IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound

Document Type

Poster

Publication Date

Fall 2018

Abstract

Computers have been extremely useful in humanity’s quest for knowledge, performing calculations and other strenuous tasks in seconds. For a computer to perform the tasks, it requires a specific set of instructions, or code, to tell it what to do. These series of commands and instructions are strict, in that any syntactic error results in faulty, or zero functionality. Human language is very much unlike that of a computer, in that it can be grammatically incorrect, irregular, or even incomplete, yet another human may still get the point and understand the information being exchanged. A significant part about what makes us human is the ability to use and develop our dynamic language. When a computer is able to completely understand and mimic human language, we will likely have something closer to artificial intelligence than anything we’ve seen yet. Development in this area has lead to Natural Language Processing, or NLP. On March 31st2017, students, professors, and hobbyists alike gathered together at the HackOH5 Student Newspaper Hackathon to analyze 170,000+ pages of student newspapers from 5 colleges: Kenyon, Denison, Oberlin, Ohio Wesleyan, and the College of Wooster. Spanning over 160 years, the digitized libraries were filled with years of student coverage organized in a huge dataset of text and images. What can be done with all of this newly digitized information? NLP allows us to analyze, visualize, and contextualize this textual data. This project aims to analyze textual information recorded between 1970 and 2000 by three different colleges: Kenyon, Denison, and Oberlin. By using NLP, any word used by any school from any issue can be mapped to an n-dimensional semantic space where the distances between the words can be used to represent their semantic closeness. For example, words like student will be closely associated with professor, college, people, alumni, etc. By investigating specific words that are historically relevant, we can try to understand how each college might perceive certain events and compare them with each other.

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS
 

Rights Statement

In Copyright - Non-Commercial Use Permitted
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.