Unfolding social content evolution along time and semantics

Abstract In the context of social media, the unstructured and dynamic nature of exchanged data and the information overload contribute to the growth of the number of research works proposing methods to improve performance of intelligent analytics services considering both time and semantics of the shared content. The presented paper focuses on the definition of a knowledge tracking framework to answer questions, such as “What is the semantic evolution of a topic (or news) along the time?”, “How did we arrive to a specific event?”, “What is the evolution of the topics of interest of a user?”, and so on. Our interest is about the elicitation of temporal patterns revealing the evolution of concepts along the time from a social media data stream; we focus on Twitter. Such patterns can be extracted at different levels of abstraction by considering different-sized time intervals and different scopes driven by the conceptualization of users’ queries. To address the proposed aim, we extend Temporal Concept Analysis and we use Description Logic to reason on semantically represented tweet streams. The evaluation activity reveals promising results from both sides quantitative and qualitative.