README.md

metadata

title: 'LexCAT: Taglish Sentiment Analysis'
colorFrom: blue
colorTo: purple
sdk: gradio
app_file: app.py
pinned: true
license: cc-by-4.0
sdk_version: 5.47.0

LexCAT: Lexicon-Enhanced Sentiment Analysis for Tagalog–English Code-Switched Text

Author: Glenn Marcus D. Cinco
Institution: Mapúa University
Thesis: LexCAT: A Lexicon-Based Approach for Code-Switching Analysis with Transformers Using XLM-RoBERTa and LexiLiksik
Model: Fine-tuned XLM-RoBERTa + LexiLiksik lexicon
Dataset: FiReCS (10,487 Taglish reviews)
Accuracy: 84.31%
Specialty: Detects intra-sentential sentiment shifts (e.g., “Maganda pero expensive” → Negative)

---

🧠 Try It Out

Enter any Taglish sentence — LexCAT will predict its sentiment and show confidence scores.

Examples:

• “sobrang lambot ng burger pero expensive tlga” → ❌ Negative
• “Salamat sa nyo nagana nmn po sya kaya super thank you ako” → ✅ Positive
• “Ang ganda ng service, one star!” → ❌ Negative

---

📚 Model Card

See full documentation, methodology, and citation at:
👉 https://huggingface.co/your-hf-username/LexCAT-LexiLiksik-Final

---

🎓 Academic Use

Cite this model in your research:

@mastersthesis{cinco2025lexcat,
  author = {Cinco, Glenn Marcus D.},
  title = {LexCAT: A Lexicon-Based Approach for Code-Switching Analysis with Transformers Using XLM-RoBERTa and LexiLiksik},
  school = {Mapúa University},
  year = {2025}
}