This repository contains my work for LTCS180.
Project: Investigate the sentiment of news sources in different languages on the same event
Homework
- Week 2: visualizing networks of character interactions
- Week 4/5: exploring texts using the vector space model
- Week 7: narrating with maps
Resources:
Course Description:
This class introduces students to the analysis of literary and historical texts using computational methods. The course is designed for students who already have some programming knowledge and want to use such skills to understand humanistic texts and data better. The class uses the Python programming language.
The course is structured around projects students begin developing from the beginning of the quarter (either in groups or individually) and is organized into four modules. In the first, students familiarize themselves with basic techniques of text mining of humanities data. In the second module, students apply social network theory (graph theory) to literary and historical texts. Using Python libraries for the modeling of social networks, students learn to formalize social relationships of fictional and historical characters, specifically how actors relate to each other in a text. In the third module, students become familiarized with vector space models that can identify text similarities and classify documents according to topics, literary genre, and authorship. The fifth module introduces the extraction and analysis of Named Entities in literary and historical texts: named entities are nouns that refer to things in real and fictional worlds. In the final part of the course, students are introduced to the modeling of topics in literary texts.
All the techniques learned in this class can be applied to other fields outside the humanities, including analyzing scientific literature, news, text produced in social media, internet reviews, etc.