12 workflows in this folder and its subfolders
Document Preprocessing applies a common sequence of preprocessing steps to clean and prepare text for subsequent analysis and comparison with other text. As input, a column containing documents is expected and as output, the newly preprocessed documents is produced. The Component requires the follow…
The Document Similarity Learner develops a model for identifying a new documents most similar matches from an existing corpus of documents. It consumes already processed documents (refer to Document Preprocessing Component) as input and provides as output both the corpus of documents and a model for…
The Document Similarity Predictor applies the model obtained by the Document Similarity Learner to a test document. It computes the cosine similarity between the original corpus of documents table and the test document.
August 2021 · This component extracts the most relevant English keywords in a corpus (a collection of documents) using three specific techniques: Topic Extraction using LDA: this technique collects a set of keywords for each different topic which clusters documents in different groups. Term Co-Occurrence: this ot…
September 2022 · This component allows you to query the News API (newsapi.org) in order to return news articles for specific search terms and parameters. The component can be used for finding articles related to a specific topic, company, or combination of search terms. The results can be used for text analysis mode…
June 2021 · This component allows you to query the News API (newsapi.org) in order to return the current top headlines for a particular country. The component can be used for finding articles related to a specific topic, company, or combination of search terms. The results can be used for text analysis models,…
June 2021 · This component allows you to query the News API (newsapi.org) in order to return the list of news sources (e.g. TechCrunch) currently registered with the News API. The component can be used to get detailed information about sources from the News API and map articles from other News API components to…
Allows the search for life sciences and biomedical topics in PubMed, which is a free search engine developed and maintained by the National Center for Biotechnology Information (NCBI) at the National Library of Medicine (NLM) More information can be found here: https://www.ncbi.nlm.nih.gov/pubmed/ T…
June 2023 · Use the component to apply the model trained with the 'Topic Extractor (STM)' component. See the other component for more information. This component integrates with the R implementation of Structural Topic Models (STM), following Roberts, Stewart and Tingley, Journal of Statistical Software (2019)…
July 2023 · The component trains an STM topic model via unsupervised learning. It integrates with the R implementation of Structural Topic Models (STM), following Roberts, Stewart and Tingley, Journal of Statistical Software (2019) (cran.r-project.org/web/packages/stm/vignettes/stmVignette.pdf), via the R libra…