Case study

Political Misinformation Classifier

Applied ML: BERT fine-tuning, evaluation discipline, honest limitations

ML work with an engineering mindset: the artifact is not only weights—it is the preprocessing contract, evaluation notebook, and clear statement of where the model will lie.

Academic

Python BERT NLP Machine learning Model evaluation Data pipelines

Problem

Keyword filters miss nuanced propaganda. The project tested whether a fine-tuned transformer could add signal while staying humble about politics, language shift, and dataset bias.

Model pipeline

Text preprocessing aligned to tokenizer and task (no silent truncation surprises).
Fine-tuned BERT classifier for political misinformation labels.
Versioned training scripts and frozen splits for reproducible comparison.

Evaluation

Reported precision/recall tradeoffs, confusion patterns, and qualitative failures—not a single leaderboard number. The goal is to know when the model should refuse to classify.

Limitations

Temporal and demographic drift break political classifiers silently. These models belong behind human review, monitoring, and governance—not as autonomous truth engines.

What I learned

Most of the “backend” in ML is evaluation and data contracts; the forward pass is the short part.