Esma Wali

Directed Studies(CS611)/Fall 2020

Advisor: Professor Jeanna Matthews

Instructor's Notes:

In this 1 credit 611 Directed Study, Esma Wali will under the direction of Prof. Jeanna Matthews, read and discuss research literature, collect and analyze data, write research paper submissions and present her results verbally to a wider research team. The work she is conducting and the related work she will be reading is in the high level areas of bias in natual language processing and social media polarization. She will meet Tuesdays from 6-7 as well as frequently at other times with Prof. Matthews and a wider research team. . She will produce a web portfolio of her research work. This course is not lecture based. Some of the work Esma does will be group work done in collaboration with other students.

This 1 credit directed study is not intended to serve as one of the four Research-Oriented courses required in the CS PhD, but it will include reading and discussing research papers as well as conducting original research.

Grading: 50% Participation and Verbal Presentation + 50% Web Portfolio of Research Objectives: Conduct original research, gain skills in collection and anaysis of data including the production of automated analysis scripts. Read and discuss related work.

Demonstrable Outcomes: Submission of an ACM FAccT paper. Portfolio of scripts written/modified. Portfolio of data collected as well as visualizations and analysis of this data, likely well beyond what can be included in the ACM FAcct paper. Attendance at research group meetings. Oral presentation of research results.

Course Goals

Goals Achieved so far:

Participatory Approaches to Machine Learning Submission Is Machine Learning Speaking my Language? A Critical Look at NLP-Pipeline Across 8 Human languages
ACM FAccT Submission Bias in Natural Language Processing Across Human Languages
Gender Bias Research Documentation
Social Media Polarization about Covid-19

I have been part of a subgroup working on Social Media Polarization with Professor Matthews. I have been attending some of the group meetings and read soem papers related to the project

Group Meetings

Weekly group Meeting, Tuesday 6-7pm
Weekly subgroup(Human Languages subgroup) meeting, Monday at noon
Taking meeting notes and information dissimination about meeting updates

More Goals achieved:

Scripts
Wrote Python script to count #words and letters in text, Completed
Expansion/Extension of Classics Corpora
Added extra coulumn for gender of author. Further added more text with an aim to extend Classics Corpora.

Future Goals:

Converting scanned PDF content into text.
Work on experiments and writing paper regarding the Classics Corpora.
Collection of the text translated in most languages and calculating gender bias.
Arrangement of Classics Corpora with respect to different timelines to calculate and compare gender bias in definition words and profession words.