Abstract
The era of big data has produced a large amount of text data. Due to the different data sources and the complexity of the data generation process, a large amount of data has a heterogeneous structure. Combining several latest machine learning methods with hierarchical technology, the algorithm for text data with heterostructure can improve the accuracy of text classification. Empirical data analysis shows that our algorithm has a significant effect on improving classification accuracy. Based on the grounded theory, this paper analyzes 2000 "short comments" of sample books on the "Douban Reading" website, and explores the motivation of short comments and the corresponding emotional analysis. The data results show that users' emotional tendencies in Douban applications are diversified and consistent, and neutral comments play an important role. The user's emotional tendency represents the user's evaluation attitude towards books. The user's emotional tendency in the evaluation can be grasped in a timely manner. Readers can be used to understand the user's recognition of books in a timely manner and adjust their service strategies in a timely manner.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
