Orange Blog

By: Ajda Pretnar Žagar, Mar 18, 2022

LDAvis: visualization for LDA topic modelling

Text add-on recently got extended with LDAvis widget, a visualization that enables exploring word frequencies in LDA-generated topics. See how to construct LDAvis pipeline in Orange.

By: Ajda Pretnar, Sep 17, 2021

Semantic Analysis of Documents

How to use Text add-on to extract keywords from documents, score documents on keywords, and display semantic content in a map.

By: Ajda Pretnar, Sep 15, 2021

New in Orange: Support for CONLL-U files

Orange can now work with CONLL-U files, including its lemmas, POS tags, and named entities.

By: Ajda Pretnar, Jan 27, 2021

Observing Word Distribution

How to inspect word distribution in a corpus with a clever combination of widgets in Orange.

By: Primož Godec and Nikola Đukić, Oct 15, 2020

How to identify fake news with document embeddings

Presenting document embeddings widget and how to identify fake news.

By: Ajda Pretnar, Sep 28, 2020

New Video Tutorials on Text Mining

New video tutorials on text mining available on our YouTube channel.

By: Ajda Pretnar, Jul 27, 2020

Detecting Story Arcs with Orange

How to detect sentiment, plot story arcs and analyze the key segments in a corpus.

By: Dr. Sven Bingert & Steffen Rörtgen, Jul 2, 2019

Data Science Made Easy: How To Identify Hate Comments with AI

How to teach text mining and data science to the 9th grade students in 60 minutes? With Orange and the analysis of hate speech on social media, of course!

By: AJDA, Nov 6, 2018

Data Mining for Anthropologists?

This weekend we were in Lisbon, Portugal, at the Why the World Needs Anthropologists conference, an event that focuses on applied anthropology, design, and how soft skills can greatly benefit the industry. I was there to hold a workshop on Data Ethnography, an approach that tries to combine methods from data science and anthropology into a fruitful interdisciplinary mix! Data Ethnography workshop at this year’s Why the World Needs Anthropologists conference.

By: AJDA, Oct 5, 2018

Orange Now Speaks 50 Languages

In the past couple of weeks we have been working hard on introducing a better language support for the Text add-on. Until recently, Orange supported only a limited number of languages, mostly English and some bigger languages, such as Spanish, German, Arabic, Russian… Language support was most evident in the list of stopwords, normalization and POS tagging. Related: Text Workshops in Ljubljana Stopwords come from NLTK library, so we can only offer whatever is available there.