1. Task-teams

During Fall 2018, all teams will focus on U.S. sources unless otherwise noted. We will begin expanding outward globally again later in the year. The first task of each team will be to meet and discuss goals and plans for the fall quarter. (Project team folders in Google Drive)

• (1) Primary Corpus Collection & Analysis Team -- (Led by: Lindsay Thomas, with the other PIs; Members: Tyler, Leila, Tarika, Rebecca, Jamal, Ryan, Sean)
• “Humanities” Keyword Sub-Team -- (Led by: TBD; Members: TBD) Analyzes materials collected by searching for the word "humanities"

• Review LexisNexis data from the summer; determine what else we need to collect and collect it

• Other Keywords Sub-Team -- (Led by: TBD; Members: TBD)  Analyzes materials collected through experiments with other search terms/phrases

• Determine what other keywords we should collect and from what sources, collect this data

• Small-scale experiments with this data to compare to “humanities” data

• Metadata Sub-Team -- (Led by: Lindsay Thomas) 

• Planning Document for Team Goals and Tasks   

• (2) Students and the Humanities Team (Led by Abigail Droge; Members: Jessica, Avery, Leila, Rebecca, Aleah, Tyler)
•  Analyzes materials collected to help understand students' relation to, and perception of, the humanities. One special focus of this team will be to try to collect and study materials related to first-generation-to-college students. (Note: This team is associated with the WE1S Curriculum Lab led by Abigail. The Curriculum lab will assist with IRB-related research. Also, If the linguistics sub-team consisting of Chloe Willis and Sandra Auderset proceeds, it could be coordinated with the "Students and the Humanities Team.")

• Planning Document for Team Goals and Tasks  

• (3) "Gender, Ethnic, and Racial Diversity and Interests" Team (Led by Giorgina Paiella; Members: Jamal, Aleah, Su) 
• Analyzes materials collected to help understand the relation of racial, ethnic, and gender groups to the humanities. Note: this team will liaise as needed with other teams, including team #1, #2, and #3.

• Focus during fall on one or two groups 

• Collection of materials from college websites to supplement collection of journalistic media materials 

• Planning Document for Team Goals and Tasks  

• (4) Interpretation Lab Team (Led by Dan Baciu; Members: Su, Isaac, Ryan, Sean, Cindy, Sihwa) 
• Development of Interpretation Protocol for topic modeling; methods of exploration and validation to support the protocol (plus experimentation with related other methods such as topic modeling over time, structured data extraction and Wikification)
• Slides for recent Interpretation Lab meeting  
• Interpretation Lab Work Log  

• Word Embedding Sub-Team (Fabian offert, Teddy Roland, Isaac, Su, Ryan)

• Data Visualization Sub-Team (Sihwa Park, Cindy Kang) 

• "Random" Corpus Sub-Team (Led by Lindsay Thomas; Members: U. Miami RAs, Ray) 

• Determine how to collect random corpus; collect it; small-scale experiments

• (5) Team to Harvest and Report on Summer 2018 work (and notes from the Advisory Board meeting) --  (Led by TBD; Members: )  

2. Workshop on WE1S Source Collection & Topic Modeling Workflow

• Queuing searches in LexisNexis (instructions by Lindsay)
• Google Form for LexisNexis Collection Queries 
• Sources IDs + Geographic Info 
• Also: collecting materials using "WE1S Chomp" tool by Sean Gilleran (Github | Windows version)
• Running the Workspace Manager System Jupyter notebooks to create and visualize topic models (Workshop led by Jeremy and Lindsay)
• Step-by-step Guide to Using the WE1S Data Notebooks System 
• Sample Topic Models from Summer Research Camp 2018
• Directory of all current WE1S topic models (public version)
• Directory of Topic Bubbles variant interfaces for WE1S topic models (public version)