Meeting time: Tuesday, Dec. 12, 2017, 10 a.m. Pacific |
Meeting Zoom URL: https://ucsb.zoom.us/j/338657444 |
- PIs: Alan Liu; co-PIs: Jeremy Douglass, Scott Kleinman, Lindsay Thomas
|
|
|
- UCSB RAs:
- Rebecca Baker (English)
- Nazanin Keynejad (Comp. Lit.)
- Somak Mukherjee (English) -- Winter
- Giorgina Paiella (English)
- Aili Peeker (English)
- Jamal Russell (English)
- Tyler Shoemaker (English)
- Xiuhe Zhang (Film/Media)
- [Word embedding workflow team in formation]
|
- U. Miami RAs:
- Samina Ali (English, U. Miami)
- Tarika Sankar (English, U. Miami)
- Annie Schmalstig (English, U. Miami)
- CSUN RA: Sandra Fernandez
|
Next meeting (?):
|
Purpose of today's meeting
- PIs meeting to move the project forward.
2. Workshops
- Reschedule Markdown/GitHub workshop for Friday January 26th?
- Next workshops?
- Team collaboration tech
- Ingest workflow for our RAs
- Manifest & Virtual Workspace Manager workshop for our RAs
- General topic modeling workshop (open to others)
- Scott: April 13 workshop (remote)
- [workshops to be offered by the Text Analysis Hackerspace]
- Lindsay workshop on text classification
3. Advisory Board
- Current 12 "yes's" highlighted in yellow on the spreadsheet
- Add other members? (David, Thomas?)
- We are currently budgeted for 10 at the board meeting (total cost ~$4,900)
- Announcement of Advisory Board
- Initial communication to the Advisory Board:
- plans for this year
- plans to consult subsets of the Board for specific purposes
- plans for the summer Board meeting
- Lindsay's plan to consult with Ryan Cordell and Jonathan Fitzgerald.
4. WE1S Text Analysis Hacker Research Group
(Note: the TAH group will proceed whether or not the proposal to the DAHC for a "Text Analysis Hackerspace" succeeds)
- Participants:
- Faculty:
- Alan Liu
- Fermín Moscoso del Prado Martín (UCSBB Linguistics Dept. ; specializing in psycholinguistics, quantitative linguistics, computational linguistics, cognitive modelling, statistics)
- [WE1S postdocs]
- Douglass, Kleinman, and Thomas
- RAs
- Sandra Auderset (Ph.D. student, Linguistics)
- Devin Cornell (Ph.D. student, Sociology)
- Nicholas Lester (Ph.D. student, Linguistics)
- Fabian Offert (Ph.D. student, Media Arts & Technology)
- Teddy Roland (English; function as a member of Text-Analysis Hackerspace and also as DAHC GSR)
- Chloe Willis (Ph.D. student, Linguistics)
- "Text Analysis Hackerspace" Proposal for the DAHC (Digital Arts & Humanities Commons)
5. Data Collection Work
- Lindsay & Alan's meeting with the RAs on Nov. 30th
- Current state of data collection work: (updates from Alan and Lindsay)
- Next steps:
- RAs to continue adding sources and metadata to the WE1S Corpus Collection List during Dec and Jan.
- Lindsay and Alan to hold an "assessment meeting" with the RAs in January to take stock of our corpus and it's "representativeness." Individual RAs will be assigned the task of reporting on our corpus's current coverage of particular facets in the metadata sheet (e.g., do we have sources that cover a range of political orientations? cultural classes? regions? etc).
6. Manifest & Virtual Workspace Manager
- State of development (updates from Scott and Jeremy)
- Developing the ingest workflow so that RAs can start collecting articles
- Next steps:
- PIs to do a rehearsal of a collection workflow?
- Workshop for RAs on collection workflow
- Create timeline and plan for collection -- e.g.,
- Stage 1: collect designated subset of sources for the year 2017
- Stage 2: collect other sources and previous years in reverse chronological order
Meeting Outcomes
- Administrative Issues
- Workshops
- Markdown/GitHub workshop rescheduled for Friday Jan. 26th, 12:30-3:30
- Test Zoom "recording" function before the workshop
- Explore idea of getting funding for lunch from Transcriptions or DAHC
- Possible future workshops:
- Team collaboration tech (Trello, Ryver, Zoom) -- open to others
- Ingest workflow for our RAs / Manifest & Virtual Workspace Manager workshop for our RAs
- General topic modeling workshop -- open to others
- Scott is giving a topic modeling workshop on: April 13th that we could participate in remotely
- Word embedding and other workshops to be offered by the Text Analysis Hackerspace
- Lindsay to offer workshop on text classification
- Advisory Board
- Stay with our 13 Advisory Board members at present (including Thomas)
- Ask David later in conjunction with launch of the Text Analysis Hackerspace group
- Alan to start working on announcement of, and initial communication with, the Advisory Board
- Consultation meeting with Ryan Cordell and Jonathan Fitzgerald to be scheduled for Feb. (organized by Lindsay)
- We will have possible future meetings with subsets of the Board.
- RA Work on the WE1S Corpus Collection List
- Lindsay and Alan to set meeting for Jan. 18th (or 16th) with the RAs to assess the state of the corpus
- Alan to poll RAs for best date
- Lindsay and Alan to assign individual RAS the task of assessing specific facets of "representativeness" in the current corpus list of sources
- Ingest and Manifest/Virtual Workspace Manager Development
- Jeremy and Scott to conduct "work sprints" between now and February to create "golden spike" allowing their systems to converge. Currently, the systems include:
- Jeremy's "app" + Jupyter notebooks platform
- Scott's iPywidgets + Jupyter notesbooks (Publication Manager, Collection Manager)
- Aim point is a February milestone when we have a working ingest workflow
- PIs to try out the workflow
- Jeremy and Scott to do a show-and-tell workshop for project participants, including the Text Analysis Hackerspace group
- Samina to begin documenting intellectual property metadata for various components of the workflow system