Monitoring youth depression risk in Web 2.0

摘要

Purpose – Social networking sites have in recent years become an increasingly popular avenue foryoung people to express and to share their thoughts, views, and emotions. When young people areemotionally distressed for instance, instead of the traditional channel of consulting friends, parents orspecialists, social networking blogs may provide a channel to share and release their emotions andintentions. The objective of the paper is to explore the use of text mining and data warehousingtechnologies to identify and monitor bloggers who are depressed and may be at risk of suicide, selfharm or harming others. Design/methodology/approach – The paper first provides a literature review on relevant work inaffective and emotional content text mining and relevant suicide research. An algorithm based on aweighted dictionary text search algorithm was developed to identify at risk bloggers to illustrate theviability of the system. An example that compares the percentage of at-risk bloggers of three differentcountries – Australia, the UK and New Zealand-- from a sample blog population is provided. Findings – The results show that it is possible to use text mining technologies to identify depressedbloggers. However, there is a need for future research to improve identification and remove falsealarms. Practical implications – The ability to identify at-risk bloggers and to provide appropriateinterventions could be critical in avoiding tragic consequences. Such a system could provide ane-monitoring service for various social agencies to engage with potentially at-risk bloggers. Originality/value – The current research represents pioneer work in monitoring depression risk inweblogs – research on monitoring at-risk bloggers is rather limited.