Abstract
A new depiction method based on the merge-AP algorithm is proposed to effectively improve the mining accuracy of negative comment data on microblog. In this method, we first employ the AP algorithm to analyze negative comment data on microblog and calculate the similarity value and the similarity matrix of data points by Euclidean distance. Then, we introduce the distance-based merge process to solve the problem of poor clustering effect of the AP algorithm for datasets with the complex clustering structure. Finally, we compare and analyze the performance of K-means, AP, and merge-AP algorithms by collecting the actual microblog data for algorithm evaluation. The results show that the merge-AP algorithm has good adaptability.
Highlights
Social media is an important platform for users to share and acquire information
The mining accuracy of negative comment data on microblog is not high enough, and the clustering effect of nongroup datasets with the complex clustering structure is especially poor. e distance-based merge process can merge multiple categories into fewer categories according to a certain calculation method to effectively solve the problem of poor clustering effect of complex structures. erefore, a new depiction method based on the merge-affinity propagation (AP) algorithm is proposed in this paper, and the similarity value and the similarity matrix of data points are calculated by Euclidean distance, and the damping coefficient is added for optimization to improve the mining accuracy
In view of the phenomenon that negative comments on microblog have led to unhealthy social atmosphere, an improved algorithm based on affinity propagation (AP) is proposed in this paper to mine negative comment data on microblog
Summary
Social media is an important platform for users to share and acquire information. With the rapid development of social media applications in recent years, more and more users express their views through social media platforms. Xie et al [7] used the probabilistic uncertain multiplicative linguistic preference relations to assess the management ways of the online public opinion. E numerical example that helped assess the valid way to manage the online public opinion was performed to check the feasibility of the proposed decision-making procedure. Zhu and Hu [8] used the probabilistic uncertain multiplicative linguistic preference relations to assess the management ways of the online public opinion, and the numerical example could help assess the valid way to manage online public opinion was performed to check the feasibility of the proposed decisionmaking procedure. Haihong et al [9] explored the key issues of theme and sentiment analysis from the perspective of Mathematical Problems in Engineering public opinion analysis with deep learning and experimented with the short text topic classification dataset TREC and the sentiment analysis dataset IMDB to verify the validity of the proposed model. The mining accuracy of negative comment data on microblog is not high enough, and the clustering effect of nongroup datasets with the complex clustering structure is especially poor. e distance-based merge process can merge multiple categories into fewer categories according to a certain calculation method to effectively solve the problem of poor clustering effect of complex structures. erefore, a new depiction method based on the merge-AP algorithm is proposed in this paper, and the similarity value and the similarity matrix of data points are calculated by Euclidean distance, and the damping coefficient is added for optimization to improve the mining accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
