Characterizing negative sentiments in at-risk populations via crowd computing: a computational social science approach

Drawing on psychological theory, we created a new approach to classify negative sentiment tweets and presented a subset of unclassified tweets to humans for categorization. With these results, a tweet classification distribution was built to visualize how the tweets can fit in different categories. The approach developed through visualization and classification of data could be an important base to measure the efficiency of a machine classifier with psychological diagnostic criteria as the base (Thelwall et al. in J Assoc Inf Sci Technol 62(4):406–418, 2011 ). Nonetheless, this proposed system is used to identify red flags in at-risk population for further intervention, due to the need to be validated through therapy with an expert.