Unsupervised and supervised clustering for topic tracking
Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Topic Detection, Tracking, and Trend Analysis Using Self-Organizing Neural Networks
PAKDD '01 Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining
The Journal of Machine Learning Research
On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms
Data Mining and Knowledge Discovery
Automatic new topic identification using multiple linear regression
Information Processing and Management: an International Journal
Use of place information for improved event tracking
Information Processing and Management: an International Journal - Special issue: AIRS2005: Information retrieval research in Asia
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
The Journal of Machine Learning Research
Hot Topic Extraction Based on Timeline Analysis and Multidimensional Sentence Modeling
IEEE Transactions on Knowledge and Data Engineering
Relaxed online SVMs for spam filtering
SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
IEEE Transactions on Pattern Analysis and Machine Intelligence
Joint latent topic models for text and citations
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Detecting, Assessing and Monitoring Relevant Topics in Virtual Information Environments
IEEE Transactions on Knowledge and Data Engineering
The Unreasonable Effectiveness of Data
IEEE Intelligent Systems
Content Quality Assessment Related Frameworks for Social Media
ICCSA '09 Proceedings of the International Conference on Computational Science and Its Applications: Part II
QuestionHolic: Hot topic discovery and trend analysis in community question answering systems
Expert Systems with Applications: An International Journal
Box office prediction based on microblog
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
A large number of people use social media to generate content in a vast network of friends or strangers, and often with an unspecified number of users generating long lasting topic information which affects the normal operation of enterprises. The overall purpose of this paper is to explore the topic evolution mechanism of user generated content (UGC) and predict the topic evolution trend. Previous work related to the UGC topic evolution is data-driven modeling and did not take enterprises' UGC interfering into account. This paper tries to build a principle-driven model to predict the process of UGC topic evolution under considering enterprises' intervention, with which enterprise can predict UGC trend more earlier and know what actions the enterprise should take more exactly than using previous methods. Based on the topic evolution principles of social media and the propagation mechanism of UGC, a mean field equation model is developed to predict the UGC topic evolution. Experiment on a specific case is used to examine the flexibility and effectiveness of the proposed model. The result shows that the model can describe the real UGC topic evolution trend. Our research has some help for enterprises in dealing with UGC topic.