Topics over time: a non-Markov continuous-time model of topical trends

By Xuerui Wang, Andrew McCallum. Knowledge Discovery and Data Mining, 2006

1,462 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/ba007612814e7b2fffd9e5723069dcd5c52bcd34

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis (2020, methodology): “• RP has attracted attention and has been employed in many machine learning scenarios recently such as classiﬁcation, clustering, and regression (Wang and McCallum, 2006; Ramage et al., 2011).”
Novel Word-sense Identification (2014, positive): “We also believe that topic models could be useful for identifying emerging or changing domains themselves given the reference and focus corpus, and related work in this area (e.g., Wang and McCallum, 2006; Blei and Lafferty, 2007).”
A temporal model of text periodicities using Gaussian Processes (2013, methodology): “, 2011) or modelled using a simple uni-modal distri bution (Wang and McCallum, 2006).”
Continuous Time Dynamic Topic Models (2008, background): “The TOT model treats the time stamps as observations of the latent topics, while DMM assumes that the topic mixture proportions of each document is dependent on previous topic mixture proportions.”
A state-space mixed membership blockmodel for dynamic network tomography (2008, methodology): “This scheme has been adopted in a number of recent works on extracting evolving topical themes in text documents [Blei and Laﬀerty (2006b); Wang and McCallum (2006)] or author embeddings [Sarkar and Moore (2005)] based on author, text, and reference networks of archived publications.”
Diachronic word embeddings and semantic shifts: a survey (2018, background): “For instance, there is a strong vein of research based on dynamic topic modeling (Blei and Lafferty, 2006; Wang and McCallum, 2006), which learns the evolution of topics over time.”
Topic modelling for qualitative studies (2017, background): “…additional information and structure that may be available in specific settings (see Section 2.2 for a brief review), supervised versions to be used as text classifiers [4], analysis of topic evolution in a set of documents over time [5, 6], image recognition and classification [7, 8] and others.”
An overview of topic modeling and its current applications in bioinformatics (2016, background): “Wang and McCallum (2006) proposed topic over time (TOT) to jointly model both word co-occurrences and localization continuously.”
Studying the History of Ideas Using Topic Models (2008, background): “The Topics over Time Model (Wang and McCallum, 2006) assumes that each document chooses its own time stamp based on a topic-speciﬁc beta distribution.”
Scalable inference of topic evolution via models for latent geometric structures (2018, background): “Another approach is to keep topics fixed and consider only evolving topic popularity [26].”
Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey (2017, methodology): “1 -study Model ears Estimation / ence Methods Domain [70] Corr A 2003 EM A al [75] Model 2004 Sampling A authors, topics [76] T) 2005 Sampling A T) ery [73] model(DTM) 2006 algorithm A process topics [77] T) 2006 Sampling A time. [78] AM 2006 Sampling A method correlations [79] A 2007 sampling A alg”
Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression (2008, methodology): “…such “downstream” models include the authorship model of Erosheva, Fienberg and Laﬀerty [5], the Topics over Time (TOT) model of Wang and McCallum [15], the Group-Topic model of Wang, Mohanty and McCallum [16], the CorrLDA model of Blei and Jordan [1] and the named entity models of Newman,…”
Understanding semantic change of words over centuries (2011, background): “Topics-Over-Time [5] is an LDA like topic model that captures not only the low dimensional structure of data, but also captures how that structure changes over time.”