Mining Association Language Patterns for Negative Life Event Classification

Negative life events, such as death of a family member, argument with a spouse and loss of a job, play an important role in triggering depressive episodes. Therefore, it is worth to develop psychiatric services that can automatically identify such events. In this paper, we propose the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with negative life events into predefined categories (e.g., Family, Love, Work). The language patterns are discovered using a data mining algorithm, called association pattern mining, by incrementally associating frequently co-occurred words in the sentences annotated with negative life events. The discovered patterns are then combined with single words to train classifiers. Experimental results show that association language patterns are significant features, thus yielding better performance than the baseline system using single words alone.