Package index • idiolect

Input and pre-processing

Functions to input the data and prepare it for an analysis

create_corpus(): Create a corpus

chunk_texts(): Chunk a corpus

contentmask(): Content masking

tokenize_sents(): Tokenize to sentences

Authorship analysis functions

Functions to run an authorship analysis

delta(): Delta

impostors(): Impostors Method

lambdaG(): Apply the LambdaG algorithm

ngram_tracing(): N-gram tracing

Likelihood ratio

Functions to calibrate, interpret, and evaluate likelihood ratios

calibrate_LLR(): Calibrate scores into Log-Likelihood Ratios

density_plot(): Plot density of TRUE/FALSE distributions

performance(): Performance evaluation

posterior(): Posterior prosecution probabilities and odds

Post-hoc and intepretation

Functions to interpret the output

lambdaG_visualize(): Visualize the output of the LambdaG algorithm

concordance(): Qualitative examination of evidence

Optional advanced functions for analysis

Typically only needed in special cases

vectorize(): Vectorize data

most_similar(): Select the most similar texts to a specific text

Data

Sample dataset for testing

enron.sample: Enron sample