Roberta Rocca's repositories
DataSci-AU-24
Primary repository for the course: Data Science, Prediction, and Forecasting, taught as part of the CogSci masters program at Aarhus University.
benchmarks_paper
Code and data for Rocca, R., & Yarkoni, T., (2023): Putting psychology to the test: rethinking model evaluation through benchmarking and prediction, published in Advances in Methods and Practices in Psychological Science
contrastive-user-encoders
Code for: Rocca, R., & Yarkoni, T. (2022), Language models as user encoders: Self-supervised learning of user encodings using transformers, to appear in Findings of the Association for Computational Linguistics: EMNLP 2022
multidiagnosis-text
Feature-based and Transformer models for classification of mental disorders from text
chatbot-conversations
A library for running experiments of conversing chatbots.
ctx_transformers
Training encoder for context-aware MLM and user encoding
eucomm-twitter
Code repository for paper: "From economy to identity: A data-driven analysis of the European Commission’s Twitter communication between 2010 and 2022
mteb
MTEB: Massive Text Embedding Benchmark
neuroscout-docs
The neuroscout documentation.
PastTwitter
Functions to scrape Twitter account info for past points in time via archive.org
pyNS
Python neuroscout API library
rbroc.github.io
Roberta Rocca
sbert-align
Compute alignment using SentenceBERT
TextDescriptives
A Python library for calculating a large variety of statistics from text
turftopic
Robust and fast topic models with sentence-transformers.