With　the　advent　of　the　intelligence　era,　the　usage　and　investment　for　chips　have　risen　year　by　year,　causing　the　demand　for　chip　security.　Machine　learning　(ML)　analysis　has　made　progress　as　a　pre-silicon　hardware　Trojan　(HT)　detection　technology.　Whereas　the　performance　of　existing　methods　almost　relies　on　the　accuracy　of　multi-feature　representation,　moreover,　it　is　difficult　to　extract　features　manually　and　easily　cause　unstable　classifier　performance　(namely　uncertainty).　In　this　paper,　an　automatic　feature　extraction　detecting　model　is　first　proposed,　named　HTtext,　which　generates　simple　path　sentences　from　chip　netlists　and　employs　TextCNN,　a　deep　learning　algorithm,　to　distinguish　HT　circuits.　The　pre-training　for　TextCNN　only　uses　the　automatic　single-feature　calculation　to　avoid　the　uncertainty　problem.　Additionally,　the　model　can　obtain　non-repetitive　HT　component　information　expression,　which　satisfies　the　stable　detection　performance.　To　measure　the　efficiency　and　balance　of　the　model,　the　paper　proposes　the　concept　of　the　Stability　Efficiency　Index　(SEI).　In　the　experimental　results　for　the　benchmark　netlists,　not　only　the　average　accuracy　(ACC)　in　TextCNN　is　as　high　as　99.26%,　but　also　its　SEI　value　ranks　first　in　all　comparison　classifiers,　which　proves　that　the　proposed　HTtext　model　has　high　stability　in　generality.　©　2021　IEEE.