# Posts of Peril: Detecting Information About Hazards in Text

arXiv: https://arxiv.org/abs/2405.17838 · HTML: https://mlsanity.com/paper/2405.17838/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 97 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks](https://mlsanity.com/paper/1701.05923/) (2017)
- [Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm](https://mlsanity.com/paper/1708.00524/) (2017)
- [Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks](https://mlsanity.com/paper/2306.07899/) (2023)
- [SpanEmo: Casting Multi-label Emotion Classification as Span-prediction](https://mlsanity.com/paper/2101.10038/) (2021)
- [Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign](https://mlsanity.com/paper/1802.04291/) (2018)
- [RTbust: Exploiting Temporal Patterns for Botnet Detection on Twitter](https://mlsanity.com/paper/1902.04506/) (2019)
- [Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion](https://mlsanity.com/paper/2210.15842/) (2022)
- [Unmasking the Web of Deceit: Uncovering Coordinated Activity to Expose Information Operations on Twitter](https://mlsanity.com/paper/2310.09884/) (2023)
- [Understanding and Detecting Dangerous Speech in Social Media](https://mlsanity.com/paper/2005.06608/) (2020)
- [Quantifying Valence and Arousal in Text with Multilingual Pre-trained Transformers](https://mlsanity.com/paper/2302.14021/) (2023)
- [SeerNet at SemEval-2018 Task 1: Domain Adaptation for Affect in Tweets](https://mlsanity.com/paper/1804.06137/) (2018)
- [Socio-Linguistic Characteristics of Coordinated Inauthentic Accounts](https://mlsanity.com/paper/2305.11867/) (2023)
- [Quantifying the Effect of Sentiment on Information Diffusion in Social Media](https://mlsanity.com/paper/1506.06072/) (2015)
- [Coordinated Activity Modulates the Behavior and Emotions of Organic Users: A Case Study on Tweets about the Gaza Conflict](https://mlsanity.com/paper/2402.05873/) (2024)
- [Quantifying the Impact of Cognitive Biases in Question-Answering Systems](https://mlsanity.com/paper/1909.09633/) (2019)

## Abstract (arXiv)

Socio-linguistic indicators of affectively-relevant phenomena, such as emotion or sentiment, are often extracted from text to better understand features of human-computer interactions, including on social media. However, an indicator that is often overlooked is the presence or absence of information concerning harms or hazards. Detecting such indicators in text is important because substantial research demonstrates that negative events are more likely to be attended to, and more likely to elicit a response. In addition, statements about hazards are often found to be more believable than statements about benefits. Here, we develop a new model to detect information concerning hazards, trained on a new collection of annotated X posts. We show that not only does this model perform well, but that the hazard information it extracts is not strongly correlated with such widely used indicators as moral outrage, sentiment, and emotions. To demonstrate the utility of our tool, we apply it to two datasets of X posts that discuss important geopolitical events, namely the 2023 Israel-Hamas war and the 2022 French national election. In both cases, we find that hazard information, especially information concerning conflict, is common. We extract accounts associated with information campaigns from each data set to explore how information about hazards could be used to attempt to influence geopolitical events. We find that inorganic accounts representing the viewpoints of weaker sides in a conflict often discuss hazards to civilians, potentially as a way to elicit aid for the weaker side. Moreover, the rate at which these hazards are mentioned differs markedly from organic accounts, likely reflecting information operators' efforts to frame the given geopolitical event for strategic purposes. These results are first steps towards exploring hazards within an information warfare environment.