Repository of DSoC 2025

This repository contains data, metadata, and tests used for the study Digital Specters of Colony: Securitization, Moros, and the Age of Social Media by Frances Cruz. It contains the following folders: 1) Metadata Metadata of the speech corpus Metadata of the news corpus Link to the k1 social media corpus and data paper 2) R tests Folder of multinomial tests Associated with Chapter 6.1.2 Folder of linear model and rank-based estimation for linear models (Rfit) results Associated with Chapter 6.1.3 Folder of binomial tests Associated with Chapter 6.1.3 Folder of paired tests Associated with Chapter 6.1.1 and Chapter 6.2 ck1 based on Cruz (2024) (zenodo.org/doi/10.5281/zenodo.10971589) 3) Python tests Folder of word2vec tests for the news corpus Associated with Chapter 6.2 Folder of word2vec tests for the social media corpus Associated with Chapter 6.2 Folder of emotion and sentiment classification Associated with Chapter 6.1.1 Folder of key word removal code Associated with 6.1.1 4) k1 Folder of fastText word embedding results Associated with Chapter 5.3.2 Folder of search terms and for k1 creation Associated with Chapter 5.3.2 Folder of language classification Associated with Chapter 5.2 5) ReadMe References These tests make use of the dataset found here: zenodo.org/doi/10.5281/zenodo.10971589 And the following papers: Cruz, F. A. (2024).

A Multilingual Collection of Facebook Comments on the Moro Identity and Armed Conflict in the Southern Philippines. Journal of Open Humanities Data, 10(1), 41. DOI: 10.5334/johd.219 Cruz, F. & Kestemont, M. (2022).