There are 6 repositories under text-as-data topic.
Beautiful visualizations of how language differs among document types.
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021.
Interpretable data visualizations for understanding how texts differ at the word level
Notebooks for the Seattle PyData 2017 talk on Scattertext
Summer/ winter schools, workshops and conferences in computational social science 🫂
This is a designed package for replicating the estimates and findings in the article of Factionalism and the Red Guards under Mao's China: Ideal Point Estimation Using Text Data.
2018 Computational Text Analysis Notebooks, University of Mannheim
Code and models for 3 different tools to measure appeals to 8 discrete emotions in German political text
Literature 📄 and datasets 📚 on automatic populism detection
Summer 2017 Social Media Analytics Workshop Series
LinkOrgs: An R package for linking linking records on organizations using half a billion open-collaborated records from LinkedIn
An Automation Webcrawler for Extracting Central Bankers' Speeches
'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.
The ABC of Computational Text Analysis. BA Seminar, Spring 2022, University of Lucerne
A small showcase for topic modeling with the tmtoolkit Python package. I use a corpus of articles from the German online news website Spiegel Online (SPON) to create a topic model for before and during the COVID-19 pandemic.
A tutorial on using regular expressions in R
Uso de structural topic modeling para análise de teses e dissertações da pós-graduação em filosofia no Brasil.
From using xpdf, rvest, and quanteda on United Nations Digital Library search results to applying dictionaries to speeches in United Nations meeting records
The ABC of Computational Text Analysis. BA Seminar, Spring 2021, University of Lucerne
This repository uses text-as-data methods alongside traditional primary source reading to analyze early American state constitutions. The R scripts create a function to scrape and clean the constitutional text, run sentiment analysis, calculate tf-idf, and perform LDA. This is a work-in-progress.
Empirical framework applied to parliament discourses and Twitter data, with a Discourse Polarization Index.
A little sample of my recent work as a data analyst.
Original corpus of articles relating to refugees scraped from Tennessee newspaper The Chattanoogan along with simple code for text-as-data word cloud.
Collection of text corpora for publicly available speeches from Mexican president Andres Manuel Lopez Obrador (AMLO) sourced from YouTube. The dataset includes his daily morning conferences (conferencias mañaneras) 😴🪿
Material from my Machine Learning for the Social Sciences course