A method and apparatus for de-noising e-commerce comment emotion analysis

• Main Authors: WANG HANG, LI PINGZHANG
• Format: Patent
• Language: Chinese; English
• Published: 22.01.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

A method and apparatus for de-noising e-commerce comment emotion analysis. The method for de-noising e-commerce comment emotion analysis comprises the follow steps of: Step S1, construction of a pre-marking module; step S2, construction of a manual marking module; step S3, construction of a depth neural network model training module; step S4, construction of a depth neural network model marking module; step S5, construction of a noise reduction module; and step S6, construction of an emotion analysis module. The invention has the advantages: the method can help businesses to detect and correctmalicious comments, irrigating, repeated emphasizing, exaggeration of the problem of comments, eliminate or reduce the impact of these noises, so that the emotional analysis results are more accurate. 本发明涉及种电商评论情感分析降噪方法和装置，所述方法电商评论情感分析降噪方法包括以下步骤：步骤S1、预打标模块的构建：步骤S2、人工标注模块的构建：步骤S3、深度神经网络模型训练模块的构建：步骤S4、深度神经网络模型标注模块的构建：步骤S5、降噪模块的构建：步骤S6、情感分析模块的构建。其优点表现在：能够帮助商家发现并修正恶意评论，灌水，反复强调，夸大问题的评论，消除或者降低这些噪声带来的影响，让情感分析结果更准确。