Semi-Supervised Algorithm for Document Scaling
Coerce various objects to coefficients_textmodel This is a helper func...
Convert a list or a dictionary to seed words
Coerce various objects to statistics_textmodel
Assign the summary.textmodel class to a list
Create a Latent Semantic Scaling model from various objects
[experimental] Compute polarity scores with different hyper-parameters
Extract model coefficients from a fitted textmodel_lss object
Computes cohesion of components of latent semantic analysis
Identify noisy documents in a corpus
[experimental] Compute variance ratios with different hyper-parameters
Prediction method for textmodel_lss
Print methods for textmodel features estimates This is a helper functi...
Implements print methods for textmodel_statistics
print method for summary.textmodel
Seed words for Latent Semantic Analysis
Smooth predicted polarity scores
Fit a Latent Semantic Scaling model
[experimental] Plot clusters of word vectors
Plot similarity between seed words
Plot polarity scores of words
Identify context words
Internal function to generate equally-weighted seed set
A word embeddings-based semi-supervised model for document scaling Watanabe (2020) <doi:10.1080/19312458.2020.1832976>. LSS allows users to analyze large and complex corpora on arbitrary dimensions with seed words exploiting efficiency of word embeddings (SVD, Glove). It can generate word vectors on a users-provided corpus or incorporate a pre-trained word vectors.