2016 · 12 citations · 10 references
ComputingComputer ScienceData MiningNatural Language ProcessingText AnalyticsDocument RepresentationInformation ExtractionText MiningText Similarity AnalysisTopic ModelingTrend DetectionTime Window AnalysisTime WindowsTopic DiscoveryTopic EvolutionTopic Evolution AnalysisTopic ProgressionTopic SimilarityTopic Trend Analysis
Mining evolution of topic from papers plays an important role in learning about the trend and monitoring the hot topic of research. The paper proposes a model based on Latent Dirichlet Allocation (LDA) for the purpose of mining evolution of topic. Firstly, we deal with the collection of all the papers using LDA to find out topics and their key words, and get probability distribution of document -topic on different time windows so that we can figure out the trend of topic intensity. Secondly, we apply LDA in papers on every single time window to get probability distribution of topic -word, through which we can compute similarity of topics from different time windows, and the words probability of similar topics can help us figure out trend of topic content.
10
David M. Blei · Communications of the ACM · 2012 · 5.5K citations
Xuerui Wang, Andrew McCallum · 2006 · 1.1K citations
Studying the history of ideas using topic models
David Hall, Daniel Jurafsky, Christopher D. Manning · 2008 · 455 citations · Full text
David M. Blei · 2011 · 436 citations
Continuous Time Dynamic Topic Models
Chong Wang, David M. Blei, David Heckerman · arXiv (Cornell University) · 2012 · 325 citations · Full text