Fifty participants (30 young adults, 18 to 25 years old; 20 middle-/old age adults, 26 to 70 years old) drove the simulator, for approximately 10 min each. Video recordings and behavior observations (e.g., recording single longest off-road eye glance while texting and driving) were further documented. While texting and driving at the roundabout, significant differences were found between the mean lane positions of the young and middle-/old age groups. Additionally, a slightly higher speed variance for middle-/old age drivers existed while texting and driving on freeways during the daytime compared with their younger counterparts. Comparisons with the safe stopping sight distance revealed potential safety risks for all texting while driving situations for both age groups compared with nontexting situations. On average, participants with a higher distracted-driving crash-risk expended 0.676 more seconds glancing off-road than lower distracted-driving crash-risk participants. Furthermore, on average, lower-risk participants had a 3.99 mph speed standard deviation compared with the 5.34 mph speed standard deviation of higher-risk participants. It should be noted that the top five higher-risk drivers were from the middle/older population, whereas the top five lower-risk drivers were from the younger population.

Improving the effectiveness of anti-texting and driving PSAs: the effect of ad elements on attitude change

Purpose Public service announcements (PSAs) are frequently used tools to try to change attitudes and behaviors on social issues, including texting and driving, which has been social problem for over a decade. However, the effectiveness of such PSA campaigns often meet with varying degrees of success, suggesting changes to current anti-texting and driving campaigns are needed. This study aims to examine how to design more effective anti-texting and driving PSA campaigns by identifying the elements of existing campaigns that have the strongest impact on attitude change. Design/methodology/approach In total, 682 respondents from Amazon’s Mechanical Turk participated in an online study in which they evaluated 162 real-world anti-texting and driving ads. Respondents evaluated the ads on various ad elements (i.e. type of appeal, source of emotion, discrete emotions and perceived creativity), as well as their attitudes toward the issue after seeing the ad. Findings PSAs that use emotional (vs rational) appeals, evoke emotion through imagery (vs text) and/or use fear (vs disgust, anger or guilt) result in the largest changes in attitude. In addition, more creative PSAs are more effective at changing attitudes. Originality/value Overall, the results provide useful information to social marketers on how to design more effective anti-texting and driving campaigns.

“Texting & Driving” Detection Using Deep Convolutional Neural Networks

The effects of distracted driving are one of the main causes of deaths and injuries on U.S. roads. According to the National Highway Traffic Safety Administration (NHTSA), among the different types of distractions, the use of cellphones is highly related to car accidents, commonly known as “texting and driving”, with around 481,000 drivers distracted by their cellphones while driving, about 3450 people killed and 391,000 injured in car accidents involving distracted drivers in 2016 alone. Therefore, in this research, a novel methodology to detect distracted drivers using their cellphone is proposed. For this, a ceiling mounted wide angle camera coupled to a deep learning–convolutional neural network (CNN) are implemented to detect such distracted drivers. The CNN is constructed by the Inception V3 deep neural network, being trained to detect “texting and driving” subjects. The final CNN was trained and validated on a dataset of 85,401 images, achieving an area under the curve (AUC) of 0.891 in the training set, an AUC of 0.86 on a blind test and a sensitivity value of 0.97 on the blind test. In this research, for the first time, a CNN is used to detect the problem of texting and driving, achieving a significant performance. The proposed methodology can be incorporated into a smart infotainment car, thus helping raise drivers’ awareness of their driving habits and associated risks, thus helping to reduce careless driving and promoting safe driving practices to reduce the accident rate.