1,538-Word Taglish Pedagogical Sentiment Lexicon:
Year: 2026
Type: dataset
Abstract: This dataset repository contains the underlying data assets for the CAF-VADER (Custom-Augmented Filipino VADER) sentiment analysis framework: Taglish Pedagogical Sentiment Lexicon ($N = 1,538$ words): A domain-specific Filipino/Taglish dictionary extracted from unmapped baseline tokens in student course evaluations, featuring expert-validated sentiment polarities. Human Ground-Truth Benchmark ($N = 133$ comments): A multi-rater annotated gold-standard benchmark of bilingual qualitative student feedback evaluated independently by a panel of nine academic experts. These files support empirical research on positivity bias mitigation, neutral class recovery, and Explainable AI (XAI) in higher education quality assurance and teacher evaluations.
Author: Ortiz, Marie Grace
Institution: University of the Cordilleras
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W7204775346
