Spatio-temporal query contextualization for microtext retrieval in socialmedia

摘要

Generally, texts on the social media (eg, Twitter and Facebook) are too short (microtexts) tornunderstand the meaning and to search for relevant texts. It is difficult for the conventional informationrnretrieval systems to conduct the searching tasks. Thereby, in this paper, we propose arnnovel approach on query contextualization by integrating all possible microtexts by consideringrnspatio-temporal contexts. The proposed approach consists of two steps, which are (i) to understandrnand process microtexts in social media and (ii) to reformulate the queries for searching forrnrelevant microtexts in these social media. To evaluate the performance of the query contextualizationrnapproach,microtexts from Twitter have been collected during 4months.