【目的/意義】基于離散情感理論,對電商平臺在線評論中所含不同離散情感的分布規律進行探究,發掘其對于營銷管理的實踐意義。【方法/過程】以手機這一搜索型產品的海量中文評論為研究對象,以情感認知模型OCC模型為情感分類依據,通過深度學習的方法構建離散情感語料庫,并在此基礎上對不同評論星級、不同的商品購買和評論發布的時間間隔中,評論所包含離散情感的分布特征進行了深入的研究。【結果/結論】研究發現:包含不同離散情感的評論在不同評論星級中的分布情況差別較大,在不同時間間隔中的分布曲線卻大致相同,雖都與"長尾分布"非常類似,但仍有細微差別。

【Purpose/significance】Based on Discrete Emotion Theory, this paper makes a thorough inquiry into the distribution of different discrete emotions contained in online reviews of e-business platform, and explores its practical significanceto marketing management.【Method/process】By taking the massive Chinese reviews of mobile phone which is a kind ofsearch goods as the research object, and using the OCC model which is a kind of emotional cognition model as the basis ofemotion classification, the paper constructs a discrete emotional corpus through the depth learning method, and on this basis, the distribution characteristics of different discrete emotions contained in different star reviews and in different time in-tervals between product purchase time and product release time have been studied and analyzed in detail.【Result/conclusion】The results show that the distributions of reviews containing different discrete emotions are different in different starreviews, and the distribution curves in different time intervals are almost the same, although they are very similar to the "long tail distribution", there are still nuances.