createWordEmbeddings: Create Word Embeddings

In zieglerjef/openEnded: Tools for Implementing and Analyzing Open-Ended Responses as Manipulation Checks

Description

Generate comparison between the prompt and participants' responses in a latent word2vec space.

Usage

createWordEmbeddings(
  dataframe,
  prompts,
  responses,
  user_seed = 5,
  prune_len = 2,
  language = "en"
)

Arguments

dataframe	Dataframe from which we will estimate our regression model.
prompts	Vector/column in dataframe that contain the prompt that each respondnet saw.
responses	Vector/column in dataframe that records participants' recollection of prompt.
user_seed	Set seed for reproducibility. Default = 5.
prune_len	Cut words that are not frequently mentioned. Default = 2 (must be mentioned at least twice in the corpus).
language	What language are the prompts and responses? Default is English ('en'), Spanish ('es') and Brazilian-Portuguese ('br-pt') will hopefully be available soon.

Author(s)

Jeffrey Ziegler (<jeffrey.ziegler[at]emory.edu>)

See Also

similarityMeasures

zieglerjef/openEnded documentation built on Nov. 30, 2020, 2:03 p.m.