Understanding loneliness in social awareness streams: Expressions and responses

Abstract

We studied the experience of loneliness as communicated by thousands of people on Twitter. Using a data set of public Twitter posts containing explicit expressions of loneliness, we qualitatively developed a categorization scheme for these expressions, showing how the context of loneliness expressed on Twitter relates to existing theories about loneliness. A quantitative analysis of the data exposed categories and patterns in communication practices around loneliness. For example, users expressing more severe, enduring loneliness are more likely to be female, and less likely to include requests for social interaction in their tweets. Further, we studied the responses to expressions of loneliness in Twitter's social settings. Deriving from the same dataset, we examined factors that correlate with the existence and type of response, showing, for example, that men were more likely to receive responses to lonely tweets, and expressions of enduring loneliness are critically less likely to receive responses.