Recently,　Graph　Convolutional　Neural　Network　(GCN)　is　widely　used　in　text　classification　tasks,　and　has　effectively　completed　tasks　that　are　considered　to　have　a　rich　relational　structure.　However,　due　to　the　sparse　adjacency　matrix　constructed　by　GCN,　GCN　cannot　make　full　use　of　context-dependent　information　in　text　classification,　and　cannot　capture　local　information.　The　Bidirectional　Encoder　Representation　from　Transformers　(BERT)　has　been　shown　to　have　the　ability　to　capture　the　contextual　information　in　a　sentence　or　document,　but　its　ability　to　capture　global　information　about　the　vocabulary　of　a　language　is　relatively　limited.　The　latter　is　the　advantage　of　GCN.　Therefore,　in　this　paper,　Mutual　Graph　Convolution　Networks　(MGCN)　is　proposed　to　solve　the　above　problems.　It　introduces　semantic　dictionary　(WordNet),　dependency　and　BERT.　MGCN　uses　dependency　to　solve　the　problem　of　context　dependence　and　WordNet　to　obtain　more　semantic　information.　Then　the　local　information　generated　by　BERT　and　the　global　information　generated　by　GCN　are　interacted　through　the　attention　mechanism,　so　that　they　can　influence　each　other　and　improve　the　classification　effect　of　the　model.　The　experimental　results　show　that　our　model　is　more　effective　than　previous　research　reports　on　three　text　classification　data　sets.　©　2021　Institute　of　Physics　Publishing.　All　rights　reserved.