In　this　paper,　we　investigate　a　typical　clustering　technology,　namely,　Gaussian　mixture　model　(GMM)-based　approach,　for　user　interest　prediction　in　social　networks.　The　establishment　of　the　model　follows　the　following　process:　collect　dataset　from　4613　users　and　more　than　16　million　messages　from　Sina　Weibo,　obtain　each　user＇s　interest　eigenvalue　sequence　and　establish　GMM　model　to　clustering　users.　In　theory　and　experiment,　this　approach　is　feasible.　The　GMM-based　approach　considers　the　prediction　accuracy　and　consuming　time.　A　series　of　experiments　are　conducted　to　validate　the　feasibility　and　efficiency　of　the　proposed　solution　and　whether　it　can　achieve　a　higher　accuracy　of　prediction　compared　with　other　approaches,　such　as　SVM　and　K-means.　Further　experiments　show　that　GMM-based　approach　could　produce　higher　prediction　accuracy　of　93.9%,　thus　leveraging　computation　complexity.　©　2015　IEEE.