"My life is miserable, have to sign 500 autographs everyday": Exposing Humblebragging, the Brags in Disguise

TL;DR

This paper introduces the novel task of automatically detecting humblebragging in text, formalizes its definition, and evaluates various models and humans on this challenging linguistic phenomenon, providing a new dataset and baseline performance.

Contribution

It is the first to formalize humblebragging detection, create a dataset, and compare machine learning models with human performance on this nuanced task.

Findings

Best model achieves F1-score of 0.88

Humans find humblebragging detection non-trivial

Deep learning models outperform traditional ML methods

Abstract

Humblebragging is a phenomenon in which individuals present self-promotional statements under the guise of modesty or complaints. For example, a statement like, "Ugh, I can't believe I got promoted to lead the entire team. So stressful!", subtly highlights an achievement while pretending to be complaining. Detecting humblebragging is important for machines to better understand the nuances of human language, especially in tasks like sentiment analysis and intent recognition. However, this topic has not yet been studied in computational linguistics. For the first time, we introduce the task of automatically detecting humblebragging in text. We formalize the task by proposing a 4-tuple definition of humblebragging and evaluate machine learning, deep learning, and large language models (LLMs) on this task, comparing their performance with humans. We also create and release a dataset called HB-24, containing 3,340 humblebrags generated using GPT-4o. Our experiments show that detecting humblebragging is non-trivial, even for humans. Our best model achieves an F1-score of 0.88. This work lays the foundation for further exploration of this nuanced linguistic phenomenon and its integration into broader natural language understanding systems.