Blog
data
How to get data from Wikidata?
My new hobby: creating data sets from Wikidata. With some help from ChatGPT.
Janez Demšar, Apr 20, 2025
text mining, digital humanities, embedding
Finding semantic neighbors with Orange
Finding semantically similar documents in Orange helps digital humanists retrieve relevant documents in a large corpus.
Ajda P. Žagar, Mar 28, 2025
analysis, bioinformatics, Foundation Models
Foundation models in Orange with just a few lines of code
Foundation models can be used in Orange in just a few lines of code. Python Script can unlock every model from Hugging Face if you are brave enough.
Martin Špendl, Jan 20, 2025
data, analytics, pharma, PLS, Orange, insights
Partial Least Squares in the Pharmaceutical Industry
Partial Least Squares (PLS) enhances pharmaceutical research by analyzing complex, high-dimensional datasets, addressing multicollinearity, and building predictive models. Orange streamlines its implementation for robust and innovative insights, driving innovation in pharmaceutical research.
Tine Porenta, Dec 03, 2024
gui
Orange Is Becoming a Poliglot
Orange 3.38 supports switching between languages
Janez Demšar, Dec 02, 2024
text mining, text, bag of words, vectorization, word cloud
Visualize bag of words?
We are used to seeing word clouds. How about a TF-IDF word cloud? Orange has a great way of observing TF-IDF results. Useful for the analysis and teaching!
Ajda P. Žagar, Nov 21, 2024
data, analysis, Luxembourg, teachers, Orange, experiment
Luxembourgish Teachers Experiment with Orange in Nature
How can Orange support the needs of teachers and children in the pedagogical process? In Luxembourg, Blaž Zupan and Janez Demšar carried out an experimental workshop with local primary school teachers to test some approaches.
Erika Funa, Oct 23, 2024
new, course, bioinformatics
Diving into Data: How We Used COVID-19 to Teach Bioinformatics
During the COVID-19 pandemic, we completely redesigned our Introduction to Bioinformatics course. Every year since then, the students' feedback has been overwhelmingly positive. This summer, Pavlin Poličar presented the course at the International Conference on Intelligent Systems for Molecular Biology (ISMB) in Montreal, Canada.
Pavlin Poličar, Aug 10, 2024
text preprocessing, text mining, conllu, filtering
Text Preprocessing: Tips & Tricks
Some tips and tricks for text preprocessing in Orange.
Ajda Pretnar Žagar, Jun 26, 2024
data, analysis, international, school, project
International Primary School Teachers Experiment with Data Analysis in Orange
Janez Demšar and Blaž Zupan from Biolab at the University of Ljubljana, Faculty of Computer and Information Science experimented with Orange in primary school data exploration activities with a group of teachers from Ireland, Luxembourg, and Slovenia.
Erika Funa, Jun 01, 2024
embedding, text mining, bag of words
Document embeddings vs. Bag of words
When to use document embeddings instead of a bag of words.
Ajda Pretnar Žagar, May 30, 2024
tsne, papers
Orange Data Mining uses the fastest t-SNE implementation in Python
Journal of Statistical Software published a paper describing our state-of-the-art implementation openTSNE.
Pavlin Poličar, May 14, 2024
image, tutorials
So Sweet and So Fresh … New Text Mining Tutorial is Out
A step-by-step guide on how to build a classifier to predict food types. Getting the know the widgets Test and Score, Logistic Regression, Confusion Matrix, Predictions.
Erika Funa, Apr 15, 2024