Actions speak as loud as words: predicting relationships from social behavior data

摘要: In recent years, new studies concentrating on analyzing user personality and finding credible content in social media have become quite popular. Most such work augments features from textual with representing the user's ties tie strength. Social are crucial understanding network people a part of. However, is extremely useful topics discussed of individual. We bring dimension to this type analysis methods compute individuals strength each dimension. present genre behavioral that able capture "function" specific relationship without help features. Our novel based statistical properties communication patterns between as reciprocity, assortativity, attention latency. introduce methodology for determining how can be compared features, show, using Twitter data, our used contextual information very accurately. Conversely, we also demonstrate determine attributes related an