A Hybrid Model For Information Retrieval From Microblogs During Disaster

When the disaster occurs, the social network site such as Twitter is increasingly being used for helping direct rescue operations. This article describes the methods we used in the Fire2017. We regarded the distinction of need-tweets and availability-tweets as classification tasks, and the logistic regression and Support Vector Machine are used to decide the type of the tweets. In the need and availability matching, we regard it as an information retrieval task, using the retrieval model to complete the task.