Recognizing semantic correlation in image-text weibo via feature space mapping.

•We make effort on recognizing semantic correlation between image and text in image-text weibo.•We make an in-depth study of weibo text from language cognitive and computational views and extract textual-linguistic features, from weibo text.•We select visual feature space as the unified one and the genetic mapping algorithm is used to transform textual-linguistic and social features into the unified feature space to eliminate the heterogeneity and incomparability of the different types of features.