IRLGMLNov 20, 2019

A Coefficient of Determination for Probabilistic Topic Models

arXiv:1911.11061v25 citations
Originality Synthesis-oriented
AI Analysis

This work provides a standardized evaluation metric for topic modeling, which is incremental as it adapts an existing statistical concept to a specific domain.

The research tackles the problem of evaluating goodness of fit in topic models by proposing the coefficient of determination (R²) as a standard metric, addressing the lack of cross-contextual evaluation and improving communication with lay audiences.

This research proposes a new (old) metric for evaluating goodness of fit in topic models, the coefficient of determination, or $R^2$. Within the context of topic modeling, $R^2$ has the same interpretation that it does when used in a broader class of statistical models. Reporting $R^2$ with topic models addresses two current problems in topic modeling: a lack of standard cross-contextual evaluation metrics for topic modeling and ease of communication with lay audiences. The author proposes that $R^2$ should be reported as a standard metric when constructing topic models.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes