Jeff Jacobs

Unsupervised Extraction of Workplace Rights and Duties from Collective Bargaining Agreements

Elliott Ash, Jeff Jacobs, Bentley MacLeod, Suresh Naidu, and Dominik Stammbach

Proceedings of the 20th IEEE International Conference on Data Mining -- International Workshop on Mining and Learning in the Legal Domain (ICDM-MLLD). 2020.

Monopsony in Online Labor Markets

Arindrajit Dube, Jeff Jacobs, Suresh Naidu, and Siddharth Suri

American Economic Review: Insights, (2)1: 33-46. 2020.

How to Do Things with Translations: Cross-Lingual Phrase Embeddings for Translation Analysis

Jeff Jacobs

Ninth Annual Conference on New Directions in Analyzing Text as Data (TADA). 2018.

Information Cartography: Creating Zoomable, Large-Scale Maps of Information

Dafna Shahaf, Jaewon Yang, Caroline Suen, Jeff Jacobs, Heidi Wang, and Jure Leskovec

Proceedings of the ACM International Conference on Knowledge Discovery and Data Mining (KDD), 1097-1105. 2013.

Metaheuristic Approaches to Resource Scheduling in Heterogeneous Wireless Networks

Cristy Duan, Honghao Gao, Jeff Jacobs, and Weixiang Wu

Joint Mathematics Meetings (JMM). 2012.

Evolving Musical Counterpoint: The Chronopoint Genetic Algorithm

Jeff Jacobs and James Reggia

Proceedings of the 2011 IEEE Congress on Evolutionary Computation, 11-16. 2011.

How to Do Things with Translations: Cross-Lingual Phrase Embeddings for Translation Analysis

Last Updated September 1, 2018

"Simultaneous and Systematic Abolition": Automated Content Analysis of the 1789 Cahiers de Doleances

Last Updated June 1, 2018

Threadsheets: Weave Tabular Data into Weighted and Imputed Estimates

Package in both Python and R allowing interactive specification and visualization of data concordance tasks. Interfaces with GitHub and Google Sheets APIs to generate grid of estimates color-coded by confidence levels.

MarxDB.com: Web App for Browsing the Marx-Engels Digital Cyclopedia

Web app with ReactJS frontend and MongoDB backend, deployed using Vercel, allowing browsing and searching various datasets compiled for my dissertation. Updated October 3, 2022.

QConjoint: PHP server for running conjoint experiments in Qualtrics

A php script that interacts with the Qualtrics interface, allowing survey creators to send respondent-entered data (categorical or continuous) and receive randomly-generated variations of this data, for populating a conjoint comparison table. Demo server here, and demo survey showing implementation here. Updated January 28, 2021.

scipot: Topic Modeling in Reverse for Synthetic Document Generation

Trains an Author-Topic Model on a collection of \(N\) documents with \(M\) authors, then runs the model "in reverse" to generate synthetic documents via a user-specified Dirichlet mixture \((\alpha_1, \ldots, \alpha_M)\), where \(\alpha_i\) represents the probability of sampling from author \(i\)'s topic distribution when generating a new word. Updated June 3, 2020.

ngramdl: R functions for downloading and plotting ngram frequency from Google Books

Mainly a fix of the ngramr library to work with the latest version of Google's Ngram Viewer. Run github_install("jpowerj/ngramdl") to install the package directly from within R/R Studio (requires devtools package), then use ngram2csv(phrase_list, csv_filepath) to download, or ggram(phrase_list) to plot within R. Updated June 3, 2020.