Life-Saving Israeli Tech Prevents Suicide Using Big Data

Israeli researchers developed a method to analyze big data and social media to detect suicide risk in its earliest stages.

By Yakir Benzion, United With Israel

Researchers at the Technion Institute and Hebrew University of Jerusalem have developed an innovative new technology that analyzes massive amounts of data on social media to detect suicidal tendencies.

They hope their advance will reduce the more than one million suicides that are committed worldwide each year.

This new technology detects at-risk groups within the overall population and is not limited to identifying people who are already being treated for mental health issues. The system combines machine learning and natural language processing with theoretical and analytical tools from the realm of psychology and psychiatry, using layered neural networks.

“We now understand that detecting suicidal tendencies cannot depend only on explicit expressions of distress (such as: ‘I want to die’) or on official medical records such as physiological data from brain scans, psychiatric evaluations, and other data from medical files,” said Technion Professor Roi Reichart, an expert in natural language processing.

“Attempts to predict suicide attempts based on demographic, psychological, and medical data have not been particularly successful despite five decades of intensive research. Therefore, we realized that we had to approach the challenge from different directions simultaneously,” Reichart said.

Clinical psychologist Dr. Yaakov Ophir of Hebrew University said the group got the idea following the tragic death of a 16-year-old high school student who committed suicide because he was bullied online and in person.

“It quickly became apparent that detecting suicidal tendencies early enough requires interdisciplinary research that includes researchers from different fields. That is how this multi-university and multi-disciplinary group was formed,” Dr. Ophir said.

With some 500 suicides annually in Israel, it’s not a leading cause of death among the general population, but it is the number one cause for Israelis under the age of 24.

Traditional help – psychological, psychiatric and social – are effective preventing suicides, but they are only applied in cases where the problem has already been diagnosed and the person is receiving treatment.

Although it’s a complex challenge, the researchers realized that being able to recognize suicidal tendencies in the general population could help identify many at-risk people do not seek help.

The researchers discovered that people with real suicidal tendencies rarely use explicitly alarming words in their posts (such as “death,” “kill” or “suicide”). More often, they use negative descriptive words (“bad,” “worst”), curse words (“f***ing,” “b**ch”), expressions of emotional distress (“sad,” “hurt,” “cry,” “mad”), and descriptions of negative physiological states (“sick,” “pain,” “surgery,” “hospital”).

On the opposite side, previous studies show that people with no suicidal tendencies tend to express more positive emotions and experiences.

Altogether, the researchers analyzed more than 80,000 Facebook posts written by adults in the U.S., comparing their language usage patterns with their scores on a wide range of valid psychological indices.

“The power of the natural language processing-based algorithm lies in its ability to analyze enormous quantities of linguistic clues – something that humans are not able to do,” said Refael Tikochinski, a doctoral student in computational psychology. “In this project, we integrated cutting-edge attention-based neural network modeling for text representation, with layered neural networks for classification.”

Prof. Christa Asterhan, an educational psychologist, said the research helps in identifying people in distress and providing help on time, and shows the strength of collaboration across disciplines to use advanced computational techniques on big data to solve problems “that were hitherto not possible.”

“I have a problem with clichés,” concluded Dr. Ophir, “but in this case I believe that, at the end of the day, the breakthrough we achieved is capable of saving lives. I hope that this research is a harbinger of hope in the field of mental health.”