According to Prof. Yair Neuman, a member of the BGU Homeland Security Institute, “School shooters present a challenge to both forensic psychiatry and law enforcement agencies. There is currently no clear consensus or clinical diagnosis that can be used for screening shooters. Finding a single shooter in a large population, as well as a lack of clinical diagnosis before an occurrence, adds to the complexity.”
The study discusses the text-based computational personality-profiling tool, which uses “vector semantics.” This entails constructing a number of vectors that represent personality dimensions and disorders. These are analyzed automatically by computer to measure the similarity with texts written by the human subject.
As Neuman explains, “For example, an investigator may want to measure the extent in which narcissism is manifested in a text. First, we define a vector of words representing this personality such as ‘arrogant,’ ‘manipulative,’ ‘egocentric,’ and ‘insensitive.’ The computer measures the distance between the vector of words comprising our target text and those representing narcissism in a high-dimensional semantic space. The closer the vectors appear, the higher the writer’s narcissistic ranking.”
BGU researchers chose the writings of six shooters involved in a number of high-profile incidents worldwide, including the Virginia Tech Massacre in 2007. Subsequently, they analyzed and compared these writings with those of 6,000 bloggers and used the computer to identify the shooters.
While pinpointing a single person was not the goal, the tool was able to reduce the pool of suspects to only three percent of the original sample, which included the writings of all six shooters. This demonstrates the ability of intelligent technology to reduce the effort needed to identify shooters or even solo terrorists. Because the methodology is automatic, it enables screening a massive number of texts in a short time, which could help in detection.
As Neuman said, “While ethical considerations are inevitable, we can definitely imagine a situation in which parents give the school permission to scan their teenagers’ social media pages under certain limitations. In this context, using our automatic screening procedure, a qualified psychiatrist or psychologist who is trained may automatically get red flag warnings for students whose texts express a high level of potential danger. The proposed methodology does not pretend to solve the enormous difficulties in profiling and identifying school shooters, but modestly adds another tool to the tool kit of forensic psychiatry and law enforcement agencies. We believe our methodology can gain more validity with the ranking/prioritization process of suspects, similar to the automatic identification of sexual predators created to prioritize an investigation.”