Research on the Application of Big Data Mining Algorithms in Reading Analysis of WeChat Public Numbers

Due to the increase in the number and types of public numbers, it has become increasingly difficult to boost the readership of WeChat public numbers. The study analyses the mining algorithm and constructs a WeChat readership analysis model based on random forest. The results show that the NMSE value of random forest is 0.457 in terms of the reading volume data of WeChat public numbers. With the same data set, random forest uses the shortest time and occupies the least memory, i.e. random forest has the best fitting effect. As the single frequency increases, the degree of influence on the total number of reads becomes greater; while the degree of influence gradually decreases when the average daily number of posts first increases; the higher the proportion of originality, the higher the reading rate; the increased punctuation index of titles is detrimental to the readers' reading effect; the increase in the proportion of videos helps to increase the total number of reads; and the lower information entropy has a higher number of reads for its public number. It shows that the random forest can effectively mine the data information and provide reference significance for the improvement of the reading volume of WeChat public numbers.