UTMN at SemEval-2020 Task 11: A Kitchen Solution to Automatic Propaganda Detection

TL;DR

This paper presents a quick, feature-based approach using logistic regression for propaganda detection in text, testing various data and feature configurations, achieving an F-score of 0.37 at SemEval-2020.

Contribution

It introduces a fast, feature adjustment method with per-token vectorization and simple classification for propaganda detection, emphasizing rapid hypothesis testing.

Findings

Achieved an F-score of 0.37 on SemEval-2020 Task 11

Analyzed the impact of class imbalance and feature variations

Demonstrated the effectiveness of simple logistic regression with feature tuning

Abstract

The article describes a fast solution to propaganda detection at SemEval-2020 Task 11, based onfeature adjustment. We use per-token vectorization of features and a simple Logistic Regressionclassifier to quickly test different hypotheses about our data. We come up with what seems to usthe best solution, however, we are unable to align it with the result of the metric suggested by theorganizers of the task. We test how our system handles class and feature imbalance by varying thenumber of samples of two classes (Propaganda and None) in the training set, the size of a contextwindow in which a token is vectorized and combination of vectorization means. The result of oursystem at SemEval2020 Task 11 is F-score=0.37.