Pedesis SVM for Depression Screening by Tweeting Activities in Bahasa Indonesia

Pedesis SVM for Depression Screening by
Tweeting Activities in Bahasa Indonesia
(Telkom University, Indonesia)
Houw Liong Thee
(Telkom University, Indonesia)
Henndy Ginting
Faculty of Psychology, Maranatha Christian University, Indonesia

Depression is a global crisis and over 80% of the people that have symptomps of clinical depression are not receiving any specific treatment for their depression because depression is an invisible disease. That is why it is needed to proactively detect depression.Twitter is one of the tops social medias. If we compare what people talk about on twitter, the general purpose of using twitter, and the symptoms of depression, we may use twitter as a tool for depression screening. Neuman using “pedesis” discovereda system that could detect a pattern in writing with English and metaphor, and this pattern was correlated with depression. But Neuman’s system can not detect whether the writer depressed or not. De Choudhury using SVM found another system that could measure depression in a population based on their behaviors (e.g., comments in English) in twitter. But De Choudhury’s system did not include the metaphor. There is no tool for screening depression via twitting activities in Bahasa Indonesia. This studybuild a tools for depression screening via tweeting activities in Bahasa Indonesia using the combination of those systems (Pedesis and SVM).This combination improvesaccuracy because both of the methods are complement each other. Construction of features for thisnew system is described in this study.
Keywords: Depression, twitter, pedesis, SVM



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s