In SVD decomposition of a term-document matrix (A = UΣVᵀ), what do the singular values in Σ represent?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — singular values measure the magnitude or importance of each latent dimension, so the dimension with the bigger value explains more variance in the term-document matrix. You don't use them to count documents or store raw term weights.
Full Explanation
The correct answer is that singular values represent the magnitude or importance of each latent dimension; larger values mean that dimension explains more variation in term-document co-occurrence patterns. The document-count option is wrong because singular values do not count documents. The average-term-frequency option is wrong because average term frequency is not represented by singular values. The inverse-document-frequency option is wrong because IDF weights are applied before SVD, not represented as singular values.