Twitter Analysis for Depression on Social Networks based on Sentiment and Stress

Detecting words that express negativity in a social media message is one step towards detecting depressive moods. To understand if a Twitter user could exhibit depression over a period of time, we applied techniques in stages to discover words that are negative in expression. Existing methods either use a single step or a data subset, whereas we applied a multi-step approach which allowed us to identify potential users and then discover the words that expressed negativity by these users. We address some Twitter specific characteristics in our research. One of which is that Twitter data can be very large, hence our desire to be able to process the data efficiently. The other is that due to its enforced character limitation, the style of writing makes interpreting and obtaining the semantic meaning of the words more challenging. Results show that the sentiment of these words can be obtained and scored efficiently as the computation on these dataset were narrowed to only these selected users. We also obtained the stress scores which correlated well with negative sentiment expressed in the content. This work shows that by first identifying users and then using methods to discover words can be a very effective technique.