Study on detection of impulsive purchase behaviour of e-commerce platform consumers based on social network media

Studying consumers' impulsive purchasing behaviour helps to understand their purchasing behaviour and increase sales revenue. Therefore, this article proposes a method for detecting consumer impulse buying behaviour on e-commerce platforms based on social network media. Firstly, collect data on consumer purchasing behaviour. Secondly, preprocess the characteristics of impulse buying behaviour based on the RFM function. Then, considering the polarity and degree of emotional words, calculate impulsive emotion scores based on an emotion dictionary. Finally, use the LSH algorithm to find the nearest neighbour point that matches each user's emotional needs, and use the input of LOF to find the extreme point, obtaining the detection results of impulse buying behaviour. The results show that the detection recall rate of this method can reach 99.0%, the detection error is only 0.02, and the detection time is only 8.9 seconds. The detection effect of this method is good.