Project SP17h: Collecting and evaluating sports and politics in multilingual news

Project SP17h: Collecting and evaluating sports and politics in multilingual news
Researcher: Sam Stehle
Position type: Spanish translation, web browsing/scraping, interpreting textual results
Scope: 45-135 hours of work during the semester for 1-3 credits.
Application deadline: 5:00 p.m. on Friday, December 9, 2016
Application URL:

Project and position description

Seeking an assistant to help with data collection and analysis on 2 related projects:

  1. Collecting digital news articles on Latin American political interactions (think Cuba post-trade embargo with the US) and the World Baseball Classic. Through the international World Baseball Classic competition, nations compete against one another, and their politics intercede. We will together develop a list of publication sources and work with existing Java code for automated downloading (scraping) of individual relevant articles from the web.
  2. Manually and computationally interpreting and evaluating the results from topic models of news articles related to the Catalonian independence movement. Catalonians have long desired independence from Spain, and in 2014 they held a referendum vote. I have performed clustering on a collection of news articles into primary themes using automatic topic models, and together we will examine the output from those models in English, Spanish, and Catalan for their significance for global politics and text analysis methods.

Key due date: data collection must be completed by February 15, 201.

Desired qualifications

  • Read Spanish with high proficiency (high priority)
  • Familiarity with or interest in international relations and national identity scholarship
  • Experience in or desire to learn about Latin American and/or Spanish politics
  • Experience in or desire to learn programming in Java, Python, or R (low priority)

To apply

Prospective candidates should complete the application form at by 5:00 p.m. on the indicated date. Follow all instructions.