Sentiment　analysis　of　social　media　texts　has　become　a　research　hotspot　in　information　processing.　Sentiment　analysis　methods　based　on　the　combination　of　machine　learning　and　sentiment　lexicon　need　to　select　features.　Selected　emotional　features　are　often　subjective,　which　can　easily　lead　to　overfitted　models　and　poor　generalization　ability.　Sentiment　analysis　models　based　on　deep　learning　can　automatically　extract　effective　text　emotional　features,　which　will　greatly　improve　the　accuracy　of　text　sentiment　analysis.　However,　due　to　the　lack　of　a　multi-classification　emotional　corpus,　it　cannot　accurately　express　the　emotional　polarity.　Therefore,　we　propose　a　multi-classification　sentiment　analysis　model,　GLU-RCNN,　based　on　Gated　Linear　Units　and　attention　mechanism.　Our　model　uses　the　Gated　Linear　Units　based　attention　mechanism　to　integrate　the　local　features　extracted　by　CNN　with　the　semantic　features　extracted　by　the　LSTM.　The　local　features　of　short　text　are　extracted　and　concatenated　by　using　multi-size　convolution　kernels.　At　the　classification　layer,　the　emotional　features　extracted　by　CNN　and　LSTM　are　respectively　concatenated　to　express　the　emotional　features　of　the　text.　The　detailed　evaluation　on　two　benchmark　datasets　shows　that　the　proposed　model　outperforms　state-of-the-art　approaches.