Clickbait Classification and Spoiling Using Natural Language Processing

TL;DR

This paper explores classifying clickbait types and spoiling their content using NLP techniques, including classifiers and large language models, to better understand and counteract sensationalized titles.

Contribution

It introduces two binary classifiers for clickbait type classification and compares question-answering and LLM approaches for spoiler generation, improving understanding of clickbait content.

Findings

Classifiers outperform baselines in clickbait type classification

Question-answering models effectively identify spoiler spans

Large language models' spoiler generation is limited by evaluation metrics

Abstract

Clickbait is the practice of engineering titles to incentivize readers to click through to articles. Such titles with sensationalized language reveal as little information as possible. Occasionally, clickbait will be intentionally misleading, so natural language processing (NLP) can scan the article and answer the question posed by the clickbait title, or spoil it. We tackle two tasks: classifying the clickbait into one of 3 types (Task 1), and spoiling the clickbait (Task 2). For Task 1, we propose two binary classifiers to determine the final spoiler type. For Task 2, we experiment with two approaches: using a question-answering model to identify the span of text of the spoiler, and using a large language model (LLM) to generate the spoiler. Because the spoiler is contained in the article, we frame the second task as a question-answering approach for identifying the starting and ending positions of the spoiler. We created models for Task 1 that were better than the baselines proposed by the dataset authors and engineered prompts for Task 2 that did not perform as well as the baselines proposed by the dataset authors due to the evaluation metric performing worse when the output text is from a generative model as opposed to an extractive model.