Social media sites could do more than let you share updates about what you’re doing right now or what you ate for lunch — they could provide a new way for automakers identify safety and performance problems.
The presence of certain “automotive smoke words” in vehicle-related posts on blogs, Twitter, bulletin boards and other sites can indicate potential defects that car companies need to address, researchers at Virginia Tech’s Pamplin College of Business found. These words include “ABS” (for “anti-lock brakes”), “retract,” “overheat,” “persistent” and “gearbox.”
“A lot of useful but hidden data on vehicle quality is embedded in social media that is largely untapped by auto manufacturers,” said Alan Abrahams, assistant professor of business information technology, who led the study together with Weiguo Fan, professor of accounting and information systems.
Abrahams and Fan developed a computer-based decision support system that can sift useful information about potential defects and safety problems from the vast amounts of unstructured and dynamic information people post online about cars. That system could help automakers find valuable nuggets of information that aren’t always easy to identify online.
“In some domains — for example, retail, hospitality and retail box office — sentiment analysis has been successfully used to find product complaints,” Abrahams said. “In the automotive domain, however, we discovered that conventional sentiment determination may be a poor indicator of whether a defect exists and how critical it is for safety.”
In other words, general online questions, gripes and comments about cars don’t always indicate a potential safety defect. But vehicle-related posts with certain smoke words can raise a red flag.
“Vehicle quality management professionals would greatly benefit in terms of productivity by employing a vehicle defect discovery system like ours to sift defects from unrelated posts,” Abrahams said.