Steps Toward Automatic Understanding of the Function of Affective Language in Support Groups

Abstract

Understanding expression of emotions in support forums has great value and NLP methods are key to automating this. Many approaches use subjective categories which are more fine-grained than a straightforward polarity-based spectrum. However, the definition of such categories is non-trivial, and we argue for a need to incorporate communicative elements even beyond subjectivity. To support our position, we report experiments on a sentiment-labelled corpus of posts from a medical support forum. We argue that a more fine-grained approach to text analysis important, and also simultaneously recognising the social function behind affective expressions enables a more accurate and valuable level of understanding.