Cyberspace and Real-World Behavioral Relationships: Towards the Applications of Interest Search Queries to Identify Individuals At-Risk for Suicide.

摘要

The Internet has become an integral and pervasive aspect of society. Not surprisingly, the growth of ecommerce has led to focused research on identifying relationships between user behavior in cyberspace and the real world - retailers are tracking items customers are viewing and purchasing in order to recommend additional products and to better direct advertising. As the relationship between online search patterns and real-world behavior becomes more understood, the practice is likely to expand to other applications. Indeed, Google Flu Trends has implemented an algorithm that accurately charts the relationship between the number of people searching for flu-related topics on the Internet, and the number of people who actually have flu symptoms in that region. Because the results are real-time, studies show Google Flu Trends estimates are typically two weeks ahead of the Center for Disease Control. The Air Force has devoted considerable resources to suicide awareness and prevention. Despite these efforts, suicide rates have remained largely unaffected. The Air Force Suicide Prevention Program assists family, friends, and co-workers of airmen in recognizing and discussing behavioral changes with at-risk individuals. Based on other successes in correlating behaviors in cyberspace and the real world, is it possible to leverage online activities to help identify individuals that exhibit suicidal or depression-related symptoms. This research explores the notion of using Internet search queries to classify individuals with common search patterns. Text mining was performed on user search histories for a one-month period from nine Air Force installations. The search histories were clustered based on search term probabilities, providing the ability to identify relationships between individuals searching for common terms. Analysis was then performed to identify relationships between individuals searching for key terms associated with suicide, anxiety, and post-traumatic stress.