thieled/dictvectoR
'dictvectoR' measures the similarity between a concept dictionary and documents, using fastText word vectors. Implements the "Distributed-Dictionary-Representation" (Garten et al. 2018) method in R.
This tool helps researchers and analysts quantify how strongly specific concepts are expressed in text documents. You provide a list of keywords defining a concept (like "populism" or "economic anxiety"), and it calculates a score for each document indicating its similarity to that concept. This is useful for social scientists, political analysts, or market researchers who need to measure abstract ideas across large volumes of text like social media posts, news articles, or survey responses.
No commits in the last 6 months.
Use this if you need to measure the presence and intensity of specific theoretical concepts within a collection of texts using a dictionary-based approach.
Not ideal if you need to perform basic keyword counting or sentiment analysis, or if you prefer not to work within the R statistical programming environment.
Stars
9
Forks
2
Language
R
License
CC-BY-4.0
Category
Last pushed
Sep 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/thieled/dictvectoR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
JuliusBahr/SimpleSimilarity
A framework for semantic text search
tlack/semantics
Semantic similarity via text embeddings in Elixir - powered by SentenceTransformers by SBert.net
fangrouli/Document-embedding-generation-models
Development and Application of Document Embedding for Semantic Text Retrieval