Product-harm crisis intelligent warning system design based on fine-grained sentiment analysis of automobile complaints

Abstract

Due to the huge losses caused by product-harm crises and subsequent recalls in the automobile industry, companies must urgently design a product-harm crisis warning system. However, the designs of existing warning systems use the recurrent neural network algorithm, which suffers from gradient disappearance and gradient explosion issues. To compensate for these defects, this study uses a long and short-term memory algorithm to achieve a final prediction accuracy of 90%. This study contributes to the research and design of automatic crisis warning systems by considering sentiment and improving the accuracy of automobile product-harm crisis prediction.