Exploring the Space of Topic Coherence Measures

By Michael Röder, Andreas Both, Alexander Hinneburg. Web Search and Data Mining, 2015

2,293 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/40e4b215b810f671b4c55b02e92573060945f4a4

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

Citations in the corpus

Caste in the News: A Computational Analysis of Indian Newspapers (2019, methodology): “We calculated the “Cv” coherence measure being the most adequate measure as reported in the literature (Röder et al., 2015).”
An analysis of the coherence of descriptors in topic modeling (2015, background): “More recently, Röder, Both, and Hinneburg (2015) proposed a unifying framework that represented coherence measures as a composition of parts, with the objective of achieving higher correlation with human judgements.”
Interpretable Machine Learning : Lessons from Topic Modeling (2016, background): “Metrics to measure the coherence of topics were introduced by [17] and [16], and later improved upon and generalized by others [13] [21].”
On Cross-Dataset Generalization in Automatic Detection of Online Abuse (2020, methodology): “To determine the optimal number of topics, we use a coherence measure that calculates the degree of semantic similarity among the top words (Röder et al., 2015).”
Machine learning and soil sciences: a review aided by machine learning tools (2019, methodology): “We estimated a coherence measure proposed by Röder et al. (2015) (referenced as CV in their paper) for different models trained with an increasing number of topics, from 2 to 30.”
Dissecting Climate Risks: Are they Reflected in Stock Prices? (2021, methodology): “rely on the CV coherence measure by Röder et al. (2015) to select the optimal number of topics and select a model with 25 topics.”
Full-Text or Abstract? Examining Topic Coherence Scores Using Latent Dirichlet Allocation (2017, methodology): “[19] systematically and empirically explored the multitude of topic coherence measures and their correlation with available human topic ranking data.”
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence (2020, background): “, 2009) to approximated scores (Lau et al., 2014; Röder et al., 2015).”
Generating Summaries with Topic Templates and Structured Convolutional Decoders (2019, methodology): “We performed grid search on the number of topics [10 , · · · , 90] every ten steps, and used the context-vector-based topic coherence metric (cf. (R¨oder et al., 2015)) as guidance to manually inspect the output topic sets and”